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 106,401–106,500 of 108,435
Li, S., Salowe, R., Lee, R., Ying, G., Lee, I., O'Brien, J., & Bastani, O. (2026) · npj Digital Medicine · doi:10.1038/s41746-025-02318-2
Lai, S., Tian, Y., & Zhang, Q. (2026) · npj Heritage Science · doi:10.1038/s40494-026-02348-3
LPCLNet: Leveraging local pixel-wise contrastive learning for image tampering localization
Sang, J., Chen, X., Gong, W., et al. (2026) · Information Sciences · doi:10.1016/j.ins.2026.123205
Toward Trustworthy AI: Explainable and Robust Machine Learning for Medical ApplicationsPreprint
Yu, T., Tao, P., & Ru, Z. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5328192
Dehbozorgi, P., Ryabchykov, O., & Bocklitz, T. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5333395
Sserunjogi, M., & Ambrose, R. K. (2026) · Powder Technology · doi:10.1016/j.powtec.2026.122246
Guilcapi, D. A. C., & Paz-Arias, H. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-031-98768-7_17
Schweder, F., Trujillo-Gomez, S., & Polsterer, K. L. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6190683
NDM: Boosting Dataset Distillation via Nested Difficulty Matching
Zhang, D.-Y., Gou, H., Zhang, Y., et al. (2026) · IEEE transactions on circuits and systems for video technology (Print) · doi:10.1109/tcsvt.2026.3661992
Zeng, J., Kou, M., Yao, H.-L., et al. (2026) · IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems · doi:10.1109/tcad.2026.3661431
Feature-Based Inversion of 2.5-D Controlled Source Electromagnetic Data Using Generative Priors
Zhou, H., Sun, H., Guo, R., et al. (2026) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2026.3661733
“) denotes a pre-trained and frozen image processing neural network such as AlexNet [55], and γ is the hyper-parameter adjusting the relative weights of the two types of loss.”
Park, S., Jeong, S., Cho, M., et al. (2026) · Scientific Reports · doi:10.1038/s41598-026-37116-7
Hu, N., Li, X., Zhao, Z., et al. (2026) · Neurocomputing · doi:10.1016/j.neucom.2026.133011
Improving and Evaluating the Corruption Robustness of Image Classifiers Using Random p-Norm Noise
Siedel, G., Shao, W., Vock, S., et al. (2026) · Communications in computer and information science · doi:10.1007/978-3-032-07623-6_17
Computer vision-based prediction of quality and mechanical properties of wooden lamellae
Achatz, J., Speigl, L., Elsener, R., Burgert, I., Rigling, A., & Schubert, M. (2026) · Advanced Engineering Informatics · doi:10.1016/j.aei.2026.104363 · Cited by 1
BF-DETR: A Lightweight and Adjustable Model Based on RT-DETR
Xu, Q., Qi, X., Wang, W., Huang, Y., & Zou, K. (2026) · IEEE Access · doi:10.1109/access.2026.3662346
FreeStyle: Toward Style-Inclusive Sketch-Based Person Retrieval
Wu, X., Chen, C., Zeng, H., et al. (2026) · IEEE Transactions on Image Processing · doi:10.1109/tip.2026.3660575
檀, 文. (2026) · Software Engineering and Applications · doi:10.12677/sea.2026.151004
Enhancing Fashion Product Recommendations Through CNN-Based Ensemble Learning
Rajani, C., Moturi, S., Rao, M. K., et al. (2026) · Lecture notes in networks and systems · doi:10.1007/978-981-96-9771-7_15
Communication and Storage Efficient Coded CNN Inference for Straggler-Resistant Over IoT Devices
Xie, S.-K., Liu, R., Wan, K., et al. (2026) · IEEE Internet of Things Journal · doi:10.1109/jiot.2026.3662568
Pham, N.-G., Nguyen, N.-L., Vo, P.-H., & Tran, H.-N. (2026) · Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering · doi:10.1007/978-3-032-12941-3_5
Chao, W.-J., Tseng, Y.-C., & Hsieh, T.-Y. (2026) · ACM Transactions on Design Automation of Electronic Systems · doi:10.1145/3793551
“We consider various combinations of well-known CNN models (with different complexities) and benchmarks, including AlexNet [ 37 ], VGG16 [ 38 ], ResNet18 [ 39 ], and ResNet50 [ 39 ].”
Vural, M. A., & Akay, M. K. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6210554
Flexible DC Grid Fault Detection Method Based on MTF ‐ EfficientNetV2 Algorithm
Zeng, Z., Li, J., Wei, Y., et al. (2026) · IEEJ Transactions on Electrical and Electronic Engineering · doi:10.1002/tee.70256
Integrating Transfer Learning and CNN for Object Detection in Autonomous Vehicles
Jayasurya, R., Kirankumar, K., Archana, T., et al. (2026) · Lecture notes in electrical engineering · doi:10.1007/978-981-95-0207-3_24
Tsai, T., Lin, J.-H., Liu, Y.-T., et al. (2026) · Journal of Imaging · doi:10.3390/jimaging12020076
Ren, R., Fan, Q., Sun, W., Pan, Y., Li, R., & Wang, W. (2026) · Drying Technology · doi:10.1080/07373937.2026.2628101
“[16] Since then, CNN-based fault diagnosis approaches have been rapidly developed and have become a mainstream architecture widely adopted by researchers.”
InfluentialStrawberry ripeness detection based on improved lightweight network in cluttered field environment
Wu, R.-Y., Chen, X.-Y., Wang, Y.-M., et al. (2026) · Journal of Measurements in Engineering · doi:10.21595/jme.2026.25196
“Convolutional neural network (CNN), a representative algorithm of deep learning, performs consistently well in image recognition by extracting discriminative features from images in the presence of sufficient training data [2-5].”
Restricted Receptive Fields for Face Verification
Öztürk, K., Bhatta, A., Wu, H., Flynn, P. J., & Bowyer, K. W. (2026) · IEEE Transactions on Biometrics Behavior and Identity Science · doi:10.1109/tbiom.2026.3663919
“Patch-level Feature Learning: While global feature learning approaches have shown great success in recent years [59], [60], BagNet [44] investigates the use of patch representations for object recognition.”
Todkar, A. S., Kotha, S. R., Bai, L., Mandula, S., Wilson, H. B., Meyer, D., Berdeaux, R., Roysam, B., & Varadarajan, N. (2026) · Frontiers in Bioinformatics · doi:10.3389/fbinf.2026.1711797
Fired bullet matching candidate retrieval algorithm based on Siamese neural network
Guo, B., Shen, Y., Zhou, Z.-F., et al. (2026) · Journal of Forensic Sciences · doi:10.1111/1556-4029.70287
Teng, X., Jiang, W., Xiang, P., et al. (2026) · Applied Soft Computing · doi:10.1016/j.asoc.2026.114807
From Brain Maps to Behavioral Governance
Quintana, S. C. (2026) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3373-4480-5.ch009
Image processing technology based on machine learning
Vajpayee, A., Singh, S., Bali, N., Sharma, A. K., Aggarwal, A., & Anand, A. (2026) · AIP conference proceedings · doi:10.1063/5.0318510
Reddy, K. B., Reddy, P. S., Goud, G. V., Sallahuddin, M., Rout, S. K., & Kumar, K. S. (2025) · Global Conference on Information Technology and Communication Networks (GITCON) · doi:10.1109/gitcon65266.2025.11378005
“With its hybrid attention processes, YOLOv7 was proposed by Wang et [13].”
Making neural networks more neural
Freeman, A. W. (2026) · Patterns · doi:10.1016/j.patter.2026.101494
“Using an AlexNet network, 5 they replaced the first layer of their DNN with an array of Gabor filters.”
基于深度展开网络的VISAR速度场超快成像诊断重构算法及硬件实现
Miao, 黎. L., Chaorui, 陈. C., Xi, 王. W., et al. (2025) · ACTA PHOTONICA SINICA · doi:10.3788/gzxb20255412.1232001
Hao, 王. W., Xinglei, 赵. Z., & Fengnian, 周. Z. (2026) · Laser & Optoelectronics Progress · doi:10.3788/lop252034
Ma, C., Jia, R., Lou, J., et al. (2026) · International Journal of Pattern Recognition and Artificial Intelligence · doi:10.1142/s021800142640001x
Haibo, 于. Y., Zibin, 李. L., Xuyu, 曾. Z., et al. (2026) · Laser & Optoelectronics Progress · doi:10.3788/lop251920
Steiner, J., Ismail, Y., Glumbfskie, W., & Price, J. (2026) · Corrosion Engineering Science and Technology The International Journal of Corrosion Processes and Corrosion Control · doi:10.1177/1478422x261420383
Deep Learning Based Traffic Sign Recognition
Ravindra, B. V., Chaya, Shetty, B. M., & Rathod, S. (2025) · International Conference on Electronics, Communication and Aerospace Technology (ICECA) · doi:10.1109/iceca66444.2025.11383236
“Deep learning with convolutional neural networks (CNNs) has revolutionized TSR by being able to learn image features hierarchically automatically and possessing high accuracy and robustness against environmental changes [4] – [6].”
Multimodal Engagement Estimation for Online Teaching through Facial and Postural Analytics
Sivasangari, V., Saranya, G., & Uma Maheswari, B. (2025) · International Conference on Ubiquitous Computing and Intelligent Information Systems (ICUIS) · doi:10.1109/icuis67429.2025.11380296
“The basis for many modern facial analysis systems was established by Krizhevsky et al. [2], who introduced deep “Convolutional Neural Networks (CNNs) for image classification”.”
Attention-Enhanced Hybrid Graph Neural Network for 3D Localization of Rock Fracture Events
Li, B., Sun, J., Li, H., Zhang, C., Teng, W., Song, H., Ji, X., & Yao, Z. (2026) · Communications in computer and information science · doi:10.1007/978-981-95-6730-0_43
AE-BiseNet: Anomaly-Enhanced Bilateral Segmentation Network for Industrial Defect Detection
Wang, X., Wu, X., Hou, Y., et al. (2026) · Communications in computer and information science · doi:10.1007/978-981-95-6730-0_38
Gesture Recognition-Based Multimedia Control in Automotive Systems: A Novel Approach
Castro, R., Deolinda, A., Sousa, M., de Medeiros, F. P. A., Santos, C., Scoralick, F., de Sousa, R. M., & de Medeiros, J. D. R. V. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-12876-8_38
CGDFNet: a dual-branch real-time semantic segmentation network with context-guided detail fusion
Zhao, S., Fu, W.-J., Gao, J.-J., et al. (2026) · Scientific Reports · doi:10.1038/s41598-026-39370-1
“The model is trained using the Stochastic Gradient Descent (SGD) 41 optimizer with a momentum of 0.9, a weight decay of 5 × 10 − 4 , and a batch size of 16.”
InfluentialLi, C., Sun, J., Gao, Y., Feng, C., Wang, Z., Zhang, H., & Niu, W. (2026) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2026.109820 · Cited by 1
Maoulainine, R. C., Chihab, Y., Korchiyne, R., Salaheddine, L., Dahmani, R., Hajbi, S., & Houssaini, Z. S. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-12869-0_10
A Scene-Based Multimodal Video Similarity Detection Algorithm
Li, X. (2025) · Automatic Control and Computer Sciences · doi:10.3103/s0146411625701354
“In recent years, convolutional neural networks (CNN) have been widely used in computer vision, and many excellent CNN models have been developed, such as AlexNet [5], VGG [6], and GoogLeNet [7].”
Teng, Y., Sun, D., Hu, S., et al. (2026) · ENGINEERING Information Technology & Electronic Engineering · doi:10.1631/eng.itee.2025.0034
Han, J.-H., Park, J.-H., & Hong, S.-K. (2026) · IEEE Open Journal of Industry Applications · doi:10.1109/ojia.2026.3665357
Li, K.-T., Li, H.-J., Qiu, H., et al. (2026) · Scientific Reports · doi:10.1038/s41598-026-40506-6
Ishigaki, S., Nishiyama, K., Nishikawa, T., et al. (2026) · Advanced Biomedical Engineering · doi:10.14326/abe.15.57
Mamba-Face: Rethinking Facial Beauty Prediction with State Space Models
Boukhari, D. E., Kezai, M., & Benchabane, I. (2025) · doi:10.1109/aiia68273.2025.11383684
AI-Powered Detection of Potato Leaf Diseases Using Deep Neural Networks
Ghosh, A., Adesh, N. D., Raghavendra, S., et al. (2025) · 2025 Second International Conference on Computing, Semiconductor, Mechatronics, Intelligent Systems and Communications (COSMIC) · doi:10.1109/cosmic67569.2025.11380951
“The emergence of deep learning has fundamentally transformed the landscape of computer vision with computer-aided image inspection, where Convolutional Neural Networks (CNNs) have emerged as the dominant method for nearly all computer vision tasks [3].”
BAFTCNet: A model for motor imagery decoding based on EEG principles and attention mechanisms
Chen, Z., Cao, D.-G., Liang, G., Yu, H.-Y., & Zhao, Y.-L. (2026) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2026.109847
Deep Learning for Advancing Synthetic Biology in Plants
Guerfel, M., & Essemine, J. (2026) · CABI biotechnology series. · doi:10.1079/9781836991120.0009
Class-Aware Coreset Selection for 3D Point Clouds Classification
Yim, J., Kim, D., & Sim, J.-Y. (2025) · doi:10.1109/icipw68931.2025.11386049
“Recently, deep learning models [1, 2, 3] have shown good performance across various computer vision applications.”
Cell Anaemia Detection using Vision Transformer
Mahalakshmi, S. B., S, K. K. G., Murali, V., & KamalrajSubramaniam (2025) · International Conference on Evolutionary Computing and Mobile Sustainable Networks (ICECMSN) · doi:10.1109/icecmsn68058.2025.11382991
“Public health research highlights the importance of scalable diagnostic tools [17][18], supported by open access datasets [19][20], and successful execution of pre-trained models [21][22].”
Pruned but Accurate: Lightweight AlexNet for On-Device Skin Lesion Diagnosis
Amer, Y. A., Saleh, H. I., & Nasr, O. A. (2025) · International Conference on Future Telecommunications and Artificial Intelligence (IC-FTAI) · doi:10.1109/ic-ftai67960.2025.11384597
“The core research problem addressed in this work is the computational inefficiency and large memory footprint of deep neural networks, particularly AlexNet [7], which hinder their deployment on portable or edge medical devices.”
Lee, S. H., Nemenman, I. M., & Levchenko, A. (2026) · Cell Systems · doi:10.1016/j.cels.2025.101507
Insight into Spectral Graph Theory and Spectral Graph Neural Networks
Tsolakidis, S., Tsolakidis, A., Karanikolas, N. Ν., & Skourlas, C. (2026) · WSEAS Transactions on Information Science and Applications archive · doi:10.37394/23209.2026.23.9
Carrasco-García, M. G., González-Enrique, J., Ruíz-Aguilar, J. J., Orive, A. C., Elizondo, D. A., & Turias, I. J. (2026) · Journal of Marine Science and Engineering · doi:10.3390/jmse14040383
Securing Face ID: Privacy Preservation for Non-Retentive Face Recognition System
Chua, M., Yeow, C. Y.-T., Chwee, C. X.-Y., Leong, S.-M., & Phan, R. C. ‐. (2025) · IEEE Region 10 Conference (TENCON) · doi:10.1109/tencon66050.2025.11374999
“Convolutional Neural Networks (CNNs), in particular, have emerged as a powerful tool for feature extraction, enabling systems to learn complex patterns and representations from large datasets [9].”
Paralath, M. N. (2025) · International Conference on Advances in Next-Gen Computer Science (ICANCS) · doi:10.1109/icancs65819.2025.11376668 · Cited by 4
“Traditional CNNs have demonstrated remarkable success in large-scale image classification and detection tasks [3], [4], largely due to their ability to learn hierarchical feature representations.”
SecureFace: A Controlled Deepfake Generation Framework for Exposing Detector Vulnerabilities
Afgan, M. S., Liu, B., Shifa, A., & Asghar, M. N. (2025) · Cyber Research Conference - Ireland (Cyber-RCI) · doi:10.1109/cyber-rci68134.2025.11385159
Asgari, M. M., & Hashemi, S. M. (2026) · Results in Control and Optimization · doi:10.1016/j.rico.2026.100672
van Dyck, L. E., & Dobs, K. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.02.16.706115 · Cited by 1
“Feature visualizations for a representative model (supervised AlexNet trained on Ecoset) revealed distinct preferences (Fig.”
InfluentialInstance-based visualization and analysis of neural networks
van den Elzen, S. (2026) · Information Visualization · doi:10.1177/14738716261418575 · Cited by 1
Rahman, J. U., Khan, M. S., Khan, A., & Mirza, A. (2026) · NeuroMarkers. · doi:10.1016/j.neumar.2026.100165
Pareto calibrated adversarial sample generation for SAR ATR with aggression-concealment balance
Su, X., Quan, S., Cai, Z., et al. (2026) · Results in Engineering · doi:10.1016/j.rineng.2026.109650
Impact of Transfer Learning on Convolutional Neural Networks for Odontogenic Tumor Diagnosis
Giraldo‐Roldán, D., Nakamura, T. C. R., Claret, A. F., dos Santos, G. C., Díaz, K. P., Gerber‐Mora, R., Pérez, L. V. G., Câmara, J., Pontes, H. A. R., Martin, M. D., et al. (2026) · Head and Neck Pathology · doi:10.1007/s12105-025-01875-y · Cited by 1
“For more than a decade, it has been widely used as a reference dataset for training deep neural networks in visual recognition tasks [ 31 ].”
Liu, X., Guan, J., Liu, L., Feng, J., Xu, H., & Duan, Y. (2026) · Journal of Geophysical Research Machine Learning and Computation · doi:10.1029/2025jh000970
Self-supervised vision transformers for classification in unconventional shales
Mohammad, R., Devegowda, D., Curtis, M. E., Rai, C., Mudduluru, S., & Maryada, S. K. (2026) · The Leading Edge · doi:10.1190/tle-2025-0061
Coupled End-to-End Transfer Learning with Generalized Fisher Information
Shrivastava, V., Malhotra, N., Sharma, C., Goel, A., Agarwal, M., & -, I. G. (2025) · International Conference on Advancement in Electronics & Communication Engineering (AECE) · doi:10.1109/aece67531.2025.11386587
“The progress made by deep convolutional neural networks (CNNs) in various areas of computer vision like object recognition, scene understanding, and semantic segmentation cannot be understated [1].”
Syafitri, W., & Masripah, S. (2025) · doi:10.1109/icaisd68166.2025.11385448
“These models have also been pretrained using transfer learning techniques to enhance their performance by leveraging large-scale datasets, such as ImageNet [7].”
Otsuka, Y., Kantavat, P., & Kijsirikul, B. (2026) · Machine Learning with Applications · doi:10.1016/j.mlwa.2026.100870
Priya, S. V., Lotus, R., Varalakshmi, S., Karthikeyan, G., Kumari, E. N. V., & Al-Safarini, M. Y. (2025) · International Conference on Electronics and Computing, Communication Networking Automation Technologies (ICEC2NT) · doi:10.1109/icec2nt65402.2025.11380168
“[9].”
Interactive Emotion Recognition System: AI-Driven Emotional Assistance
Jain, J., Kushwaha, S., Jaiswal, U. K., Kumar, S., V, Jain, E., & Dublish, M. (2025) · International Conference on Advancement in Electronics & Communication Engineering (AECE) · doi:10.1109/aece67531.2025.11386645 · Cited by 1
Identification of Pests Using Neural Networks
Jayabalaji, K. A., S, A. S. K., Abinaya, A., & Ms. Aiswarya, S. (2025) · International Conference on Intelligent Innovations in Engineering and Technology (ICIIET) · doi:10.1109/iciiet65921.2025.11377609
Janakamma, C., Gouthami, S., Golamari, J. M., et al. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-15134-6_18
CSFEM-YOLO: cross-scale fusion enhanced YOLO chip surface defect detection
Gao, Y., Gu, J., Wang, W., Xia, Z., Liu, W., Xiang, H., 孙培越, Shan, Y., & Zhu, Y. (2026) · Engineering Research Express · doi:10.1088/2631-8695/ae3b98 · Cited by 1
Lin, L., Dong, C., Henson, S. A., et al. (2026) · Geophysical Research Letters · doi:10.1029/2025gl120669
“Convolutional neural networks (CNN), one type of deep learning technique, can effectively capture spatial features in large data sets and identify weak signals amid noise, making them ideal for analyzing two‐dimensional images or spatial data (Krizhevsky et al., 2017).”
A Comparative Study on CNN and ConvSNN
Chakraborty, S., Paul, P., & Ghosh, S. (2026) · Lecture notes in networks and systems · doi:10.1007/978-981-96-9494-5_13
Enhanced Brain Tumor Detection Using CNN-Based Image Classification: A Deep Learning Approach
Karwa, P., Sharma, N., Bolakhe, A., et al. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-09825-2_28
Gupta, A., & Bhatnagar, M. (2025) · 2025 Second International Conference on Pioneering Developments in Computer Science & Digital Technologies (IC2SDT) · doi:10.1109/ic2sdt68218.2025.11383748
Deep Learning-Based Predictive Bidirectional Beamforming in ISAC-Enabled UAV Networks
Xu, J., Zhou, X. Y., Zhang, H., & Li, Y. (2026) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2026.3664980 · Cited by 1
Multi-scale Target Detection of Unmanned Ground Vehicles Based on YOLO-MAC
Wang, Y., Qin, Y., Liu, W., et al. (2025) · IEEE Smart World Congress (SWC) · doi:10.1109/swc65939.2025.00106
“Since the introduction of AlexNet in 2012 [6], the era of convolutional neural networks has been opened up.”
Integrating MHSSA-transformer and GCN for enhanced micro-expression recognition
Zhu, L., Hu, C., Zhao, H., & Yu, H. (2026) · The Visual Computer · doi:10.1007/s00371-026-04391-4 · Cited by 2
Abueed, O., Thakkar, P., AlAlaween, W. H., Wang, Y., & Khasawneh, M. T. (2026) · Neural Computing and Applications · doi:10.1007/s00521-025-11743-z · Cited by 4
“Alexnet [ 106 ] used the ReLU activation function to speed up network convergence and implemented dropout regularization to mitigate overfitting.”
Zhang, W.-H., Zhou, X., Hou, C., Hu, Z.-Z., & Guo, Y.-T. (2026) · Advanced Engineering Informatics · doi:10.1016/j.aei.2026.104494
Yin, Y.-Z., Cai, Y., Wei, X.-L., et al. (2026) · Engineering applications of artificial intelligence · doi:10.1016/j.engappai.2026.114256
Luo, H., Xie, M., Zhou, J., et al. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6281824
Bonteanu, G., Bonteanu, P., Patache, N., et al. (2024) · Buletinul Institutului Politehnic din Iaşi. Secţia Electrotehnică. Energetică. Electronică · doi:10.2478/bipie-2024-0008
A Novel Encoder - CNN Architecture for Robust Fingerprint Biometric Classification
Salma, S., & Ramamurthy, G. (2025) · International Conference on Artificial Intelligence and Signal Processing (AISP) · doi:10.1109/aisp68263.2025.11396274
“• Normalization – pixel values were normalized into the range [0, 1] using Min–Max normalization: • Data augmentation – to improve generalization, random rotations, translations, and slight elastic distortions were applied, following standard practices in fingerprint CNN training [6].”
Kubota, Y., Hirata, A., Hontani, H., Hatsusaka, N., Sasaki, M., & Sasaki, H. (2026) · IEEE Access · doi:10.1109/access.2026.3666874
Hierarchical Knowledge-Guided Recognition for Wolfberry PestsPreprint
Zhao, H., Wang, X., Man, R., et al. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6293238
AgeVision: Integrating Biomarkers and Facial Analysis for Accurate Age Prediction
Bhuiyan, M. A. A., Tawsif, M., Chowdhury, A., et al. (2026) · Arabian Journal for Science and Engineering · doi:10.1007/s13369-026-11121-4
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
