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 105,601–105,700 of 108,435
The Symbol of Time: Efficiency of shape stimuli drives time estimatesPreprint
Macedo, G., & Wiener, M. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5688367
Distance, classification and deep learning
Nixon, M. S., & Aguado, A. S. (2025) · Elsevier eBooks · doi:10.1016/b978-0-443-36686-4.00002-x
Zekun, S., Liu, T., Zhao, Z., et al. (2025) · Acta Physica Sinica · doi:10.7498/aps.75.20251048
Liu, J., Liu, Z., Hu, B., & Hou, Z. (2025) · Concurrency and Computation Practice and Experience · doi:10.1002/cpe.70198
Understanding Data Preprocessing for Effective End-to-End Training of DNN
Gong, P., Ma, Y., Li, C., Ma, X., & Noh, S. H. (2025) · Lecture notes in computer science · doi:10.1007/978-981-95-1021-4_23
Pig cough detection using deep features and an improved SKA-TDNN model
Jie, D., Jiang, P., Li, T., et al. (2025) · Tropical Animal Health and Production · doi:10.1007/s11250-025-04725-9
“Grouped Convolution is a technique that partitions the input features into multiple groups and applies independent convolution operations within each group, thereby signifi - cantly reducing computational overhead(Krizhevsky et al. 2017 ).”
Alotaibi, S., Al-Hadhrami, S. A., & Al-Ahmadi, S. A. (2025) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2025.1646176
A Deep Learning Techniques for Brain Tumor Detection Using MRI Imaging : A Review
Joshi, P. V. M., Sudhakar, T. G., & Dattatray, H. P. (2025) · International Journal of Advanced Research in Science Communication and Technology · doi:10.48175/ijarsct-29643
Furferi, R. (2025) · Textiles · doi:10.3390/textiles5040053 · Cited by 1
Boukouvalas, D. T., Bissaco, M. A. S., Dellê, H., Deana, A. M., Belan, P. A., & de Araújo, S. A. (2025) · BioMedInformatics · doi:10.3390/biomedinformatics5040061
“There are several CNN architectures, many of which were developed focusing on the classification of the image set provided by the ImageNet Project [24], which contains more than 14 million images distributed in 100 classes.”
Detecting Shilling Attacks Using Hybrid CNN+Bi-LSTM Model of Social Networks
Sunitha, M., & Venkatesh, N. (2025) · doi:10.1109/iccds64403.2025.11209761
“A spatial feature extraction process occurs in the CNN [17] model through its application of convolutional filters to user-item interaction matrices.”
Shahrbabak, S. M., Youn, B. D., Cheng, H., et al. (2025) · Sensors · doi:10.3390/s25216678
“The CNN architecture is essentially a one-dimensional adaptation of AlexNet [29], which includes 5 convolutional layers for feature extraction and 3 fully connected layers for label prediction (Figure 2).”
Lightweight Deep Learning Model for Drowsiness Detection
Harits, R. A., Karna, N., & Wijayanto, I. (2025) · 2025 IEEE International Conference on Networking, Intelligent Systems, and IoT (ICONS-IoT) · doi:10.1109/icons-iot65216.2025.11210923
“According to Sandler et al. [16], MobileNetV2 outperforms traditional convolutional architectures such as AlexNet [25], VGG16 [26], InceptionV3 [27], and ResNet [28] in terms of accuracy while maintaining a significantly smaller model size.”
ASE-RAE: an attention-based squeeze-excitation residual autoencoder for medical image denoising
Babu, T., Murthy, H. S. N., Surya, G., & Muthalakshmi, M. (2025) · The Imaging Science Journal · doi:10.1080/13682199.2025.2581929
A parallel dual-stream spatial–temporal attention network for cement raw meal fineness prediction
Liu, G., Zhai, S., Hao, X., Xu, X., Xie, S. Q., & Liu, M. (2025) · Chemical Engineering Science · doi:10.1016/j.ces.2025.122929
UGRS: Uncertainty-Guided Gaussian Representation Sharing for Imbalanced Data
Hao, L., Liu, X., Liu, Y., et al. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3628846
Energy Efficient Implementation of CNNs Using Pruning: Techniques and Insights
Pinto, D. G., & Mane, S. B. (2025) · International Conference on Information, Implementation, and Innovation in Technology (I2ITCON) · doi:10.1109/i2itcon65200.2025.11210640
Fingerprint Recognition Using Modified EfficientNetV2 and Transfer Learning
Singla, A., Kaur, A. A., Jain, P., et al. (2025) · IEEE World Conference on Applied Intelligence and Computing (AIC) · doi:10.1109/aic66080.2025.11212178
“The loss function used in this model is categorical cross-entropy ( ∁ ) [22] shown in equation (1) below: where 𝛼 ! is the actual data, 𝛽 ! is the predicted data.”
Real-Time Drone Flight Height Decision for 3D Building Reconstruction with NeRF
Jia, S., Niu, C., & Wu, F. (2025) · IEEE International Conference on Mobile Ad-Hoc and Smart Systems (MASS) · doi:10.1109/mass66014.2025.00033
“We take four common CNN architectures for example, including ResNet50 [16], EfficientNet-B3 [17], MobileNetV3 [18], and AlexNet [19], to illustrate the construction process of PSNR prediction models, as shown in Figure 5.”
Adversarial Sample Attacks and Defense Methods for AI Classification Models
Ding, Y., Wang, B., Song, H., & Shen, L. (2025) · International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery (CyberC) · doi:10.1109/cyberc66434.2025.00013
“Benefiting from the advancements in deep learning, intelligent classification models have been widely applied in practical scenarios such as autonomous driving, security surveillance, facial recognition, and industrial inspection, bringing great convenience to society [1], [2], [3], [4], [5], [6].”
Deep Learning Techniques for Throat Cancer Detection: A Comprehensive Review
Arpita, & Soni, S. (2025) · doi:10.1109/i2itcon65200.2025.11210606
“By recognizing complex patterns linked to oral cancer, developments in deep neural networks and automated systems provide encouraging answers [8].”
Enhancing image feature representation through maximum gaussianity discriminative normalization flow
Li, J., Cai, F., Dong, Z., et al. (2025) · Engineering Research Express · doi:10.1088/2631-8695/ae1b64
Neves, H. P., Santos, A. Á. B., & da Costa, L. H. C. (2025) · Caderno Pedagógico · doi:10.54033/cadpedv22n13-018
Kim, S.-O., Lee, J. J., & Wang, S. (2025) · Economic and Environmental Geology · doi:10.9719/eeg.2025.58.5.561
Udomwong, P., Pamonsupornwichit, T., Kodchakorn, K., & Tayapiwatana, C. (2025) · Frontiers in Bioinformatics · doi:10.3389/fbinf.2025.1684042
The Cognitive Science of Deep Learning: Neural Networks in Educational Achievement
Charly, S. (2025) · International Journal of Teacher Education Research Studies (IJTERS) · doi:10.63090/ijters/3049.1614.0020
Kurniawan, A., Mohandes, M. A., Iqbal, N., et al. (2025) · FME Transaction · doi:10.5937/fme2504537k
Wu, J., Ma, D., Chen, X., et al. (2025) · IEEE Antennas and Wireless Propagation Letters · doi:10.1109/lawp.2025.3629029
Cycle-GAN-based spectral reconstruction of ambient THz-TDS data for water-vapor suppression
Park, M., Kim, J., Park, W., & Lee, J. W. (2025) · Optics Express · doi:10.1364/oe.575420
Comprehensive Analysis of Deep Learning for Early and Accurate Plant Disease Identification
Radad, M., Essam, Z., El-Fishawy, N. A., et al. (2025) · 2025 4th International Conference on Electronic Engineering (ICEEM) · doi:10.1109/iceem66692.2025.11225297
“AlexNet [11] was one of the earliest deep CNN architectures that achieved significant success in image classification, winning ILSVRC-2012.”
AraBert MIXUP Transformer Data Augmentation
Hamwi, A., Aboukassem, M., & Ghneim, N. (2025) · IEEE Congress on Information Science and Technology (CiSt) · doi:10.1109/cist65886.2025.11224124
“The process of augmenting datasets through modified versions of their samples has proven to be highly effective in various domains, such as image classification [2] [13] [14] and sound classification [15].”
Spinal Health: A Machine Learning-Based Approach for Scoliosis Detection Using MobileNetV2
Agnaber, K., & Chtouki, Y. (2025) · IEEE Congress on Information Science and Technology (CiSt) · doi:10.1109/cist65886.2025.11224086 · Cited by 1
HAOT: Heterogeneous Hardware-Aware Tensor Computation Optimization Framework via Transformer
Wu, Z., Wang, H., Li, N., Cao, H., & Liu, Y. (2025) · IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems · doi:10.1109/tcad.2025.3629566 · Cited by 1
“T ENSOR computations play critical roles in a wide range of domains, including machine learning [1], [2], data analytics [3], and scientific computing [4].”
MGCFDN: Image copy-move forgery detection method based on multi-granularity feature consistency
Tu, H., Liang, P., Lu, X., & Zhao, H. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.132029
Impact of image segmentation on video frame classification performance with tiny objects
Stefański, P., Jach, T., & Kozák, J. T. (2025) · Procedia Computer Science · doi:10.1016/j.procs.2025.09.132
Explainable Deep Learning Framework for Classification of Total Hip Arthroplasty Gaits
Pantonial, R., & Simić, M. (2025) · Procedia Computer Science · doi:10.1016/j.procs.2025.09.196 · Cited by 1
Venkatraman, S., R., J., & Kavitha, M. (2025) · Comput. Biol. Medicine · doi:10.1016/j.compbiomed.2025.111276 · Cited by 1
Traffic Safety Evaluation Based on Macroscopic Traffic Features in Road Tunnels
Zhang, Y., Jia, L., Miao, H., et al. (2025) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3746252.3761296
“This model combines Convolutional neural network (CNN) [23] and Focal Loss (FL) [26] to predict crash risk in real time.”
InfluentialBOVIS: Bias-Mitigated Object-Enhanced Visual Emotion Analysis
Lee, Y., Lee, S., Cha, J., Yang, J., & Park, E. (2025) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3746252.3761180 · Cited by 2
“The experiments include comparisons with classic deep learning models such as AlexNet [16], VGG-16 [31], ResNet-50 [9], DenseNet-121 [11], and ViT [8], as well as VEA-oriented methods like WSCNet [42], PDANet [52], Stimuli-aware [41], MDAN [35], and OSANet [18].”
A Comprehensive Toolkit for Generalized Robust Vision
Li, Z., Chen, Y., Xue, H., et al. (2025) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3746252.3761631
Wang, J., Zhang, S., Lai, J., et al. (2025) · Science China Technological Sciences · doi:10.1007/s11431-025-3057-5
Optimizing resource allocation for geographically-distributed inference by large language models
Sun, T., He, T., Ji, B., & Parag, P. (2025) · Performance Evaluation · doi:10.1016/j.peva.2025.102527
“It is further divided into pipeline parallelism that assigns model parameters at the granularity of layers [9, 10, 11], and tensor parallelism that assigns model parameters at the granularity of neurons [12, 13, 14].”
Peng, L., & Song, Y. J. (2025) · Elsevier eBooks · doi:10.1016/b978-0-443-43950-6.00005-8
Fundamentals of Deep Learning Optimization Techniques
Peng, L., & Song, Y. (2025) · Elsevier eBooks · doi:10.1016/b978-0-443-43950-6.00001-0
Liu, C., Chen, Y., Zhang, T., & Lu, Q. (2025) · Earth Science-Journal of China University of Geosciences · doi:10.3799/dqkx.2024.114
Multiscale Dynamic Inference Acceleration for Deep Neural Networks
Zhang, C., Liu, H., Wang, H., Du, W., Wang, J., & Zheng, S. (2025) · Communications in computer and information science · doi:10.1007/978-981-95-2566-9_21
Wu, Y., Xu, X., Gong, X., Cheng, Q., Yao, C., He, F., & Cheng, J. (2025) · Digital Health · doi:10.1177/20552076251395553
Liang, Q., Lai, Y., Deng, S., et al. (2025) · IEEE Sensors Journal · doi:10.1109/jsen.2025.3628829
“Moreover, all pretrained models employed in our study are derived from the official PyTorch versions [29] pretrained on the ImageNet-1k dataset [30].”
A Hybrid CNN-SVM Algorithm for Detecting Manufacturing Defects
Karakaş, B., & Kulluk, S. (2025) · IEEE Access · doi:10.1109/access.2025.3630968 · Cited by 1
Li, X., Xiao, Y., Zheng, Y., Zhang, J., & Leung, C.-S. (2025) · IEEE Transactions on Consumer Electronics · doi:10.1109/tce.2025.3631148
“These networks have demonstrated notable performance in perceptual tasks [47], [48], [49].”
Using deep learning techniques to detect and classify weeds in Fagopyrum esculentum crops
Риксен, В. С., & Shpak, V. A. (2025) · Siberian Herald of Agricultural Science · doi:10.26898/0370-8799-2024-12-1
Leveraging artificial intelligence for integrative omics analysis to elucidate Covid-19 response
Zetum, A. S. S., Moraes, A. V. P., Brioschi, A. G., Corrêa, C. H. P., Rocha, F. V. V., de Oliveira, J. R., Borges, R. P., Roza, T. L. D. O., Casotti, M. C., Cavalieri, D. C., et al. (2025) · Network Modeling Analysis in Health Informatics and Bioinformatics · doi:10.1007/s13721-025-00646-7
“The fundamental architecture of an ANN comprises three primary components: the input layer, which receives data; the hidden layers, responsible for intricate data processing through complex calculations; and the output layer, which provides the final outcomes of the process (Krizhevsky et al. 2017).”
Sandhya, L., & Khan, M. S. (2025) · Lecture notes in networks and systems · doi:10.1007/978-981-96-8441-0_5
A deep learning-based MRI automatic detection model for spinal schwannoma and meningioma
Liu, Y., Liu, Y., Cai, J., et al. (2025) · Medical & Biological Engineering & Computing · doi:10.1007/s11517-025-03468-x
“To solve the problem of insufficient data volume and imbalance, we performed the following data expansion: the data set was expanded eight times by using data augmentation techniques [21] on the original data, using rotation, scaling, and clipping as well as their combination methods.”
A Hierarchy of Hilbert Spaces for Computing with Granular Semantics by Deep Learning Enhanced
Kaburlasos, V. G., Siavalas, G., & Bris, L. (2025) · IntechOpen eBooks · doi:10.5772/intechopen.1013226
Utilization of Diffusion Models for Noise Reduction in Ultrasound Images
Setlak, B., Drotár, P., & Gazda, M. (2025) · doi:10.1109/ipta66025.2025.11222045
“Convolutional neural networks (CNNs) [11] have become a cornerstone in this area due to their ability to learn complex noise patterns directly from data.”
Toward Fair Adversarial Defense via Class Encourage-Suppress Robust Learning
Liu, D., Zhou, Z., Peng, C., et al. (2025) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2025.3632217
Chang, S., Huang, S., Yang, Z., et al. (2025) · Lecture notes in networks and systems · doi:10.1007/978-981-96-5006-4_75
A dual approach: CNN - KMeans vs ResNet-decision tree for diabetic retinopathy classification
Maddala, S., Devi, Y. S., Patil, J. S., et al. (2025) · AIP conference proceedings · doi:10.1063/5.0298319
Kızıloluk, G. D., & Akın, M. (2025) · International Artificial Intelligence and Data Processing Symposium (IDAP) · doi:10.1109/idap68205.2025.11222306
Feature Fusion Units for Fine-grained Image CategorizationPreprint
Zhao, H., Liu, Z., Yang, B. F., Lu, T., & Xing, Y. (2025) · Research Square · doi:10.21203/rs.3.rs-7717226/v1
Transformer-based Multimodal Framework for Misogynous Meme Identification
Singh, N. K., Das, P., Singh, P., & Chand, S. (2025) · IETE Journal of Research · doi:10.1080/03772063.2025.2586735
“For image, models like AlexNet [19], VGG [20], Inception [21], ResNet [22], DenseNet [23], EfficientNet [24] are widely used.”
Berger, P., & von Garrel, J. (2025) · Cureus Journal of Business and Economics. · doi:10.7759/s44404-025-07591-8
“These advancements became particularly evident during the 2010s with the milestones in generative AI, which demonstrated its transformative capabilities (Krizhevsky et al., 2012).”
Deepika, S., & Arunachalam, V. (2025) · Scientific Reports · doi:10.1038/s41598-025-23303-5
A Parkinson’s Disease Recognition Method Based on Plantar Pressure Feature Fusion
Ma, L., & Huo, H. (2025) · Technologies · doi:10.3390/technologies13110522
Swin-Det and MOVE-Net Based Drone Target Tracking and Camera Movement Classification Methods
Wen, M.-G. (2025) · International Conferences on Computers, Information Processing and Advanced Education · doi:10.1109/cipae66821.2025.00052
“Paper [5] used pre-trained weights of famous CNN models such as VGG [6], AlexNet [7], and GoogleNet [8] on ImageNet, and performed transfer training on a shot scale dataset containing 120 movie materials with three categories (close-up, medium shot, long shot), achieving an accuracy of 94%.”
A Conceptual Theoretical Model Integrating Machine Learning for Intelligent Transportation Systems
Andreev, D., & Trifonov, R. I. (2025) · International Scientific Conference on Computer Science (COMSCI) · doi:10.1109/comsci67172.2025.11225195
“CNNs are utilized in autonomous driving systems for lane detection, traffic sign recognition, and object tracking [7], while RNNs and Long Short-Term Memory (LSTM) models are used to model sequential dependencies in traffic data, enabling accurate predictions of speed and flow [3].”
Cultivator: Multi-granularity Tree Construction in Heterogeneous Edge-Cloud Training
Ding, M., Zhao, Y., Qiu, C., Gao, F., Wang, X., & Zhang, D. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-10459-5_29
Contrastive Learning-Enhanced Trajectory Matching for Small-Scale Dataset Distillation
Li, W., Sakai, S., & Hasegawa, T. (2025) · Communications in computer and information science · doi:10.1007/978-981-95-4094-5_24
Azam, M., Zeng, S., Aldihis, H., Popescu, M., & Xu, D. H. (2025) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2025.3631538
Chen, H., Ouyang, L., & Ren, B. (2025) · Multimedia Tools and Applications · doi:10.1007/s11042-025-21107-3
“The extracted features are then linearly mapped to obtain the final predictions [ 10, 11].”
Anomaly Detection Method Based on Compressed Sensing and Multi-Channel Feature Fusion
Lu, S., & Zongzuo, Y. (2025) · doi:10.1109/ijcnn64981.2025.11229014
“Convolutional Neural Networks (CNN) are deep learning models widely used in image recognition [5], video analysis [6], and natural language processing [7].”
Direction-Oriented Edge Reconstruction Network for Camouflaged Object Detection
Yang, X., Zhang, Q., & Zhou, Q. (2025) · doi:10.1109/ijcnn64981.2025.11227430
“The pre-trained PVTv2 [23] on the ImageNet dataset [38] was used as the encoder for our network.”
Towards An Unsupervised Deep Representations for Plant Species Recognition
Presner, D. H., Hochuli, A. G., & Britto, A. D. S. (2025) · doi:10.1109/ijcnn64981.2025.11229183
“Similarly, Tan et al. [29] utilized a pre-trained AlexNet model [30] for extracting image features from the MalayaKew dataset [20].”
Song, J. (2025) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn64981.2025.11228987
“Following the remarkable success of AlexNet in image classification [6], the application of deep neural networks to instance retrieval tasks has become a key area of research.”
Groundwater Seepage Modeling in a River-Canal System based on Physics-Informed Neural Networks
Chen, C., Li, Y., Han, Z., et al. (2025) · doi:10.1109/ijcnn64981.2025.11229154
CGDMamba: Boosting Remote Sensing Change Detection with Dual-Mamba
Li, X., Li, D., Fang, J., et al. (2025) · doi:10.1109/ijcnn64981.2025.11227207
“However, CNN are inherently limited by their local receptive fields, which restrict their ability to model global dependencies [9].”
Wei, W., Cao, L., zhen, Y., & Wang, Y. N. (2025) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn64981.2025.11228053
“Tao et al. [8] achieved 93.2% Average Precision(AP) with fewer parameters using a CNN-visual attention hybrid with AlexNet [9] backbone.”
InfluentialNH-YOLOv5: An Improved YOLOv5 for Real-Time Traffic Sign Detection
Li, Z., Song, J., Yu, B., et al. (2025) · doi:10.1109/ijcnn64981.2025.11227889
“Convolutional Neural Networks (CNNs) [2] to significant breakthroughs in this field.”
Kennedy, A., & Everson, R. (2025) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn64981.2025.11227282
“…is a wide range of applications, the following exemplary references just collect non-exclusively some areas for further reading: Image recognition [11], natural language processing [7], autonomous driving [5], applications in medicine [12], and prediction of stock markets [4], just to mention a…”
Cascade Adversarial Attack Search
Wang, Z., Shen, D., Sun, X., Yang, S., Yu, X., & Tian, Y. (2025) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn64981.2025.11228300
Yu, K., Fang, Y., & Yang, J. (2025) · doi:10.1109/ijcnn64981.2025.11227687
“Moreover, existing solutions, such as group convolution [22] and dilated convolution [23], have their own limitations.”
Enhanced Neural Architecture Search with Multi-Dimensional Curriculum Learning for Defect Detection
Yong, Y., & Ma, L. (2025) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn64981.2025.11228890
FM-EVT:Feedforward Neural Network and Multilayer Perceptron Classifier Enhanced Event Transformer
Liu, Y., Su, L., & Zhang, L. (2025) · doi:10.1109/ijcnn64981.2025.11228029
“ViT [13] has shown remarkable performance, often matching or exceeding that of convolutional neural networks [14] on multiple image recognition benchmarks.”
Integrating Torsion Features into Semantic Segmentation for Remote Sensing Images
Sun, X., Zhou, S., Mu, J., et al. (2025) · doi:10.1109/ijcnn64981.2025.11227267
“Inspired by AlexNet [13] proposed by Hinton et al., numerous network models utilizing Deep Convolutional Neural Networks (DCNN) for semantic segmentation have emerged, such as VGGNet [14] and ResNet [15].”
Zhang, L. M. (2025) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn64981.2025.11228354
“ViTs and Convolutional Neural Networks (CNNs) [11]–[13] have clear differences in the features and internal structures [14].”
Improving Fast Adversarial Training with Adversarial Sample Fusion
Fan, C., Sun, J., & Li, X. (2025) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn64981.2025.11227274
Tag Prediction and Recommendation with Transfer Learning: Boosting Views on Illustration Platforms
TERADA, N., & Yinxing, L. I. (2025) · Interdisciplinary Information Sciences · doi:10.4036/iis.2025.a.03
Zhao, A., Yin, J., Wang, W., Guo, Z., & Zhu, L. (2025) · Electronics · doi:10.3390/electronics14132702
Plant Disease Detection Using Deep Learning: A Focus on Pathogen-Based Classification
Rao, S. N. T., Moturi, S., Bhavani, M. M. N., et al. (2025) · Smart innovation, systems and technologies · doi:10.1007/978-981-96-6250-0_1
A lightweight model and corn leaf disease recognition
Bai, L., Zhu, S., & Gao, H. (2025) · PLoS ONE · doi:10.1371/journal.pone.0336945
Graph Neural Network for Unstructured 3D Environmental Modelling: A Symmetry Group-Based ApproachPreprint
Gao, Q., & Tang, W. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5760661
A novel lightweight network VMobileNet for visual detection of surface roughness in turning
Liu, X.-C., Li, Y., Shi, L., et al. (2025) · Measurement science and technology · doi:10.1088/1361-6501/ae2044
“In 2012, Alex et al [21] proposed the AlexNet network, which won the ImageNet competition classification task.”
Berlyand, L. V., Bourdais, T., Owhadi, H., & Shmalo, Y. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5762414
Predictive networks generate motion-induced color illusions
Ueda, K., Sinapayen, L., & Watanabe, E. (2026) · Scientific Reports · doi:10.1038/s41598-026-57953-w
Meng, B., Bayane, I., & Leander, J. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5758915
Deep Learning Image Processing for Trustworthy Equipment Fault DiagnosticsPreprint
Floreale, G., Baraldi, P., & Zio, E. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5758819
Das, D., Ghosh, P., Rout, M., et al. (2025) · Proceedings of the Institution of Mechanical Engineers Part E Journal of Process Mechanical Engineering · doi:10.1177/09544089251396285
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
