The DOI matches its Crossref record, with a small difference in title or year; 31 of the 31 references it cites were found in a registry or an index; 2 of the 14 sources its claims cite were checked for support.
ImageNet classification with deep convolutional neural networks
Open accessAbstract
We trained a large, deep convolutional neural network to classify the 1.2 million high-resolution images in the ImageNet LSVRC-2010 contest into the 1000 different classes. On the test data, we achieved top-1 and top-5 error rates of 37.5% and 17.0%, respectively, which is considerably better than the previous state-of-the-art. The neural network, which has 60 million parameters and 650,000 neurons, consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully connected layers with a final 1000-way softmax. To make training faster, we used non-saturating neurons and a very efficient GPU implementation of the convolution operation. To reduce overfitting in the fully connected layers we employed a recently developed regularization method called "dropout" that proved to be very effective. We also entered a variant of this model in the ILSVRC-2012 competition and achieved a winning top-5 test error rate of 15.3%, compared to 26.2% achieved by the second-best entry.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
29 No basis given · 22 Own result · 19 Own interpretation · 4 No full text of the sources · 3 Sources not found · 2 Supported · 2 Not checked yet · 1 Own method
Every source the paper cites for this claim was checked and supports it.
In the paper
“This technique reduces complex co adaptations of neurons, since a neuron cannot rely on the presence of particular other neurons.”
§ ImageNet Classification with Deep Convolutional Neural Networks > 5.2. Dropout
What the sources say
- Supportedcites [12] 12. Hinton, G., Srivastava, N., Krizhevsky, A., Sutskever, I., Salakhutdinov, R. Improving neural networks by preventing co-adaptation of feature detectors. arXiv preprint arXiv:1207.0580 (2012). source
The paper states on p. 1 that dropout prevents complex co-adaptations by randomly omitting hidden units, so a hidden unit cannot rely on other hidden units being present. This directly supports the citing sentence. (LLM, conf=0.95)
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
Every source the paper cites for this claim was checked and supports it.
In the paper
“There is, however, a very efficient version of model combination that only costs about a factor of two during training.”
§ ImageNet Classification with Deep Convolutional Neural Networks > 5.2. Dropout
What the sources say
- Supportedcites [12] 12. Hinton, G., Srivastava, N., Krizhevsky, A., Sutskever, I., Salakhutdinov, R. Improving neural networks by preventing co-adaptation of feature detectors. arXiv preprint arXiv:1207.0580 (2012). source
The paper describes dropout as an efficient way to combine many neural-network models (p. 1). In F.6 Training (p. 17), it reports that ImageNet training took roughly four days with dropout versus two days without it, supporting the approximate factor-of-two training cost. (LLM, conf=0.88)
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“This scheme reduces our top-1 and top-5 error rates by 1.7% and 1.2%, respectively, as compared with a net with half as many kernels in each convolutional layer trained on one GPU.”
§ ImageNet Classification with Deep Convolutional Neural Networks > 4.2. Training on multiple GPUs
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“The size of our network made overfitting a significant problem, even with 1.2 million labeled training examples”
§ ImageNet Classification with Deep Convolutional Neural Networks > 2. INTRODUCTION
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“So these data augmentation schemes are, in effect, computationally free.”
§ ImageNet Classification with Deep Convolutional Neural Networks > 5.1. Data augmentation
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“we found that removing any convolutional layer (each of which contains no more than 1% of the model's parameters) resulted in inferior performance.”
§ ImageNet Classification with Deep Convolutional Neural Networks > 2. INTRODUCTION
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“This scheme reduces the top-1 and top-5 error rates by 0.4% and 0.3%, respectively, as compared with the non overlapping scheme s = 2, z = 2, which produces output of equivalent dimensions.”
§ ImageNet Classification with Deep Convolutional Neural Networks > 5.1. Data augmentation
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“This increases the size of our training set by a factor of 2048”
§ ImageNet Classification with Deep Convolutional Neural Networks > 5.1. Data augmentation
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Deep CNNs with ReLUs train several times faster than their equivalents with tanh units.”
§ ImageNet Classification with Deep Convolutional Neural Networks > 4.1. Rectified Linear Unit nonlinearity
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“However, we still find that the following local normalization scheme aids generalization.”
§ ImageNet Classification with Deep Convolutional Neural Networks > 4.3. Local response normalization
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- It may state two separate claims as one. 18
- Probably not a substantial claim. 26
- The quote only partly states this claim. 2
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Although the 1000 classes of ILSVRC make each training example impose 10 bits of constraint on the mapping from image to label, this turns out to be insufficient to learn so many parameters without considerable overfitting.”
§ ImageNet Classification with Deep Convolutional Neural Networks > 5. REDUCING OVERFITTING
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“though the resulting training examples are, of course, highly inter dependent.”
§ ImageNet Classification with Deep Convolutional Neural Networks > 5.1. Data augmentation
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“On the test data, we achieved top-1 and top-5 error rates of 37.5% and 17.0%, respectively”
§ ImageNet Classification with Deep Convolutional Neural Networks > Abstract
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“We generally observe during training that models with overlapping pooling find it slightly more difficult to overfit.”
§ ImageNet Classification with Deep Convolutional Neural Networks > 5.1. Data augmentation
plainconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“a four-layer CNN achieved a 13% test e r r o r r a t e w i t h o u t n o r m a l i z a t i o n a n d 1 1 % w i t h normalization.”
§ ImageNet Classification with Deep Convolutional Neural Networks > 4.3. Local response normalization
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“so we used several effective techniques for preventing overfitting”
§ ImageNet Classification with Deep Convolutional Neural Networks > 2. INTRODUCTION
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Response normalization reduces our top-1 and top-5 error rates by 1.4% and 1.2%, respectively.”
§ ImageNet Classification with Deep Convolutional Neural Networks > 4.3. Local response normalization
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“The two-GPU net takes slightly less time to train than the one-GPU net.”
§ ImageNet Classification with Deep Convolutional Neural Networks > 4.2. Training on multiple GPUs
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Our network contains a number of new and unusual features which improve its performance and reduce its training time”
§ ImageNet Classification with Deep Convolutional Neural Networks > 2. INTRODUCTION
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Without this scheme, our network suffers from substantial overfitting, which would have forced us to use much smaller networks.”
§ ImageNet Classification with Deep Convolutional Neural Networks > 5.1. Data augmentation
hedgeddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“For example, only other types of cat are considered plausible labels for the leopard.”
§ ImageNet Classification with Deep Convolutional Neural Networks > Model
plainSingle case- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“This initialization accelerates the early stages of learning by providing the ReLUs with positive inputs.”
§ ImageNet Classification with Deep Convolutional Neural Networks > 6. DETAILS OF LEARNING
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Notice that at the pixel level, the retrieved training images are generally not close in L2 to the query images in the first column.”
§ ImageNet Classification with Deep Convolutional Neural Networks > Model
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Training one CNN, with an extra sixth convolutional layer over the last pooling layer, to classify the entire ImageNet Fall 2011 release (15M images, 22K categories), and then”
§ ImageNet Classification with Deep Convolutional Neural Networks > Model
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The quote only partly states this claim.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Our top-1 and top-5 error rates on this dataset are 67.4% and 40.9%, attained by the net described above but with an additional, sixth convolutional layer over the last pooling layer.”
§ ImageNet Classification with Deep Convolutional Neural Networks > Model
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
- Rests on an assumption: The Fall 2009 ImageNet split used by the authors, which differs from previous authors' splits, does not affect the results appreciably.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“This kind of specialization occurs during every run and is independent of any particular random weight initialization (modulo a renumbering of the GPUs).”
§ ImageNet Classification with Deep Convolutional Neural Networks > Model
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds. It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The magnitude of the effect demonstrated here varies with network architecture, but networks with ReLUs consistently learn several times faster than equivalents with saturating neurons.”
§ ImageNet Classification with Deep Convolutional Neural Networks > 9. EPILOGUE
boosteddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Our network achieves top-1 and top-5 test set error rates of 37.5% and 17.0%, respectively.”
§ ImageNet Classification with Deep Convolutional Neural Networks > 7. RESULTS
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Averaging the predictions of five similar CNNs gives an error rate of 16.4%.”
§ ImageNet Classification with Deep Convolutional Neural Networks > Model
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The quote only partly states this claim.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“In the remainder of this paragraph, we use validation and test error rates interchangeably because in our experience they do not differ by more than 0.1% (see Table 2).”
§ ImageNet Classification with Deep Convolutional Neural Networks > Model
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Notice that even off-center objects, such as the mite in the top-left, can be recognized by the net.”
§ ImageNet Classification with Deep Convolutional Neural Networks > Model
plainSingle case- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“All of our experiments suggest that our results can be improved simply by waiting for faster GPUs and bigger datasets to become available.”
§ ImageNet Classification with Deep Convolutional Neural Networks > 2. INTRODUCTION
hedgeddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“ReLUs have the desirable property that they do not require input normalization to prevent them from saturating.”
§ ImageNet Classification with Deep Convolutional Neural Networks > 4.3. Local response normalization
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
None of the sources cited for this claim have been checked yet.
In the paper
“Convolutional neural networks (CNNs) constitute one such class of models.9,15,17,19,21,26,32”
§ ImageNet Classification with Deep Convolutional Neural Networks > 2. INTRODUCTION
What the sources say
- Not checked — no full text of the sourcecites [9] 9. Fukushima, K. Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position. Biol. Cybern. 36, 4 (1980), 193-202. source
- Not checked yetcites [15] 15. Krizhevsky, A. Convolutional deep belief networks on cifar-10. Unpublished manuscript, 2010.
- Not checked yetcites [17] 17. LeCun, Y., Boser, B., Denker, J., Henderson, D., Howard, R., Hubbard, W., Jackel, L., et al. Handwritten digit recognition with a back-propagation network. In Advances in Neural Information Processing Systems (1990).
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“However, the immense complexity of the object recognition task means that this problem cannot be specified even by a dataset as large as ImageNet, so our model should also have lots of prior knowledge to compensate for all the data we do not have.”
§ ImageNet Classification with Deep Convolutional Neural Networks > 2. INTRODUCTION
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Thus, compared to standard feedforward neural networks with similarly sized layers, CNNs have much fewer connections and parameters and so they are easier to train, while their theoretically best performance is likely to be only slightly worse.”
§ ImageNet Classification with Deep Convolutional Neural Networks > 2. INTRODUCTION
hedgeddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“methods that require careful hand-engineering by a programmer who understands the domain do not scale as well as methods that replace the programmer with a powerful general-purpose learning procedure.”
§ ImageNet Classification with Deep Convolutional Neural Networks > 1. PROLOGUE
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper may give no reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Luckily, current GPUs, paired with a highly optimized implementation of 2D convolution, are powerful enough to facilitate the training of interestinglylarge CNNs”
§ ImageNet Classification with Deep Convolutional Neural Networks > 2. INTRODUCTION
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“they also make strong and mostly correct assumptions about the nature of images (namely, stationarity of statistics and locality of pixel dependencies).”
§ ImageNet Classification with Deep Convolutional Neural Networks > 2. INTRODUCTION
boosted- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Despite the attractive qualities of CNNs, and despite the relative efficiency of their local architecture, they have still been prohibitively expensive to apply in large scale to highresolution images.”
§ ImageNet Classification with Deep Convolutional Neural Networks > 2. INTRODUCTION
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds.
In the paper
“ImageNet, 7 which consists of over 15 million labeled high-resolution images in over 22,000 categories.”
§ ImageNet Classification with Deep Convolutional Neural Networks > 2. INTRODUCTION
What the sources say
- Not checked — no full text of the sourcecites [7] 7. Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., Fei-Fei, L. ImageNet: A large-scale hierarchical image database. In CVPR09 (2009). source
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“which is considerably better than the previous state-of-the-art”
§ ImageNet Classification with Deep Convolutional Neural Networks > Abstract
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“With enough computation and enough data, learning beats programming for complicated tasks that require the integration of many different, noisy cues.”
§ ImageNet Classification with Deep Convolutional Neural Networks > 1. PROLOGUE
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper may give no reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“and recent datasets such as ImageNet contain enough labeled examples to train such models without severe overfitting.”
§ ImageNet Classification with Deep Convolutional Neural Networks > 2. INTRODUCTION
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“for deep neural networks to shine, they needed far more labeled data and hugely more computation.”
§ ImageNet Classification with Deep Convolutional Neural Networks > 1. PROLOGUE
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“If at least some training examples produce a positive input to a ReLU, learning will happen in that neuron.”
§ ImageNet Classification with Deep Convolutional Neural Networks > 4.3. Local response normalization
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“To learn about thousands of objects from millions of images, we need a model with a large learning capacity.”
§ ImageNet Classification with Deep Convolutional Neural Networks > 2. INTRODUCTION
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim.
What the paper did — it cites no source for this, so there is none to check. The quote shows it is in the paper.
In the paper
“The constants k, n, α, and β are hyperparameters whose values are determined using a validation set”
§ ImageNet Classification with Deep Convolutional Neural Networks > 4.3. Local response normalization
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“However, on this dataset the primary concern is preventing overfitting, so the effect they are observing is different from the accelerated ability to fit the training set which we report when using ReLUs.”
§ ImageNet Classification with Deep Convolutional Neural Networks > 4.1. Rectified Linear Unit nonlinearity
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
In the paper
“since then the best published results are 45.7% and 25.7% with an approach that averages the predictions of two classifiers trained on Fisher Vectors (FVs) computed from two types of densely sampled features.29”
§ ImageNet Classification with Deep Convolutional Neural Networks > 7. RESULTS
What the sources say
- Not checked — no full text of the sourcecites [29] 29. Sánchez, J., Perronnin, F. High- dimensional signature compression for large-scale image classification. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2011 (2011). IEEE, 1665-1672. source
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A claim is checked only against the cited paper’s full text, never its abstract, and none is available for its sources.
In the paper
“Combining the predictions of many different models is a very successful way to reduce test errors, 1, 3”
§ ImageNet Classification with Deep Convolutional Neural Networks > 5.2. Dropout
What the sources say
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“but it appears to be too expensive for big neural networks that already take several days to train.”
§ ImageNet Classification with Deep Convolutional Neural Networks > 5.2. Dropout
hedgeddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim.
In the paper
“The best published results on this dataset are 78.1% and 60.9%.23”
§ ImageNet Classification with Deep Convolutional Neural Networks > Model
What the sources say
- Not checked — no full text of the sourcecites [23] 23. Mensink, T., Verbeek, J., Perronnin, F., Csurka, G. Metric learning for large scale image classification: Generalizing to new classes at near-zero cost. In ECCV -European Conference on Computer Vision (Florence, Italy, Oct. 2012). source
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
The paper relies on this without support.
Objects in realistic settings exhibit considerable variability.
“But objects in realistic settings exhibit considerable variability”
The paper relies on this without support.
Object identity is invariant to changes in the intensity and color of illumination.
“object identity is invariant to changes in the intensity and color of the illumination.”
The paper relies on this without support.
The Fall 2009 ImageNet split used by the authors, which differs from previous authors' splits, does not affect the results appreciably.
“Since there is no established test set, our split necessarily differs from the splits used by previous authors, but this does not affect the results appreciably.”
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“In the field of DL, the CNN is the most famous and commonly employed algorithm [30, 71–75].”
From Review of deep learning: concepts, CNN architectures, challenges, applications, future directions (2021) · cites this paper as [30]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Fully convolutional neural networks (fCNNs) have provided state-of-the-art performance for object classification and image segmentation (1).”
From Fully automated, real-time 3D ultrasound segmentation to estimate first trimester placental volume using deep learning (2018) · cites this paper as [1]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“The first wave saw the emergence of deep learning as the dominant paradigm for analyzing high-dimensional biological data.”
From The next paradigm in bioinformatics: a review of multi-agent systems and foundational models for end-to-end scientific discovery (2026) · cites this paper as [1]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“Krizhevesky et al. [30] first proposed AlexNet and consequently improved the CNN learning ability by increasing its depth and implementing several parameter optimization strategies.”
From Review of deep learning: concepts, CNN architectures, challenges, applications, future directions (2021) · cites this paper as [30]
The cited source says what the claim attributes to it.
In the citing paper
“In deep CNN architecture, AlexNet is highly respected [30], as it achieved innovative results in the fields of image recognition and classification.”
From Review of deep learning: concepts, CNN architectures, challenges, applications, future directions (2021) · cites this paper as [30]
The cited source says what the claim attributes to it.
In the citing paper
“Many CNN models, e.g. AlexNet [30], GoogleNet [103], and ResNet [37], have been trained on large datasets such as ImageNet for image recognition purposes.”
From Review of deep learning: concepts, CNN architectures, challenges, applications, future directions (2021) · cites this paper as [30]
The cited source says what the claim attributes to it.
In the citing paper
“To avoid model-specific biases, two different AI models, AlexNet [22] and VGG16 [38], were selected for classification.”
From Study on the Helpfulness of Explainable Artificial Intelligence (2024) · cites this paper as [22]
The cited source says what the claim attributes to it.
In the citing paper
“In particular, the choice of this specific size is based on the fact that the AlexNet 34 (and also similar CNN architectures) has been shown to offer satisfactory performances with an input matrix of that size or very similar, albeit for different types of problems with respect to the one presented in this work (e.g., image classification).”
The cited source says what the claim attributes to it.
In the citing paper
“Jung et al. [21] found that a reduction in accuracy does not occur when using only four bits for both weight and activation parameters, even for the ImageNet dataset [32].”
From Zero-Centered Fixed-Point Quantization With Iterative Retraining for Deep Convolutional Neural Network-Based Object Detectors (2021) · cites this paper as [32]
The cited source says what the claim attributes to it.
In the citing paper
“Feature-based approaches [17,18,19] commonly employ networks pre-trained on ImageNet [20] to map original images into a more distinguishable feature space. These methods are typically characterized by low training costs and outstanding performance.”
From An Unsupervised Method for Industrial Image Anomaly Detection with Vision Transformer-Based Autoencoder (2024) · cites this paper as [20]
The cited source says what the claim attributes to it.
In the citing paper
“Over the past several years, the successes of deep learning on visual tasks has critically relied on convolutional neural networks [20, 16].”
From Do Vision Transformers See Like Convolutional Neural Networks? (2021) · cites this paper as [20]
The cited source says what the claim attributes to it.
In the citing paper
“A common perception metric is the Learned Perceptual Image Patch Similarity (LPIPS) which uses pre-trained deep neural network backbones such as VGG [9] and AlexNet [22].”
From MTReD: 3D Reconstruction Dataset for Fly-over Videos of Maritime Domain (2025) · cites this paper as [22]
The cited source says what the claim attributes to it.
In the citing paper
“Starting with the the success of AlexNet [5] in the ILSVRC challenge [6] in 2012, deep learning models have been outperforming traditional approaches on a number of computer vision problems.”
From Satellite Pose Estimation Challenge: Dataset, Competition Design, and Results (2020) · cites this paper as [5]
The check wasn’t confident either way, so it gives no verdict — never disputed.
In the citing paper
“Unfortunately, it has been acknowledged that the performance of those hashing schemes may degrade significantly if the projected dimensions are imbalanced [4], [6], [13], i.e., their variances vary a lot.”
From Unsupervised Deep Video Hashing via Balanced Code for Large-Scale Video Retrieval (2019) · cites this paper as [6]
Experimental — accuracy not yet measuredThe check wasn’t confident either way, so it gives no verdict — never disputed.
In the citing paper
“When convolutional RBMs are stacked together, they form convolutional deep belief networks [22].”
From Multimodal emotion recognition using deep learning architectures (2016) · cites this paper as [22]
Experimental — accuracy not yet measuredIn the citing paper
“Convolutional neural networks (CNNs), built for spatial data, have demonstrated performance comparable to that of specialists in cancer detection and tumor segmentation [15,16,17,18,19,20].”
From Artificial Intelligence in Clinical Oncology: From Productivity Enhancement to Creative Discovery (2025) · cites this paper as [16]
In the citing paper
“When a low-capacity model, such as AlexNet, is used for pre-training, little improvement can be obtained when compared to the Resnet50 family [26].”
From Self-supervised learning: A succinct review (2023) · cites this paper as [26]
In the citing paper
“Since its introduction by Krizhevsky et al. [7] in 2012, the CNN model has been successfully applied to a wide range of multimodal applications, such as image dehazing [239, 240] and human activity recognition [241].”
From A survey on deep multimodal learning for computer vision: advances, trends, applications, and datasets (2022) · cites this paper as [7]
In the citing paper
“The AlexNet architecture was published in [4], achieved significantly improved performance over the other non-deep learning methods for ImageNet Large Scale Visual Recognition Challenge (ILSVRC) 2012.”
From Deep convolutional neural networks for computer-aided detection: cnn architectures, dataset characteristics and transfer learning (2016) · cites this paper as [4]
In the citing paper
“Deep CNN architectures with 8, even 22 layers [4], [33], can be useful even for CADe problems where the available training datasets are limited.”
From Deep convolutional neural networks for computer-aided detection: cnn architectures, dataset characteristics and transfer learning (2016) · cites this paper as [4]
In the citing paper
“focusing on AI and deep learning architectures that have already become the de facto approach.”
From AI in Medical Imaging Informatics: Current Challenges and Future Directions (2020) · cites this paper as [101]
In the citing paper
“Since then, fueled by the revolutionary results of AlexNet [101] and incarnations of patch-based adaptations of Deep Boltzmann Machines and stacked autoencoders, deep learning based segmentation of anatomy and pathology has witnessed a revolution (see also Table II), where for some tasks now we observe human level performance [102].”
From AI in Medical Imaging Informatics: Current Challenges and Future Directions (2020) · cites this paper as [101]
In the citing paper
“ReLU significantly increases the rate of con-vergence of stochastic gradient descent in comparison with the sigmoid [26].”
From Real-time system for automatic cold strip surface defect detection (2019) · cites this paper as [26]
In the citing paper
“Real-time volume estimation has been achieved using fully convolutional neural networks (FCNNs) [11] to produce state-of-the-art performance in a range of medical imaging modalities [12].”
From Fully Automated 3-D Ultrasound Segmentation of the Placenta, Amniotic Fluid, and Fetus for Early Pregnancy Assessment (2021) · cites this paper as [11]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Each contradiction between two passages listed here was confirmed by an independent check.
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ ImageNet Classification with Deep Convolutional Neural Networks > 2. INTRODUCTION
“we found that removing any convolutional layer (each of which contains no more than 1% of the model's parameters) resulted in inferior performance.”
§ ImageNet Classification with Deep Convolutional Neural Networks > 4.5. Overall architecture
“The third convolutional layer has 384 kernels of size 3 × 3 × 256”
Citations
Cites
Breiman, L. (2001) · Machine Learning · doi:10.1023/a:1010933404324 · Cited by 133,538
ImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333
Going deeper with convolutions
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298594 · Cited by 48,562
Learning Multiple Layers of Features from Tiny Images
Krizhevsky, A. (2024) · doi:10.57702/zp44cu3g · Cited by 23,889
Self-citationLearning Internal Representations by Error Propagation
Rumelhart, D. E., Hinton, G. E., & Williams, R. J. (1985) · doi:10.21236/ada164453 · Cited by 16,501
Self-citation(2010) · International Conference on Machine Learning · Cited by 13,995
Self-citationImproving neural networks by preventing co-adaptation of feature detectors
Hinton, G. E., Srivastava, N., Krizhevsky, A., Sutskever, I., & Salakhutdinov, R. R. (2012) · arXiv · doi:10.48550/arxiv.1207.0580 · Cited by 6,382
Self-citationFukushima, K. (1980) · Biological Cybernetics · doi:10.1007/bf00344251 · Cited by 5,759
LabelMe: A Database and Web-Based Tool for Image Annotation
Russell, B. C., Torralba, A., Murphy, K. P., & Freeman, W. T. (2008) · International Journal of Computer Vision · doi:10.1007/s11263-007-0090-8 · Cited by 4,210
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2015) · arXiv · doi:10.48550/arxiv.1512.03385 · Cited by 4,196
Research works printed but not linked: 13
- Berg A., 2010, Large scale visual recognition challenge
- Deng J., 2009, CVPR09
- Krizhevsky A., 2009, Department of Computer Science
- Krizhevsky A., 2010, Convolutional deep belief networks on cifar-10. Unpublished manuscript
- Krizhevsky A., 2011, ESANN
- LeCun Y., 1990, Advances in Neural Information Processing Systems
- LeCun Y., 1985, Une procedure d'apprentissage pour reseau a seuil asymmetrique (a learning scheme for asymmetric threshold networks)
- 10.5555/1896300.1896315 · DOI
- Mensink T., 2012, Italy
- 10.5555/3104322.3104425 · DOI
- Rumelhart D.E., 1985, DTIC Document
- 10.5555/938980.939477 · DOI
- Werbos P., 1974, Beyond regression: New tools for prediction and analysis in the behavioral sciences
Cited by
Sorted by citations
Items 106,501–106,600 of 108,435
Glandorf, P., & Rosenhahn, B. (2025) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw69036.2025.00316
“In this experiment, we evaluate our pruning method P3B on dataset Imagenet-1K [28], using the backbones of Deit Tiny, Small and Base [45] as model.”
PASTA: A Modular Program Analysis Tool Framework for Accelerators
Lin, M., Jeon, H., & Zhou, K. (2026) · Proceedings of the CGO/Proceedings of the ... CGO · doi:10.1109/cgo68049.2026.11395237
“We studied six widely used DL models—AlexNet [41], ResNet18 [42], ResNet34 [42], GPT-2 [43], BERT [44], and Whisper [45]—as detailed in Table IV.”
FaceScanPaliGemma multi-agent vision language models for facial attribute recognition
AlDahoul, N., Tan, M. J. T., Kasireddy, H. R., & Zaki, Y. (2026) · Scientific Reports · doi:10.1038/s41598-026-39584-3 · Cited by 17
“The accuracy of fine-tuned emotion-PaliGemma in FaceScanPaliGemma is higher than that of AlexNet CNN with the Weighted-Loss Method 23 and Vision Transformer (ViT-Base) 21 even though it was trained on only 3700 images per category from the AffectNet dataset.”
An Efficient YOLOv8-Based Framework for Traffic Sign Detection Under Adverse Weather Conditions
Ou, Y., He, X., Chuai, Q., et al. (2025) · International Conference on Robotics, Intelligent Control and Artificial Intelligence (RICAI) · doi:10.1109/ricai68060.2025.11385287
“In particular, the rapid development of convolutional neural networks (CNNs) [19], [20] has greatly enhanced the capability of object detection models, making them increasingly applicable to real-world scenarios.”
AIM 2025 Challenge on High FPS Motion Deblurring: Methods and Results
Ciubotariu, G., Vasluianu, F.-A., Zhou, Z., et al. (2025) · IEEE/CVF International Conference on Computer Vision Workshops (ICCVW) · doi:10.1109/iccvw69036.2025.00586
Enabling At-Home Gait Monitoring for Parkinson’s Disease
Song, H., & Atmosukarto, I. (2025) · IEEE International Conference on Service Operations and Logistics, and Informatics (SOLI) · doi:10.1109/soli66289.2025.11396168
“Convolutional Neural Networks (CNNs) [22], [23] paved the way for modern frameworks such as OpenPose [24], MediaPipe [25], and HRNet [26].”
Hiwase, K., Rewatkar, R. M., Langote, M., Gote, P. M., Yesankar, P., & Zode, P. P. (2025) · DMIHER International Conference on Artificial Intelligence in Healthcare, Education and Industry (IDICAIHEI) · doi:10.1109/idicaihei65991.2025.11379131
“CNN models are capable of effectively handling a wide range of image classification issues [15], [16], [17], and [18].”
Kaur, S., Singh, P., Kaur, N., Ray, N. C., & Singh, S. (2025) · IEEE Uttar Pradesh Section Women in Engineering International Conference on Electrical, Electronics and Computer Engineering (UPWIECON) · doi:10.1109/upwiecon67212.2025.11390143 · Cited by 1
“• Computer Vision Layer: Real-time fabric inspection using Convolutional Neural Networks (CNNs) and object detection algorithms like YOLO [20], [21].”
NeuReg: Domain-Invariant Brain Registration Across Species and Modalities
Razzaq, T., & Iqbal, A. (2025) · IEEE/CVF International Conference on Computer Vision Workshops (ICCVW) · doi:10.1109/iccvw69036.2025.00606
“…deviation of the patch, as governed by the following equations z = max { σ t 1 , σ t 2 , . . . , σ t n } (3) Existing pre-processing contrast normalization techniques, including local contrast normalization (LCN) [14] and lo-cal response normalization (LRN) [16], often result in information loss.”
Thermal Image Classification for Overheating Prevention in High-Voltage Equipment
Boulkaibet, S., Hacini, M., Bendaoud, A., et al. (2025) · doi:10.1109/ictaacs69003.2025.11399250
“Image classification with deep learning has advanced rapidly since AlexNet demonstrated the effectiveness of convolutional feature learning on large-scale datasets [8].”
Deep Learning-Based Fast Victim Detection in Disaster Zones via IoT Framework
Seeja, G., Hency, V. B., & Doss, A. S. A. (2025) · doi:10.1109/cict67193.2025.11398910
Artificial Intelligence: A Smart Way to Detect and Control Weeds
Seal, D., Pramanik, K., Layek, A., & PATRA, B. C. (2025) · Springer eBooks · doi:10.1007/978-981-99-0862-2_50-1
Interference Recognition Algorithm Based on Convolutional Neural Network
Liu, J., Huang, C., Shan, C., et al. (2025) · IEEE International Conference on Communication Technology (ICCT) · doi:10.1109/icct67417.2025.11374081
A Shape and Texture-Based Data Augmentation for Fine-Grained Malaysian Kuih Classification
Foong, I. W. X., Tan, T. H., Vijayashankar, M., Ng, R. K. W., & Choong, J. E. (2025) · IEEE Student Conference on Research and Development (SCOReD) · doi:10.1109/scored68498.2025.11398917
“RandomResizedCrop will randomly cut a region of an image and resizes it to a target dimension, introducing both scale and aspect ratio variations [17].”
Transformer Fault Detection Based on Feature Fusion of Partial Discharge and Thermal Image
Chen, Q., Long, Y., & Fu, W.-Q. (2025) · 2025 IEEE 3rd International Conference on Computer, Vision and Intelligent Technology (ICCVIT) · doi:10.1109/iccvit67848.2025.11391448
“Landmark architectures progressed from convolutional breakthroughs (AlexNet, VGG, ResNet) for hierarchical visual features [9]–[11] to attention-centric Transformers that scale sequence modeling and representation learning [12] .”
Accuracy-Aware IDK Cascades for Real-Time Object Classification at the Edge
Ratul, I. J., Guo, Z., & Yang, K. (2026) · Journal of Systems Architecture · doi:10.1016/j.sysarc.2026.103753
Image-based molecular classification in dual-comb spectroscopy using a convolutional neural network
Takeshi, N., Uchiyama, R., Takahoshi, T., & Nakajima, Y. (2026) · Japanese Journal of Applied Physics · doi:10.35848/1347-4065/ae49cb
“20,21) 24 ) In this study,”
Research on Multi-modal Dense Scene Individual Behavior Detection Based on Improved YOLOv13
Zhou, Y. (2026) · International Conference on Consumer Electronics and Computer Engineering (ICCECE) · doi:10.1109/iccece69169.2026.11399844
“Specifically, for each pixel channel: This step is critical, as it serves to accelerate model convergence, unify data dimensions, and maintain data stability [17].”
Attention-Guided Low-Light Object Detection Based on Receptive Field With Adaptive Depth Convolution
Zhao, J., Liu, Y., Xie, F., et al. (2026) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2026.3655151
Determining Ripening State of Banana Fruit Using with Different CNN Deep Learning Approach
Bisht, M., Gupta, A., & Gupta, R. (2025) · doi:10.1109/icoiics67115.2025.11389839
“…Layer • FCL is for Fully Connected Layer • LIN is for Fully Connected Layer • DRP is for Dropout • SOFTMAX is activation function The Relu activation function was used in AlexNet, which provides better training performance compared to other activation like tanh and sigmoid [19].”
Naspi, L., Erener, Ş., Davis, S. W., & Cabeza, R. (2026) · bioRxiv · doi:10.64898/2026.02.24.707651
“A similar pattern emerged for AlexNet ’s layer 2, a purely visual model, where greater representational specificity in FG and EVC was associated with reduced memory errors.”
Tian, J., Xiang, Z., Hu, X., et al. (2026) · Journal of Supercomputing · doi:10.1007/s11227-026-08249-3
“Early convolutional networks such as AlexNet [19] and VGGNet [20] extract hierarchical features through stacked convolutional layers, but suffer from gradient vanishing and feature degradation as depth increases.”
Okabayashi, T., Terazaki, K., Sagawa, H., et al. (2026) · Radiological Physics and Technology · doi:10.1007/s12194-026-01028-y · Cited by 1
Zhang, F., Zhang, J., Zhang, Z., Yang, K., Zhao, L., & Xu, Y. (2026) · Interdisciplinary Sciences Computational Life Sciences · doi:10.1007/s12539-025-00784-6
A hand-mimicking sensing gripper for litchi grasping and sorting
Liu, W., He, P., Zhang, H., & Xie, W. (2026) · Journal of Food Measurement & Characterization · doi:10.1007/s11694-026-04141-z
Qin, X., Zhang, X., Lai, C., Liang, H., Li, L., & Qin, C. (2026) · Journal of Food Measurement & Characterization · doi:10.1007/s11694-025-04011-0
Review of Hybrid and Data-Efficient Methods in Medical Image Segmentation
Dubey, A. K., Singh, V. K., Sharma, K., et al. (2026) · Archives of Computational Methods in Engineering · doi:10.1007/s11831-026-10514-w
Coelho, M. A. J., Neto, J. M., da Silva, O. R., et al. (2025) · doi:10.1109/icecer65523.2025.11401337
YOLO-Driven Brain Tumor Detection and Segmentation in MRI
Premnath, K., & Pandiaraj, S. (2025) · World Conference on Cutting-Edge Science and Technology (WCCEST) · doi:10.1109/wccest66994.2025.11389963
Fang, L., Zhang, W., Zhu, K., et al. (2026) · Journal of Imaging Informatics in Medicine · doi:10.1007/s10278-026-01872-9
Performance Analysis of Deep Learning Models for Smoking Scene Detection in Visual Media
Vansdadiya, R., & Vyas, D. D. (2025) · doi:10.1109/aicare66005.2025.11402779
“• AlexNet: One of the earliest deep CNNs for large-scale image recognition, featuring five convolutional layers and three fully connected layers [10].”
Gautam, J., Dhamejani, S., Mishra, K. K., et al. (2025) · International Conference on Artificial Intelligence for Innovations in Healthcare Industries (ICAIIHI) · doi:10.1109/icaiihi67124.2025.11403662
Asyuri, R. K., Sangaiah, A. K., & Chen, W. T. (2026) · IEEE Transactions on Consumer Electronics · doi:10.1109/tce.2026.3667852
Grading Breast Cancer With Deep Learning Methode in the Pathology Image
Hyperastuty, A. S., Handayani, A. N., & Herwanto, H. W. (2025) · doi:10.1109/bts-i2c67944.2025.11399422
“CNN models such as AlexNet have been shown to be effective in the classification of medical and histopathological images with high accuracy[7][8][9].”
AI-Enabled Participatory Governance for Sustainable Urban Problem Reporting
Nikhra, S., Jaiswal, S., Tudha, S., Meena, K. B., & Tyagi, V. (2026) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3373-7804-6.ch002
Jayapal, S., Sasikala, M., Nandu Bhavani, M., et al. (2026) · Multimedia Tools and Applications · doi:10.1007/s11042-026-21168-y
Huang, C., & Yuan, X. (2025) · International Conference on Software Engineering · doi:10.1109/icse68658.2025.11407595
“Among them, representative networks include conventional CNNs such as AlexNet[7-8] and Vgg-16[9-10], as well as lightweight CNNs such as MobileNet-v1[11-12], MobileNet-v2[13-14], ShffleNet[15-16], and Xception[17-18].”
Bohl, M., Esteban‐Medina, M., Beerenwinkel, N., & Lenhof, K. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.02.24.707713 · Cited by 1
“To bridge this gap, recent methods have adopted domain adaptation deep learning strategies inspired by computer vision [16–21].”
A lightweight detection model for fruit flies based on KSGM-OMN
Deng, H., Meng, F., Wang, Z., Peng, Y., Liao, M., & Hu, C. (2026) · Smart Agricultural Technology · doi:10.1016/j.atech.2026.101931
МЕТОДИКА ПОБУДОВИ НЕЙРОННИХ МЕРЕЖ ДЛЯ ІДЕНТИФІКАЦІЇ ОЗБРОЄННЯ ТА ВІЙСЬКОВОЇ ТЕХНІКИ
Slyusar, V., Protsenko, M., & Докучаєв, О. В. (2022) · Озброєння та військова техніка · doi:10.34169/2414-0651.2022.2(34).99-107
Faska, Z., Khrissi, L., Haddouch, K., & Akkad, N. E. (2026) · Multimedia Tools and Applications · doi:10.1007/s11042-026-21299-2
“Nevertheless, these algorithms have reemerged and achieved remarkable suc - cess, notably triumphing in the ImageNet Challenge in recent years [58, 59 ].”
Tea Bud Image Augmentation via Improved BicycleGAN with Attention and Perceptual LossPreprint
Liu, Y., Ma, B., Wang, X., Zhu, S., Yang, H., & Li, S. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6307353
An, D., Shi, P., & Gou, X. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6308736
Large Language Models for Anomalous Event Detection from Temporal Point Processes
Zhuang, Q., Zhang, P., & Yang, H. (2025) · IEEE International Conference on Knowledge Graph (ICKG) · doi:10.1109/ickg66886.2025.00060
“The supervised methods include a feedforward neural network (NN) with three hidden layers (256–128–64 units, ReLU activations) [27], a recurrent LSTM with 128 hidden units designed to capture temporal dependencies [1], and a Support Vector Machine (SVM) classifier with an RBF kernel ( γ = 0 .”
Nakahashi, K., Yoshida, T., Jogan, M., et al. (2026) · JTCVS Open · doi:10.1016/j.xjon.2026.101705
Semantic alignment brain diffusion: Decoding realistic visual perception from fMRI
Yang, C., Meng, L., & Gao, S. (2026) · Neurocomputing · doi:10.1016/j.neucom.2026.133156
Chandra, A. Y., Setyaningsih, P. W., & Pratama, I. (2025) · International Conference on Information System & Information Technology (ICISIT) · doi:10.1109/icisit66233.2025.11402957 · Cited by 2
“Despite variations in datasets and evaluation protocols, recent findings from both national and international studies affirm CNN’s competitive performance in batik classification [11][12][13].”
Qi, S., Wang, Y., Wang, Y., Zhang, Q., Tian, Y., & Cao, C. (2026) · Analytical Chemistry · doi:10.1021/acs.analchem.5c07582
BDU-Net: An Edge-Segmentation-Oriented U-Shaped Network for Pediatric Knee Joint Segmentation
Zhu, H., Liu, Y., Cheng, Z., Nie, Z., Yang, F., Xu, Y., & Jia, Y. (2026) · Journal of Imaging Informatics in Medicine · doi:10.1007/s10278-026-01862-x
Kacher, A., Merati, M., & Mahmoudi, S. (2026) · Vietnam Journal of Computer Science · doi:10.1142/s2196888826500041
bhandari, P., & Lakshmipriya, B. (2025) · International Conference on Smart Technologies and Systems for Next Generation Computing (ICSTSN) · doi:10.1109/icstsn67075.2025.11397948
“Landmark models such as AlexNet [13] and ResNet [14] demonstrated the ability of deep architectures for complex image recognition exercise.”
Ma, H., Li, L., Chen, K., Chi, J., Wei, S., Ren, X., Sun, W., & Gou, J. (2026) · Agriculture · doi:10.3390/agriculture16050526
Cross-Domain Knowledge Distillation for Low-Resolution Human Pose Estimation
Gu, Z., Zhao, Z., Ding, H., Shen, H., Zhang, Z., & Huang, D.-S. (2026) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2026.3668551 · Cited by 2
О., Ш. Д., & Kozlova, E. S. (2025) · Optical Memory and Neural Networks · doi:10.3103/s1060992x25602878
Balancing Efficiency and Accuracy in Image Classification Using CNNs
Gupta, H., Singh, M., Chaudhary, R., & Keshri, S. (2025) · IEEE DELCON - International Conference on Recent Smart Technologies in Engineering for Sustainable Development (DELCON) · doi:10.1109/delcon68055.2025.11400510
“The application of ANNs across multiple domains is based on their capacity to model and scrutinize intricate systems[1, 2].”
WIFI fingerprint positioning algorithm based on location mapping in graph convolutional network
Liu, H., Chen, P., Zhao, W., et al. (2025) · International Symposium on Computer Engineering and Intelligent Communications (ISCEIC) · doi:10.1109/isceic67854.2025.11405691
“Similar to convolutional neural network [9], graph convolutional neural network [10] extends the convolution operation of Euclidean space to non-Euclidean space, not only learns the node features of graph nodes, but also learns the structural information of graph, and can aggregate the complex…”
Design of a Winograd-Based CNN Accelerator with Reconfigurable Convolution Core for FPGA
Li, Y., Liu, H., Lyu, F., Xie, L., & Huang, Q. (2025) · International Symposium on Computer Engineering and Intelligent Communications (ISCEIC) · doi:10.1109/isceic67854.2025.11405693
“…Networks (CNN), as a prominent deep learning architecture, have emerged as fundamental algorithms across various domains such as computer vision [1], speech signal processing [2], and natural language processing [3], owing to their robust feature extraction capabilities and end-to-end learning…”
A deep learning based method for reference-free full-field strain measurement
Rossi, M., Tanoni, G., Ilari, V., Sasso, M., & Principi, E. (2026) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2026.114302 · Cited by 1
IMPACT OF DRONE ALTITUDE, SPEED, AND GIMBAL ANGLE ON OBJECT DETECTION IN A GAZEBO SIMULATION
Kelek, M. M., Oğuz, Y., & Fidan, U. (2026) · Konya Journal of Engineering Sciences · doi:10.36306/konjes.1656327
Virus-RK: A bionic adversarial attack framework for visual data in UAV 3D reconstruction system
Li, H., Yang, X., & Zuo, Y. (2026) · Knowledge-Based Systems · doi:10.1016/j.knosys.2026.115637
SystemC-Based Performance Analysis of Convolutional Neural Network Accelerator
Neelam, S., Kota, P., & Prince, A. A. (2025) · International Conference on Modeling, Simulation & Intelligent Computing (MoSICom) · doi:10.1109/mosicom67153.2025.11398265
Yuan, P., Zhang, C., Li, S., et al. (2026) · Journal of Computational Design and Engineering · doi:10.1093/jcde/qwag017
Liu, Y., Che, J., Ma, Q., et al. (2025) · doi:10.1109/mlcipr68329.2025.11407339
“Meanwhile, deep learning, especially CNN, has demonstrated significant advantages in image recognition with its automatic feature learning capability[2].”
Generative Adversarial Networks: A Feasibility Study
Hosseini-Zahraei, S., & Chaibakhsh, A. (2025) · National and International Iranian Conference on Biomedical Engineering (ICBME) · doi:10.1109/icbme68496.2025.11392420
“LSTM and RNN approaches, although adept at sequence modeling in gait phase detection [10] struggle with generalization across diverse populations and conditions due to their sensitivity to predefined temporal structures [16].”
Chen, J., Jang, S., & Wang, M. Q. (2026) · Medical Care · doi:10.1097/mlr.0000000000002305
“The MLP architecture consisted of 3 main components: 38 an input layer representing predictor variables (including predisposing, enabling, and need factors guided by the Andersen Behavioral Model), one or more hidden layers with nonlinear activation, and a single-node output layer for binary…”
Prayoga, Shidik, G. F., & Purwanto (2025) · 2025 International Conference on Advanced Technologies in Energy and Informatic (ICATEI) · doi:10.1109/icatei67676.2025.11405020
“Various CNN architectures such as AlexNet [6], DenseNet [7], EfficientNet [8], GoogLeNet [9], MobileNet [10][11], NASNet [12], ResNet [13], SqueezeNet [14], and VGGNet [15] have been widely applied in agricultural image classification tasks, often surpassing human-level performance.”
Art and Craft Item Recognition Using Deep Learning and MobileNet-V2
Kumari, M. S., Srinivas, B., Tekale, S., Reddy, P. T., Allada, S. R., & Gupta, A. (2025) · Modern Electronics Devices and Intelligent Communication Systems (MEDCOM) · doi:10.1109/medcom67532.2025.11405124
Tshinu, K. P., Tu, C., Owolawi, P. A., & Smith, A. (2025) · International Conference on Software Defined Systems (SDS) · doi:10.1109/sds68531.2025.11409874 · Cited by 1
Error level driven attention guided ensembles models for accurate leather defect detection
Hanzala, A., Sajjad, M., Akter, T., Kaur, H., & Rahman, M. S. (2026) · Discover Applied Sciences · doi:10.1007/s42452-025-08157-w
An Intelligent IoT-Enabled Entry Gateway for Contactless Health and Safety Screening
M, V., G.Balaji, Durga, P., et al. (2025) · 2025 Modern Electronics Devices and Intelligent Communication Systems (MEDCOM) · doi:10.1109/medcom67532.2025.11404967
Elakkiya.S, E. S., Prabadevi, B., Sudarmani., R., et al. (2025) · doi:10.1109/aectsd65988.2025.11411525
A Screening Framework for PFCD Using Bayesian Neural Networks and Ensemble Learning on MRI Images
Li, L., Yang, X., Chen, T., Zhang, H., & Lin, L. (2025) · International Conference on Image Processing, Multimedia Technology and Machine Learning (IPMML) · doi:10.1109/ipmml68499.2025.11407385
“This study employs three neural network architectures— LeNet[11], 3ConvNet[12], and AlexNet[13], and incorporates Bayesian methods to enable uncertainty estimation for these models.”
Wang, C., Elgendi, M., & Shin, H. (2026) · Scientific Reports · doi:10.1038/s41598-026-39875-9 · Cited by 1
A Controllable 3D Deepfake Generation Framework with Gaussian Splatting
Liu, W., Liang, S., Nguyen, H. H., et al. (2025) · IEEE International Joint Conference on Biometrics (IJCB) · doi:10.1109/ijcb65343.2025.11411152
“Deepfake technology has rapidly advanced in recent years, driven by progress in deep learning [1] and generative models [2, 3, 4], enabling the synthesis of highly realistic faces, voices, and expressions [5].”
Rajesh, J. S., V.Muralidharan, L.Pavithra, et al. (2025) · doi:10.1109/aectsd65988.2025.11410684
“Although the first deep learning models like AlexNet and VGG were showing promise in agriculture applications [18], they still have the issue of feature representation and computational efficiency for edge deployment along with [19] drawbacks.”
Active Dataset Distillation via Dual-Space Informative Matching
Qi, D., Li, J., Dou, S., Gao, J., Wang, Y., Zhao, B., & Zhao, C. (2026) · IEEE Transactions on Image Processing · doi:10.1109/tip.2026.3666748
Yoon, W. T., Kim, H.-G., Moon, J., et al. (2026) · IEEE Access · doi:10.1109/access.2026.3670144
Tang, J. (2025) · International Conference on Image Processing, Multimedia Technology and Machine Learning (IPMML) · doi:10.1109/ipmml68499.2025.11407192 · Cited by 1
“Krizhevsky et al. proposed AlexNet, which solved these limitations by achieving a breakthrough: reducing the top 5 error rate of the ImageNet Challenge from approximately 30% to 16.4%, thus initiating a deep learning revolution in the field of computer vision[4].”
InfluentialHuman-centred AI Investment and Firm Default RiskPreprint
Alam, M. S., Atif, M., Puwanenthiren, P., & Uddin, S. M. S. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6333528
Long, J., & Song, X. (2025) · doi:10.1109/bdamea68159.2025.11406396
“Originating from AlexNet [7], this technique divides feature maps and convolution kernels into multiple groups along the channel dimension, performing convolution operations on separate GPUs before merging outputs to generate final feature maps.”
Attention-aided GoogLeNet for Sedimentary Microfacies Identification in Delta Plains
An, X., Wang, S., Zhang, H., et al. (2025) · International Conference on Intelligent Control, Measurement and Signal Processing (ICMSP) · doi:10.1109/icmsp68723.2025.11407506
“In recent years, with the rapid advancement of information technology, deep learning owing to its powerful feature extraction and multilevel abstraction capabilities [1] has provided new momentum for the intelligent transformation of the petroleum industry.”
Data-Driven Prediction of Fertility Outcomes Through Machine Learning Models
Alamgir, Rehman, A., Ubaidullah, et al. (2026) · Earth Systems and Environment · doi:10.1007/s41748-026-01076-9
“CNNs learn hierarchical feature representations progressing from low-level patterns (e.g., edges or textures) in early layers to more abstract, high-level features in deeper layers (Krizhevsky et al. 2017).”
Liu, K., Yang, J., Wang, R., Li, S., & Xie, J. (2026) · The International Journal of Advanced Manufacturing Technology · doi:10.1007/s00170-026-17526-7
PBINet: A Pixel-Wise Boundary Information Refinement Network for Road Scene Segmentation
Wang, Y., Liu, X., Zhai, X., et al. (2026) · SN Computer Science · doi:10.1007/s42979-026-04817-9
Lombardi, M., Sapienza, D., Govi, E., & Franchini, G. (2026) · Mathematics in Engineering · doi:10.3934/mine.2026006
Sequential Dual-Model Verification for Medicinal Plant and Leaf Identification
K, L. S., & Chellamani, G. K. (2026) · International Conference on Computational Intelligence in Data Science (ICCIDS) · doi:10.1109/iccids69108.2026.11407640
“Transfer learning from big datasets (ImageNet) is common for modest sized datasets [22,23].”
Toward Resilient AI in Medical Imaging: Handling and Mining Multiple Sources of Data
Gravina, M., Simone, A. D., Pontillo, G., Shawa, Z., Marrone, S., Fusco, R., Granata, V., Petrillo, A., Cole, J. H., Sansone, M., et al. (2026) · SN Computer Science · doi:10.1007/s42979-026-04821-z
“Our earlier work [52] applied the Three Time Points (3TP) approach [ 53] to integrate CA dynamics into a fine-tuned AlexNet [ 43].”
InfluentialImages in Motion?: A First Look Into Video Leakage in Collaborative Deep Learning
Rasul, M. F., Alqobaisi, A., Bezawada, B., & Ray, I. (2025) · IEEE International Conference on Trust, Privacy and Security in Intelligent Systems and Applications (TPS-ISA) · doi:10.1109/tps-isa67132.2025.00037
“In this case, a video is segmented into clips, and a pre-trained convolutional neural network, e.g. ResNet [11], AlexNet [20], is used to extract deep features from the frames.”
Visha, B., Das, S. R., Yasin, A., et al. (2025) · Conference on Cloud and Internet of Things (CIoT) · doi:10.1109/ciot67574.2025.11410135
Jabin, A., & Ahmad, S. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.03.02.709012
“Parallel to this shift, large-scale self-supervised foundation models have redefined visual representation learning (Krizhevsky et al., 2012; He et al., 2016; Dosovitskiy et al., 2021; He et al., 2022).”
Spatial Dynamic Perception Network for Image Classification
Jiang, W., & Ji, J. (2025) · International Conference on Signal Processing, Computer Networks and Communications (SPCNC) · doi:10.1109/spcnc68200.2025.11406710
“AlexNet [5] first demonstrated the superiority of deep CNNs, but its simple architecture limited its feature extraction capability.”
Song, Z., Tang, H., Zhang, Q., et al. (2026) · IEEE Transactions on Green Communications and Networking · doi:10.1109/tgcn.2026.3669577
Automated Diagnosis of PCOS: A Deep Learning Approach Using Ultrasound Data
Gupta, C., Agarwal, L., Sharma, S., et al. (2025) · doi:10.1109/aisummit66170.2025.11410826
“The introduction of the concept of artificial intelligence to the medical imaging field has demonstrated enormous potential in deep convolutional neural networks (CNNs) regarding classification, segmentation, and detecting anomalies on a wide scale of domains [8]- [10].”
Paddy Disease Recognition Using Convolutional Neural Networks
RamaKrishna, N. S., Anitha, T., Charan, N., Kumar, P. V., Haritha, I. V. S. L., Shanthi, M., & Varaprasad, S. (2025) · Asia Pacific Conference on Innovation in Technology (APCIT) · doi:10.1109/apcit65661.2025.11411472
Semi-Supervised Web Service Classification Using Enhanced CatBoost with Confidence-Based Labelling
Bokka, D. S., & Rao, G. S. (2025) · Asia Pacific Conference on Innovation in Technology (APCIT) · doi:10.1109/apcit65661.2025.11411320
“In this case, inaccurate entries will have missing values replaced through imputation techniques to preserve data integrity[16].”
Zhao, L., Zhou, X., Hawbani, A., et al. (2026) · IEEE Internet of Things Journal · doi:10.1109/jiot.2026.3670382
Britto, J. G. M., R, A. R. G., Sravanthi, K., et al. (2025) · doi:10.1109/apcit65661.2025.11411146
Meta-Exploiting Task-aware Dual-modal Semantic Feature embedding for Few-shot Open-set RecognitionPreprint
Zhang, L., Wang, J., Bai, P., Yan, X., Xiao, H. Y., Zhang, X., Ding, C., & Zhang, Y. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6344164
COMET: Communication and Memory Co-Design for Fine-Grained AI Inference in MCM Accelerators
Sheng, T., Sun, G., & Dong, D. (2026) · Proceedings - International Symposium on High-Performance Computer Architecture/Proceedings · doi:10.1109/hpca68181.2026.11408536
Reward centering in multi-agent reinforcement learningPreprint
Hong, C., Qin, H., Liu, C., & He, N. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6344162
Metadata
- Authors
- Krizhevsky, A., Sutskever, I., & Hinton, G. E.
- Affiliations
- Google (United States) (US)
- University of Toronto (CA)
- Venue
- Communications of the ACM
- Published
- 2017-05-24
- Volume
- 60
- Issue
- 6
- Pages
- 84-90
- ISSN
- 0001-0782 (ISSN-L)
- 1557-7317
- OpenAlex
- W2163605009
- Cited by
- 112,155
- References
- 27
- Citations by year
- 2026: 2710 · 2025: 7710 · 2024: 10211 · 2023: 12267 · 2022: 12280 · 2021: 15497 · 2020: 14538 · 2019: 13976 · 2018: 9999 · 2017: 6661
- FWCI
- 5127.18
- Type
- journal article
- Language
- en
- Open access
- bronze
- doi.org
- Locations
- Communications of the ACM (publishedVersion)
- neural information processing systems
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Image and Video Retrieval Techniques
- Keywords
- ImageNet, image classification, deep convolutional neural networks, dropout regularization, overfitting
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
A language model drew the claims from the paper on 2026-10-11, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-11 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
