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 106,001–106,100 of 108,435
The Future of Deep Learning in Computational Mechanics
Herrmann, L., Jokeit, M., Weeger, O., & Kollmannsberger, S. (2025) · Springer eBooks · doi:10.1007/978-3-031-89529-6_11
Zhou, A., Hou, C., Wu, G., & Yin, L. (2025) · Microchemical Journal · doi:10.1016/j.microc.2025.115422
Focal modulation network for vision and tactile fusion
Yu, J., Su, W., Yang, W., et al. (2025) · Engineering Research Express · doi:10.1088/2631-8695/ae256c
Trivedi, V. K., Shukla, P. K., Pandey, A., Alduaiji, N., & Shreyas, J. (2025) · Journal Of Big Data · doi:10.1186/s40537-025-01261-z · Cited by 2
“In addition to these, Kabirt al (2020) proposed a multi-label CNN model for classifying various plant diseases using transfer learning techniques [15], including AlexNet [16], GoogleNet [17], VGG19 [18], ResNet50 [19], ImageNet [20], Dense121 [21], LeNet [22], and XceptionNet [23].”
Neural Detection of Failures in Glucose Sensors Through Time Windows
Alanis, A. Y., Hernandez, H. M., Aranguren, I., et al. (2025) · Lecture notes in networks and systems · doi:10.1007/978-3-032-10150-1_28
Li, K., Yu, H., Fang, Y., & Lei, C. (2025) · Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia Pacific Region (SIGIR-AP) · doi:10.1145/3767695.3769474 · Cited by 1
An Automatic Satellite Alignment Algorithm for Satellite Antennas Based on PPO
Zhao, B., Chen, Y., & Wang, P. (2025) · International Conference on Image Processing, Intelligent Control and Computer Engineering (IPICE) · doi:10.1145/3768184.3768200
“The layer consists of two fully connected layers, each containing 256 neurons, followed by a ReLU activation function [ 7 ] .”
Open-Skull Post-Selection Misconduct versus Closed-Skull Sole-Learner
Weng, J. (2025) · International Conference on Image Processing, Intelligent Control and Computer Engineering (IPICE) · doi:10.1145/3768184.3768255
Advances in Image Processing Techniques for Information Technology Application: A Review
Jain, R. (2021) · International Journal of Advanced Research in Science Communication and Technology · doi:10.48175/ijarsct-11200b
Gün, O. Y. (2025) · Mathematics and the built environment · doi:10.1007/978-3-031-81623-9_23
Sun, X., Liu, S., Wang, Z., et al. (2025) · Journal of Materials Chemistry A · doi:10.1039/d5ta05515f
Deguchi, Y., Jia, R., Nada, Y., et al. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5894386
Automated End-to-End Deep Learning Framework for Complex Multiclass Brassica Seed Classification
Elfatimi, E., Eryiğit, R., & Elfatimi, L. (2025) · Seeds · doi:10.3390/seeds4040067
“For example, Maeda-Gutiérrez et al. [16] compared CNN-based architectures such as GoogleNet [17], AlexNet [18], Inception V3 [19], and Residual Network (ResNet 18 and 50) [20] 2021) demonstrated a CNN pipeline for chickpea variety recognition with 94–95% accuracy under real-farm conditions,…”
Inverse Modeling of 2D Lubrication Film Using Convolutional Neural Networks
Huang, H., & Ji, Z. (2025) · International Symposium on Aerospace Engineering and Systems (ISAES) · doi:10.1109/isaes66870.2025.11274393
“To exploit the potential position information of the film thickness distribution to the greatest extent, a Convolutional Neural Network (CNN) [11] which combines a 2D convolutional encoder with residual enhanced fully connected decoder [12] is designed, in this structure 2D convolutional encoder…”
A deep learning approach to image analysis of M87⋆
Tsui, T., Protopapas, P., Garraffo, C., Fromm, C. M., Mizuno, Y., Blackburn, L., Chatterjee, K., Emami, R., & Doeleman, S. S. (2025) · Monthly Notices of the Royal Astronomical Society · doi:10.1093/mnras/staf2095 · Cited by 1
A Novel Evaluation Framework for 15-Minute City Using Satellite Imagery
Song, C., Chu, S., Kim, J., et al. (2025) · ACM International Conference on Advances in Geographic Information Systems (SIGSPATIAL) · doi:10.1145/3748636.3764182
“For aggregating different types of image features, we compare non-learnable methods including pooling operations (min/mean/max) [16], Hadamard product [15], and concatenation [4], as well as learnable attention mechanisms including gated attention [1] and cross attention [25].”
SPEEDY: Framework for Sharpening Promise Time Estimates in Sub-Same Day Delivery
Sarkar, A., & Comar, P. M. (2025) · ACM International Conference on Advances in Geographic Information Systems (SIGSPATIAL) · doi:10.1145/3748636.3764604
Matrix Square Root Based Differentiable RCWA Implementation for High-Performance Parallel Computing
der Ceelen, F. V., Shao, Y., & Coene, W. M. J. (2025) · Progress In Electromagnetics Research C · doi:10.2528/pierc25091202
Ghabi, K. E., Bousefsaf, F., Morère, Y., Hansen, C., Maetzler, W., & Romijnders, R. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5910028
BPformer: An Interpretable Deep Learning Framework for Livestock Breed Proportion AnalysisPreprint
Wang, J., Sun, S., Zhang, Y., Ju, Z., Jiang, Q., Wang, X., Xiao, Y., Chen, L., & Huang, J. (2025) · Research Square · doi:10.21203/rs.3.rs-8340493/v1
Jiang, D., Cao, Y., & Yang, Q. (2025) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2025.3637180
Cui, H., Shao, C., Wei, W., et al. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5933078
Kıvrak, T., Gelen, M. A., Salkin, O., et al. (2025) · Intelligent Medicine · doi:10.1016/j.imed.2025.06.003
Zhang, J., Chen, C., Gan, Z., Wang, W., Li, B., & Guo, M. (2025) · IEEE Transactions on Networking · doi:10.1109/ton.2025.3644644 · Cited by 1
ADAPT: Automated Decision-flow for Adaptive Progressive Inference on Sensor Devices
Macshane, J., Venkatasubramanian, N., & Li, Y. (2025) · MAIoT@Middleware · doi:10.1145/3774901.3778065
“A block is a coherent set of layers: convolutional, pooling, etc. that we can view as extracting features at different levels of abstraction [3, 8, 12, 20, 22].”
Context-assisted astrous deformable convolution for robust goat face detection and identification
Han, G., Zhang, L., Bai, Z., et al. (2025) · The Visual Computer · doi:10.1007/s00371-025-04298-6
Fan, Z., Zhang, Y., Li, W., Shang, S., He, H., Bi, J., Zhang, Y., Guo, H., & Yue, Y. (2025) · Advances in Civil Engineering · doi:10.1155/adce/6706091
Ertekin, E. C., & Güney, S. (2025) · AI Computer Science and Robotics Technology · doi:10.5772/acrt20250109
Hardware-aware Graph Partition for Mobile Inference Acceleration
Yu, M.-S., Zhan, F.-Y., Huang, M. Z., Chen, T.-L., & Lee, J.-K. (2025) · International Conference on Parallel Processing Workshops (ICPPW) · doi:10.1145/3750720.3757284
“The cost data was measured from models such as LeNet [24], AlexNet [22], SqueezeNet [18], VGG11 , VGG16, VGG19 [42], ResNet18, ResNet34, and ResNet50 [13].”
Zhang, Y., & Zhao, C. (2025) · Computational Biology and Chemistry · doi:10.1016/j.compbiolchem.2025.108853
Dong, H., Xu, Y., Wang, X., Ji, X., & Ding, Z. (2025) · Proceedings of the International Conference on Parallel Processing · doi:10.1145/3754598.3754634
Sezginer, S., Başar, C., & Mumcu, T. V. (2025) · IEEE Letters on Electromagnetic Compatibility Practice and Applications · doi:10.1109/lemcpa.2025.3646922
Adversarial Patch Detection Using Perturbation-Based Attribution Analysis
Panigrahi, L., Roksana, S., Saha, P. R., et al. (2025) · doi:10.1109/ciccs66437.2025.11304757
“Despite the enormous potential offered in computer vision tasks, DNN techniques have been shown to be susceptible to imperceptible perturbations, which can be used to construct purposeful misclassifications [2], [3].”
Eisentraut, L., Schadt, M., Mai, C., Koehn, W., & Buettner, R. (2025) · IEEE Access · doi:10.1109/access.2025.3646931 · Cited by 2
Lee, R., Hong, S., & Yoon, S. (2025) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2025.105315
Image Processing Techniques in Sovan Air Traffic Monitoring
Roy, S., Roy, P., & Pandit, R. (2025) · Emerald Group Publishing Limited eBooks · doi:10.1108/978-1-80592-062-520251004
Learnable token for visual tracking
Chen, Y., Jiang, Z., Du, J., et al. (2025) · Signal Processing Image Communication · doi:10.1016/j.image.2025.117465
Direct Optimization of Portfolios of Counter Strategies
Drabent, K. K., & Lisý, V. (2025) · International Conference on Distributed Artificial Intelligence (DAI) · doi:10.1145/3772429.3772437
Thienbutr, N., & Massagram, W. (2025) · International Computer Science and Engineering Conference · doi:10.1109/icsec67360.2025.11298123
Pedestrian Trajectory Prediction via Decoupled Trajectory Point HeatmapsPreprint
Jia, Y., & Chen, J. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5958816
Qian, P., & Ullman, T. D. (2025) · Open Mind · doi:10.1162/opmi.a.277 · Cited by 1
“Compared to the classic neural network models of object recognition, including AlexNet (Krizhevsky et al., 2017) and ResNet (He et al., 2016), these Transformer-based foundation models are shown to generalize more robustly and less biased towards texture (Geirhos et al., 2021).”
HVDet: Heap Vulnerability Detection Method Based on P-PDG Representation and Bi-GRU Algorithm
Zhang, B., Wu, J., Qingyu, S., Ren, R., Li, J., Wang, Q., & Kang, X. (2025) · International Journal of Software Engineering and Knowledge Engineering · doi:10.1142/s0218194025501086
CoSrch: Syntactic and Semantic Structure-Aware Code Representation for Effective Code Search
Xu, J., He, Y., Liu, H., Lv, P., Zhang, T., & Tian, Z. (2025) · ACM Transactions on Software Engineering and Methodology · doi:10.1145/3785469
“Specifically, most modern deep code search methods employ sequential models, such as Convolutional Neural Networks (CNNs) [38], Long Short-Term Memory Networks (LSTMs) [59], self-attention mechanisms [61], and co-attention mechanisms [6], to learn semantic representations of queries and codes…”
Duda, M. L. D. F., & Cabral, L. (2025) · Holos · doi:10.15628/holos.2025.17940
“O objetivo do primeiro experimento é comparar os modelos de DNN e algoritmos de SVM obtidos na Revisão Sistemática de Literatura, e também modelos de CNN eficientes para classificação de imagens (Krizhevsky, Sutskever and Hinton, 2012).”
Single object tracking based on Spatio-Temporal information
Wei, L., Luo, Y., Zhu, R., & Li, X. (2025) · Signal Processing Image Communication · doi:10.1016/j.image.2025.117463
Fang, J., Shen, Y., Sun, Y., Jiang, C., Jiang, Y. H., Pan, H., Yiu, S., & Jiang, Z. L. (2025) · Neural Networks · doi:10.1016/j.neunet.2025.108497
Real-time prediction of project duration deviation using CNN-LSTM-FIS
Ashtiyani, F. M., Gavareshki, M. H. K., & Gheidar‐Kheljani, J. (2025) · Built Environment Project and Asset Management · doi:10.1108/bepam-01-2025-0003 · Cited by 1
Nisar, H., Lee, K.-F., & Ali, S. A. (2025) · doi:10.1109/icon-sonics67145.2025.11309239
“Several state-of-the-art models have emerged from these challenges, including Inception (2015) [5], ResNet (2015) [6], ResNeXt (2016) [7], DenseNet (2017) [8], and SENet (2017) [9].”
Flores, A. M., Huilca, V. J., Jimbicti, E. A., & Huilca, M. E. (2025) · IEEE Ecuador Technical Chapters Meeting (ETCM) · doi:10.1109/etcm67548.2025.11304309
“Since their spectacular triumph in large-scale image classification tasks [1], CNNs have found widespread applications in many fields, such as remote sensing.”
Brusil, M., Andrade, R., & Grijalva, F. (2025) · IEEE Ecuador Technical Chapters Meeting (ETCM) · doi:10.1109/etcm67548.2025.11304271
“AlexNet proposed by [4], one of the first CNN architectures, was employed in initial studies due to its simplicity and effectiveness in basic classification problems.”
Strope, B., Varghese, D., Bowie, W., Wang, S., & Zhu, Q. (2025) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2025.12.22.696102
“…19,20 , such as GPT-based generative models 21,22 and BERT models 23 , have displayed the promise of synthesizing new biological insights from exceedingly large knowledge bases or biological corpuses, going beyond query-based search systems 24 , and classification-focused deep learning models 25 .”
Boosting video adversarial attacks with refined perturbations
Han, X., Wang, S., Tian, Q., et al. (2025) · Journal of Supercomputing · doi:10.1007/s11227-025-08170-1
“…computing capabilities, deep neural networks [1–3] have achieved significant success across various tasks, including image classification [4, 5], video action recognition [6, 7], object tracking [8, 9], and Visual Extended author information available on the last page of the article Page…”
Laval, G., Decugis, A., Parasayan, O., Patin, É., Quintana‐Murci, L., & Chiaroni, J. (2025) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2025.12.25.695976
“The CNNs used in this study is inspired by the popular AlexNet model (Krizhevsky et al. 2017).”
Singh, A., Singh, S., Mittal, A., Sharma, M., & Aggarwal, P. (2025) · ACM Transactions on Asian and Low-Resource Language Information Processing · doi:10.1145/3786584
“Raghavachari et al. [44] focus on analyzing various CNN architectures, including ResNet, VGG16, and InceptionV3 [27, 71] and their own proposed CNN model featuring dense layers[20, 30, 36].”
Wu, Z., Zheng, S., Xu, Y., Wang, L., Wei, Z., & Hua, G. (2025) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2025.3646464 · Cited by 2
Tian, Y., Zhou, T., Li, D., et al. (2025) · IET Image Processing · doi:10.1049/ipr2.70254
Liu, Z., Zhang, C., He, D., et al. (2025) · Computerized Medical Imaging and Graphics · doi:10.1016/j.compmedimag.2025.102691
Gong, P., Li, J., Tian, W., Ding, X. D., Su, R., & Yue, D. (2025) · Genes · doi:10.3390/genes17010017
“In model construction, a hybrid deep learning framework named ACmix-Swin was designed, integrating the strengths of CNN and Swin-Transformer architectures to capture both local gene co-expression patterns and global regulatory signals [44–46].”
SNNcut: An Efficient Partitioning Method for Large-Scale Spiking Neural Networks Using Spike-Sharing
Xing, Q., Jin, O., Chen, Z., Du, X., Zhang, M., Deng, S., He, S., Li, Y., & Pan, G. (2025) · IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems · doi:10.1109/tcad.2025.3648616
“In addition to the three mapping strategies introduced in [39] ( Hilbert_FD , ZigZag_FD , and Circle_FD ), PSO [21] and two greedy algorithms [18] and [45] are employed to map the AlexNet [46] processed by different partitioning methods.”
Wavelet-convolutional neural network for fault prediction in coal mine seismic data
Zou, G., Han, C., Yeh, H., & Peng, S. (2025) · Scientific Reports · doi:10.1038/s41598-025-33312-z
“In rigorous benchmarking against three seminal CNN architectures—LeNet-5 representing early shallow networks 54 , AlexNet exemplifying intermediate depth 55 , and VGG16 as a deep learning baseline 56 —W-CNN variants demonstrated transformative performance.”
Li, J., Yusantay, P., Wang, K., Zhou, H., Gou, S., & Li, G. (2025) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2025.109436
Çakmakçı, C., Turan, M., Çakmakçı, Y., Ferraz, P. A., Bülbüller, F., Dalga, S., Olcar, B., Demirel, A. F., Hurma, H., & Titto, C. G. (2025) · International Journal of Agriculture Environment and Food Sciences · doi:10.31015/2025.si.16
Singhal, S., & Kumar, M. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3649101
A unified deep learning framework for segmentation in remote sensing imagery
Lokula, B., Kishore, P. V. V., & Prasad, L. V. N. (2025) · Discover Computing · doi:10.1007/s10791-025-09774-0
“The Dynamic Mask R-CNN processes the refined semantic mask and generates an [2] NWPU VHR-10 0.5488 Transferred CNN [51] NWPU VHR-10 0.5961 RICNN [52] NWPU VHR-10 0.7311 RCNN [53] NWPU VHR-10 0.6576 Fast R-CNN [54] NWPU VHR-10 0.8271 Faster R-CNN [55] NWPU VHR-10 0.8451 Rotation-Insensitive and…”
InfluentialHierarchical Cross-Modal Attention Network for Target Re-Identification
Asikuzzaman, M., Cooke, T., Islam, S. I., et al. (2025) · International Conference on Digital Image Computing: Techniques and Applications · doi:10.1109/dicta68720.2025.11302431
“Examples of CNNs include AlexNet [4], VGG [5], GoogLeNet [6], and ResNet [7].”
Pain Detection Using Deep Networks and Visual Transformers
Pinto, M. A. S., Spitale, F. R., Araujo, F. A. S., Filho, C. F. F. C., & Costa, M. G. F. (2025) · International Conference on Pattern Recognition Systems (ICPRS) · doi:10.1109/icprs66293.2025.11302853
“Image preprocessing is a critical step in deep learning pipelines and has been shown to significantly affect model performance [18].”
DPLSeg: unsupervised general segmentation model for retinal images across multiple OCT devices
Fan, C., Yu, H., Tan, Z., Yang, R., Yao, R., Huang, T., Gao, Q., Shao, Y., Lu, F., Shen, M., et al. (2025) · Biomedical Optics Express · doi:10.1364/boe.581170
“When sample sizes are limited, models show poor generalization and are prone to overfitting [17].”
A brain-to-population graph learning framework for diagnosing brain disorders
Liao, Q., Cai, W., Sun, H., Liu, D., Chen, D., Yao, D., & Guo, D. (2025) · Neural Networks · doi:10.1016/j.neunet.2025.108526 · Cited by 3
Performance Comparison of AlexNet and GoogLeNet on Pneumonia Chest X-Rays
Kumar, S. P., Panchami, B., Narayanan, V., & Bhargav, S. (2025) · Global Clinical Engineering Journal · doi:10.31354/globalce.v7i4.222
Recognition of satellite particle based on SP-YOLO model
Wang, L., Liu, W., Wang, L., et al. (2025) · Powder Technology · doi:10.1016/j.powtec.2025.122097
A Bias-Aware Learning Model for Reliable Monocular Perception Under Camera Misalignment
Wang, R., Han, G., Liu, A., et al. (2025) · International Conference on Control, Automation and Systems (ICCAS) · doi:10.23919/iccas66577.2025.11301341
Heterogeneous Model Combinatorial Defense Framework (HMCDF) for Adversarial Attacks
Lu, Y., Shen, X., Cheng, Z., Mao, Z., Zhang, Y., & Qin, J. (2025) · International Journal of Intelligent Systems · doi:10.1155/int/7868904 · Cited by 1
Classification of X-Ray Images Using CNN Models
Ersoz, H., Durmuş, B., & Gedik, M. A. (2025) · International Scientific and Vocational Studies Journal · doi:10.47897/bilmes.1814345
Yang, J., Lu, R., Buske, S., Wang, K., Zhao, S., Tao, W., Cai, M., & Liu, G. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.113671
Lv, Y. (2025) · International Conference on Artificial Intelligence and Intelligent Information Processing (AIIIP) · doi:10.1145/3778534.3778585
“On the other hand, it has also led to risks like symbols breaking into pieces, algorithms making things too similar, authority being taken apart, and ”digital colonization,” which threaten the main identity of culture and how stories are told continuously [1].”
Enhancing Robustness in Deep Convolutional Neural Networks Through Multiresolution Learning
Zhou, H., & Liang, Y. (2025) · IEEE Transactions on Artificial Intelligence · doi:10.1109/tai.2025.3648953 · Cited by 2
Kannan, H. K., Shaju, S., Shiva Prasad, E., R, S. M., Aswan, S., & Rodrigues, V. V. (2025) · International Conference on Intelligent Systems and Pioneering Innovations in Robotics and Electric Mobility (INSPIRE) · doi:10.1109/inspire67328.2025.11300573
“Machine learning has revolutionized numerous fields in the past ten years, pre-eminently computer vision [9,10].”
YCENet: An Efficient and Robust One-Stage Detector for Infrared Targets in Complex ScenariosPreprint
Yang, X., Wang, Y., Liang, R., et al. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5983715
Evaluating the effectiveness of selected tools in recognizing emotions from facial photos
Wierzbowski, K. (2025) · Journal of Computer Sciences Institute · doi:10.35784/jcsi.7973 · Cited by 1
“Unlike CNNs, which rely on local receptive fields and hierarchical feature extraction [8], ViTs treat an image as a sequence of fixed-size patches and apply self-attention mechanisms to model global dependencies between them [9].”
Collaborative Subspace Learning for Unsupervised Feature Selection
Cai, Y., Yang, X., Chang, F., et al. (2025) · International Conference on Wavelet Analysis and Pattern Recognition · doi:10.1109/icwapr66259.2025.11306895
“With the advent of the era of big data, high-dimensional data is increasingly widely applied in fields such as computer vision [1] and biomedicine [2].”
Design and Research on LeNet5 Convolutional Neural Network Accelerator Based on HLS
Peng, C. (2025) · IEEE International Conference on Information Systems and Computer Aided Education (ICISCAE) · doi:10.1109/iciscae66104.2025.11307394 · Cited by 2
“For handwritten digit recognition tasks, the input is typically a 32×32-pixel grayscale image normalized to the [0,1] interval to mitigate illumination variations [12] .”
Şevik, U. (2025) · Düzce Üniversitesi Orman fakültesi ormancılık dergisi/Düzce Üniversitesi Orman Fakültesi ormancılık dergisi · doi:10.58816/duzceod.1814094 · Cited by 1
Evaluating Classification Reliability of Swiftlet Nest Images Using PaCMAP and TriMap Embeddings
Parhusip, H. A., Trihandaru, S., Hartanto, D., et al. (2025) · International Conference on Informatics and Computing (ICIC) · doi:10.1109/icic68054.2025.11309484
Performance Analysis of GRU, LSTM, and RNN for BISINDO Sign Language Recognition
Hulliyah, K., Prihatmiko, K., Mintarsih, F., et al. (2025) · International Conference on Informatics and Computing (ICIC) · doi:10.1109/icic68054.2025.11309413
“The model's capacity can be controlled by varying the width and depth of a Krizhevsky model [24].”
Multi-Scale Attention U-Net for Real-Time Object Detection in Complex Scenes
You, H., Xing, J., Wang, X., et al. (2025) · International Conference on Information Science and Technology · doi:10.1109/icist66592.2025.11306498
“CNNs can extract texture, colour, and geometric features in images to predict the temperature, composition, and flow state of molten steel [1].”
Chen, C. (2025) · IEEE International Conference on Information Systems and Computer Aided Education (ICISCAE) · doi:10.1109/iciscae66104.2025.11307757
Kaur, G., Qureshi, I., & Bagde, A. (2025) · International Conference on Sustainable Communication Networks and Application (ICSCNA) · doi:10.1109/icscn67106.2025.11308260
“CNN employed for posture classification achieves 94.3 per cent accuracy in identifying different agricultural activities, including harvesting, weeding, and pruning, enabling task-specific assistance profiles to optimise support for each activity type [44], [45], [46].”
InfluentialBreaking Myths in LLM scaling and emergent abilities with a comprehensive statistical analysis
Sun, K., & Wang, R. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.132542 · Cited by 13
Implementation of Object Detection Method Using YOLOv8n for Hompimpa Game
Dewi, E. N. F., Hidayat, E. W., Rachman, A. N., et al. (2025) · International Conference on Informatics and Computing (ICIC) · doi:10.1109/icic68054.2025.11309696
Liang, A., Zang, X., He, J., et al. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5986082
LCHnet: Research on Image Classification Based on Low-Rank Neural Networks
He, Y., Liu, W., Chang, H., et al. (2025) · IEEE International Conference on Information Systems and Computer Aided Education (ICISCAE) · doi:10.1109/iciscae66104.2025.11307238
Research on DOA estimation based on Transformer model
Wang, C. (2025) · Journal of Computer Science and Frontier Technologies · doi:10.63313/iscia.69022
PolyPE: An Efficient Multi-Precision Multi-Mode Floating-Point Processing Element for HPC and AI
Jia, Z., Tan, H., Yang, L., Guo, H., Zeng, K., Chang, J., Wang, Y., & Huang, L. (2025) · IEEE International Conference on Computer Design: VLSI in Computers and Processors (ICCD) · doi:10.1109/iccd65941.2025.00014
“In [19] and [20], the dot-product operation is supported, multiple products are added together directly in [10] and accumulated with an addend in [11].”
3D vehicle detection improving method fusing image and LiDAR in foggy environment
Niu, S., Zhigang, X., & Cui, Z. (2025) · Journal of Highway and Transportation Research and Development (English Edition) · doi:10.26599/htrd.2025.9480083
Enhanced Classification of Kidney Abnormalities using CNN-XGBoost Hybrid Framework
B, N. U., Shetty, S., Rao, S., et al. (2025) · International Conference on Sustainable Communication Networks and Application (ICSCNA) · doi:10.1109/icscn67106.2025.11308663
“The goal of this study is to classify kidney CT images into four categories cysts, stones, tumors, and normal kidneys with high accuracy and robustness[10].”
Hierarchical spatio-temporal graph network for risk prediction
Chen, F., Jia, H. B., Zhou, W., Zhu, L., & Xiao, L. (2025) · Scientific Reports · doi:10.1038/s41598-025-33873-z · Cited by 1
Influence of activation function in deep learning for cutaneous melanoma identification
Szymczyk, A., & Skublewska‐Paszkowska, M. (2025) · Journal of Computer Sciences Institute · doi:10.35784/jcsi.8064
“Following augmentation, the images were converted to tensors and normalized based on the mean and standard deviation values of the ImageNet dataset: [0.485, 0.456, 0.406] for mean and [0.229, 0.224, 0.225] for standard deviation [19].”
InfluentialRobust Clustering via multi-view Low-Rank Representation
Yang, C.-W., Zhao, Y., Wang, Y., et al. (2025) · International Conference on Wavelet Analysis and Pattern Recognition · doi:10.1109/icwapr66259.2025.11306536
“Therefore, researchers have conducted extensive research on representation learning tasks, achieving a series of related researches and applying them to related fields such as speech recognition [13], image processing [14], etc.”
Amokrane, S.-B., Stanković, M. R., Madoński, R., et al. (2025) · Proceedings of the Institution of Mechanical Engineers Part I Journal of Systems and Control Engineering · doi:10.1177/09596518251399939
GCaSNet: Global Context-Aware Selective Detection Network for Rail Surface Defect Detection
Hua, Y., Yang, Y. H., Sheng, W., Zhu, S., Zhu, J., & Li, Q. (2025) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2025.3612032
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
