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
42 Own result · 21 Own interpretation · 7 No basis given · 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)
plainstates a cause- 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)
plainstates a cause- 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
plainstates a cause- 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 states — it cites no source for it, so there is none to check. 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
plainstates a cause- 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 states — it cites no source for it, so there is none to check. 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
plainstates a cause- 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
plainstates a cause- 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 states — it cites no source for it, so there is none to check. 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
plainstates a cause- 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
plainstates a cause- 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
plainstates a cause- 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
A result the paper states — it cites no source for it, so there is none to check. 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
plainstates a cause- 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
plainstates an association- 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.
A result the paper states — it cites no source for it, so there is none to check. 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
plainstates a possible cause- 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
plainstates a cause- 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 states — it cites no source for it, so there is none to check. 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
plainstates a cause- 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 states — it cites no source for it, so there is none to check. 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.
A result the paper states — it cites no source for it, so there is none to check. 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
plainstates a cause- 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 states — it cites no source for it, so there is none to check. 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
hedgedstates a cause- 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 states — it cites no source for it, so there is none to check. 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.
A result the paper states — it cites no source for it, so there is none to check. 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
plainstates a cause- 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 states — it cites no source for it, so there is none to check. 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
plainstates a cause- 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
boostedstates a cause- 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
plainstates a cause- 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
hedgedstates a cause- 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
plainstates a cause- 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.
A statement the paper makes itself — it cites no source for it, so there is none to check. 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
hedgedstates a cause- 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
plainstates a cause- 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
plainstates a cause- 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
plainstates a cause- 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
plainstates a cause- 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
plainstates a cause- 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
plainstates a cause- 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
plainstates a cause- 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
plainstates a cause- 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 statement the paper makes itself — it cites no source for it, so there is none to check. 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
hedgedstates a cause- 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
“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]
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
“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]
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 measured
The 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
“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]
Experimental — accuracy not yet measuredThe 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
“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
“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]
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 87,301–87,400 of 108,438
Generating Adversarial Examples with Image-To-Perturbation Network
Wang, D., Jin, W., & Wu, Y. (2020) · Chinese Control Conference (CCC) · doi:10.23919/ccc50068.2020.9188343 · Cited by 1
PCS: A Productive Computational Science Platform
Ojika, D., Gordon, R., Lam, H. X., Yoo, S., Cui, Y., Dong, Z., van Dam, K. K., Lee, S., & Kurth, T. (2019) · International Conference on High Performance Computing & Simulation (HPCS) · doi:10.1109/hpcs48598.2019.9188108 · Cited by 1
Li, X., Nie, L., Si, X., et al. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-59016-1_22 · Cited by 1
Carry Out Computer Tasks with Gesture using Image Pre-Processing and TensorFlow Framework
Magar, P., & NTC, J. (2020) · International Journal of Engineering Research and · doi:10.17577/ijertv9is090303 · Cited by 1
Convolutional neural network for preprocessing‐free bacterial Spectra identification
Kim, Y.-H., Lee, J., Ahn, G., Santos, I. C., Schug, K. A., & Kim, S. B. (2020) · Journal of Chemometrics · doi:10.1002/cem.3304 · Cited by 1
Temporal Calibrated Regularization for Robust Noisy Label Learning
Wu, D., Wang, Y., Zheng, Z., et al. (2020) · doi:10.1109/ijcnn48605.2020.9207349 · Cited by 1
Searching the Adversarial Example in the Decision Boundary
Jiang, H., Song, Q., & Kernec, J. L. (2020) · International Conference on UK-China Emerging Technologies (UCET) · doi:10.1109/ucet51115.2020.9205320 · Cited by 2
Exploratory Data Analysis and Foreground Detection with the Growing Hierarchical Neural Forest
Palomo, E. J., López‐Rubio, E., Ortega-Zamorano, F., et al. (2020) · Neural Processing Letters · doi:10.1007/s11063-020-10360-2 · Cited by 1
Maeda, K., Takahashi, S., Ogawa, T., et al. (2020) · Proceedings - International Conference on Image Processing · doi:10.1109/icip40778.2020.9190866 · Cited by 1
Wang, J., Zhao, J., & Wang, D. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-60239-0_38 · Cited by 1
Research on Autonomous Driving Perception Test Based on Adversarial Examples
Wang, Y., Sha, W., Pan, Z., et al. (2020) · Advances in intelligent systems and computing · doi:10.1007/978-981-15-8462-6_24 · Cited by 1
Empirical Study on Detecting COVID-19 in Chest X-ray Images using Deep Learning-Based Methods
Babaeipour, R., Azizi, E., Abdoli, H., & Khotanlou, H. (2022) · Current Signal Transduction Therapy · doi:10.2174/1574362418666221212105053 · Cited by 1
Raj, R. R., & null, P. T. V. B. (2020) · International Journal of Engineering and Techniques · doi:10.29126/23951303/ijet-v6i4p12 · Cited by 1
Gender Identification for Coloring Black and White Portrait with cGan
Liu, Q., Lin, M., Sun, Y., et al. (2020) · Advances in intelligent systems and computing · doi:10.1007/978-981-15-8462-6_51 · Cited by 1
Shi, Z., Cao, L., Guan, C., Ju, L., Li, Q., Gu, Z., Zheng, H., & Zheng, B. (2020) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3394171.3413646 · Cited by 1
Iris Biometrics for Secure Authentication
Alshehri, A., Daws, T., & Ezekiel, S. (2020) · International Journal of Machine Learning and Computing · doi:10.18178/ijmlc.2020.10.3.961 · Cited by 1
The Mode-Fisher pooling for time complexity optimization in deep convolutional neural networks
Mansouri, D. E. K., Kaddar, B., Benkabou, S.-E., & Benabdeslem, K. (2020) · Neural Computing and Applications · doi:10.1007/s00521-020-05406-4 · Cited by 2
Should Kernels Be Trained in CNN?- a Paradigm of AG-Net
Li, J., Shi, H., & Hwang, K. (2020) · International Conference on System Science and Engineering · doi:10.1109/icsse50014.2020.9219307 · Cited by 1
Adapting In Situ Accelerators for Sparsity with Granular Matrix Reordering
Mikhailenko, D., Nakamoto, Y., Feinberg, B., et al. (2020) · IEEE Computer Architecture Letters · doi:10.1109/lca.2020.3031907 · Cited by 1
Non-intrusive Load Decomposition of Stacked Hybrid Recurrent Neural Networks
Zhang, Z., & Fan, C. (2019) · IEEE International Conference on Advanced Power System Automation and Protection (APAP) · doi:10.1109/apap47170.2019.9225173 · Cited by 1
Permutation Learning in Convolutional Neural Networks for Time-Series Analysis
Chadha, G. S., Kim, J., Schwung, A., et al. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-61609-0_18 · Cited by 1
Improving the efficiency of human action recognition using deep compression
Phan, H., Ha, C. T., & Nguyen, T. T. (2020) · International Conference on Multimedia Analysis and Pattern Recognition (MAPR) · doi:10.1109/mapr49794.2020.9237772 · Cited by 1
Comparison of Different Models for Clothing Images Classification Studies
Luo, J. (2020) · International Conference on Artificial Intelligence and Advanced Manufacture (AIAM) · doi:10.1145/3421766.3421873 · Cited by 2
Review of Semi-Supervised Learning Methods for Medical Computer-Aided Diagnosis Systems
Chapaliuk, B. V., & Zaychenko, Y. P. (2020) · IEEE International Conference on System Analysis & Intelligent Computing (SAIC) · doi:10.1109/saic51296.2020.9239210 · Cited by 1
Video Big Data Analytics in the Cloud: Research Issues and Challenges
Alam, A., Khalid, S., Khan, M. N., Afridi, T. H., Ullah, I., & Lee, Y.-K. (2021) · Lecture notes in networks and systems · doi:10.1007/978-3-030-66840-2_108 · Cited by 2
Dharmaadi, I. P. A., & Sukarsa, I. M. (2020) · Journal of Advances in Information Technology · doi:10.12720/jait.11.4.271-276 · Cited by 1
Pham, D., & Lai, B.-C. C. (2020) · IET Circuits Devices & Systems · doi:10.1049/iet-cds.2019.0225 · Cited by 1
Examining and Mitigating Kernel Saturation in Convolutional Neural Networks using Negative Images
Gowdra, N., Sinha, R., & MacDonell, S. G. (2020) · Annual Conference of the IEEE Industrial Electronics Society (IECON) · doi:10.1109/iecon43393.2020.9255147 · Cited by 2
iSalGAN - An Improvised Saliency GAN
Goutam, K., & Balasubramanian, S. (2020) · Communications in computer and information science · doi:10.1007/978-981-15-8697-2_20 · Cited by 1
Visual Objects As Context: Exploiting Visual Objects for Lexical Entailment
Muraoka, M., Nasukawa, T., & Bhattacharjee, B. (2020) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2020.findings-emnlp.246 · Cited by 1
A Novel Intelligence-Based Pan-Tilt Platform System for Measuring the Trajectories of Parachute
Tang, Z., Yang, J., Pei, Z., et al. (2020) · IEEE Conference on Industrial Electronics and Applications (ICIEA) · doi:10.1109/iciea48937.2020.9248255 · Cited by 1
Stacked conditional adversarial networks and multi-patch loss for image depth estimation
Bhatia, A. (2020) · IEEE SoutheastCon · doi:10.1109/southeastcon44009.2020.9249700 · Cited by 1
Disguising Personal Identity Information in EEG Signals
Liu, S., Yao, Y., Xing, C., et al. (2020) · Communications in computer and information science · doi:10.1007/978-3-030-63823-8_11 · Cited by 1
Omnidirectional Ring Structured Light Noise Filtering Based On DCGAN Network And Autoencoder
Li, W., Jia, T., Chen, Q., et al. (2020) · International Conference on Culture-oriented Science & Technology (ICCST) · doi:10.1109/iccst50977.2020.00093 · Cited by 1
Preißler, M., Jobmann, S., & Notni, G. (2020) · Springer eBooks · doi:10.1007/978-3-662-62442-5_4 · Cited by 1
Few-Shot Classification with Transductive Data Clustering Transformation
Wang, H., Lian, J., & Xiong, S. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-63833-7_31 · Cited by 1
Automatic Generation of Training Data for Deep Learning in AR-based Transportation Support System
Abe, T., Takahashi, S., & Hagiwara, T. (2020) · IEEE International Conference on Consumer Electronics - Taiwan (ICCE-Taiwan) · doi:10.1109/icce-taiwan49838.2020.9258224 · Cited by 1
Research on three-step accelerated gradient algorithm in deep learning
Lian, Y., Tang, Y., & Zhou, S. (2020) · Statistical Theory and Related Fields · doi:10.1080/24754269.2020.1846414 · Cited by 1
A Reading Recognition Model of Pointer Type Oil-level Meter Based on Improved Resnet
Liang, X., Wang, Y., Zhang, Y., et al. (2020) · IEEE International Conference on High Voltage Engineering and Application (ICHVE) · doi:10.1109/ichve49031.2020.9279457 · Cited by 1
Cross-Modal Retrieval via Similarity-Preserving Learning and Semantic Average Embedding
Zhi, T., Fan, Y., & Han, H. W. (2020) · IEEE Access · doi:10.1109/access.2020.3044169 · Cited by 1
MobiVision: A Novel Energy-Efficient Mobile Deep Learning Framework for Computer Vision
Dai, X., Liu, X., Liu, G., Yang, Q. P., & Xing, T. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-64243-3_32 · Cited by 1
Real-Time Person Segmentation – Based on Body Pix
Garg, A. M. A. M. (2020) · International Journal for Modern Trends in Science and Technology · doi:10.46501/ijmtst061201 · Cited by 1
Communication Optimization Schemes for Accelerating Distributed Deep Learning Systems
Lee, J., Choi, H., Jeong, H., Noh, B., & Shin, J. S. (2020) · Applied Sciences · doi:10.3390/app10248846 · Cited by 1
Kernel-convoluted Deep Neural Networks with Data Augmentation
Kim, M., Kim, Y.-G., Kim, D. H., Kim, Y., & Paik, M. C. (2021) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v35i9.16993 · Cited by 1
Reducing Triangle Inequality Violations with Deep Learning and Its Application to Image Retrieval
Khamiyev, I., Gabidolla, M., Iskakov, A., et al. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-64559-5_24 · Cited by 1
Kelley, T. D., & Dickerson, K. (2020) · Cited by 1
Sparse Signal Models for Data Augmentation in Deep Learning ATR
Agarwal, T., Sugavanam, N., & Ertin, E. (2023) · Remote Sensing · doi:10.3390/rs15164109 · Cited by 4
Grouping Feature Learning for Giant Panda Face Recognition
Wang, H., Su, H., Chen, P., et al. (2020) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc42975.2020.9283455 · Cited by 1
DrCaptcha: An interactive machine learning application
Glikis, R., Makris, C. H., & Tsirakis, N. (2020) · Computer Science and Information Systems · doi:10.2298/csis200130048g · Cited by 1
Prediction of Quality Indicators of Iron Ore Processing Operations Using Deep Neural Networks
Eremenko, Y. I., Полещенко, Д. А., & Tsygankov, Y. A. (2020) · International Conference on Control Systems, Mathematical Modeling, Automation and Energy Efficiency (SUMMA) · doi:10.1109/summa50634.2020.9280676 · Cited by 2
Cheng, Z., Juelin, Z., Chen, C., Yu, X., Wu, F., Li, Y., & Zeng, Z. (2020) · IEEE International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc45102.2020.9294755 · Cited by 1
Detection for Liver Fibrosis Based on Computer Simulation by Deep Learning
He, M., Yin, H., Liu, P., et al. (2020) · International Conference on Robotics, Intelligent Control and Artificial Intelligence (RICAI) · doi:10.1145/3438872.3439073 · Cited by 1
Improved Loss Function for Defect Detection of Mobile Phone Screen
Wang, Z., Li, C., Yifan, Z., Zhang, F., Chang, S., & Yilei, L. (2020) · EAI International Conference on Mobile Multimedia Communications (MobiMedia) · doi:10.4108/eai.27-8-2020.2294669 · Cited by 1
Breast Cancer Recognition Algorithm Based on Convolution Neural Network
Jiang, J., Li, X., Wang, J., & Lim, S. (2020) · Journal of Medical Imaging and Health Informatics · doi:10.1166/jmihi.2021.3315 · Cited by 1
Attention-based Hierarchical Convolution Neural Network for Fine-grained Crop Image Classification
Yang, J., Zhang, F., & Qian, T. (2020) · IEEE International Conference on Internet of Things (iThings) and IEEE Green Computing and Communications (GreenCom) and IEEE Cyber, Physical and Social Computing (CPSCom) and IEEE Smart Data (SmartData) · doi:10.1109/ithings-greencom-cpscom-smartdata-cybermatics50389.2020.00035 · Cited by 1
Natural vs balanced distribution in deep learning on whole slide images for cancer detection
Reshma, I. A., Cussat‐Blanc, S., Ionescu, R. T., Luga, H., & Mothe, J. (2021) · ACM Symposium on Applied Computing · doi:10.1145/3412841.3441884 · Cited by 6
Learning hierarchical face representation to enhance HCI among medical robots
Sun, D., Zhao, H., Song, T., Liu, A., Cheng, J., Liu, Z., & Zhao, X. (2021) · Future Generation Computer Systems · doi:10.1016/j.future.2020.11.007 · Cited by 2
Online Handwritten Arabic Digits (Indian) Recognition using Deep learning
Yaagoup, K. M. M., & Hamid, A. E. (2020) · IJARCCE · doi:10.17148/ijarcce.2020.91109 · Cited by 1
Li, L., Liu, Y., & Chen, Z. (2020) · International Conference on Computing and Pattern Recognition (ICCPR) · doi:10.1145/3436369.3436474 · Cited by 1
Bilingual Transfer Learning for Online Product Classification
Lehmann, E. L., Simonyi, A., Henkel, L., & Franke, J. (2020) · Cited by 2
Have Fun Storming the Castle(s)!
Anderson, C., Teuscher, A., Anderson, E., Larsen, A., Shirley, J., & Farrell, R. J. (2021) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv48630.2021.00375 · Cited by 2
Gnatyuk, V., & Moskalenko, A. (2020) · IEEE International Joint Conference on Biometrics (IJCB) · doi:10.1109/ijcb48548.2020.9304934 · Cited by 1
Brillet, L. F., Leclaire, N., Mancini, S., Nicolas, M. M., Cleyet-Merle, S., Henriques, J.-P., & Delnondedieu, C. (2021) · Journal of Signal Processing Systems · doi:10.1007/s11265-020-01616-0 · Cited by 1
Evolving Optimal Convolutional Neural Networks
Banerjee, S., & Mitra, S. (2020) · IEEE Symposium Series on Computational Intelligence (SSCI) · doi:10.1109/ssci47803.2020.9308201 · Cited by 1
Malarial Parasite Detection by Leveraging Cognitive Algorithms: A Comparative Study
Sharma, R., Thanvi, A., Goyal, D., et al. (2021) · Lecture notes in networks and systems · doi:10.1007/978-981-15-9689-6_78 · Cited by 1
Semantic Segmentation Based on Deeplabv3+ With Fractional-Order Image Enhancement Convolution Kernel
Zheng, T. (2020) · doi:10.1145/3425577.3425584 · Cited by 1
Utilizing Indonesian Universal Language Model Fine-tuning for Text Classification
Bunyamin, H. (2021) · Journal of Information Technology and Computer Science · doi:10.25126/jitecs.202053215 · Cited by 2
Image Classification Using Reinforcement Learning
Elizarov, A. A., & Razinkov, E. (2020) · Russian Digital Libraries Journal · doi:10.26907/1562-5419-2020-23-6-1172-1191 · Cited by 1
Crowd Counting Based on Multiresolution Density Map and Parallel Dilated Convolution
Tang, J., Zhou, M., Li, P., et al. (2021) · Scientific Programming · doi:10.1155/2021/8831458 · Cited by 1
Exploring Optimal Adaptive Activation Functions for Various Tasks
Liu, A., Hu, H., Qiu, T., Zhou, Q., Guan, Q., & Li, X. (2020) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm49941.2020.9313386 · Cited by 1
Transmembrane Receptor Dynamics as Biophysical Markers for Assessing Cancer Cells
Kim, M., & Liu, Y. (2021) · Springer eBooks · doi:10.1007/978-981-10-4857-9_38-1 · Cited by 1
Adversarial Deception in Deep Learning: Analysis and Mitigation
Wei, W., Liu, L., Loper, M. L., Chow, K.-H., Gürsoy, M. E., Truex, S., & Wu, Y. (2020) · IEEE International Conference on Trust, Privacy and Security in Intelligent Systems and Applications (TPS-ISA) · doi:10.1109/tps-isa50397.2020.00039 · Cited by 1
Comparative study of Image Classification Algorithms
Pandey, H. A. D. J. A. A. T. U. (2021) · International Journal for Modern Trends in Science and Technology · doi:10.46501/ijmtst070120 · Cited by 1
An Effective Hybrid Deep Learning Model for Eukaryotic Promoter Identification
Wang, Y., Peng, Q., Xu, M., Han, T., Sun, Z., & Wang, X. (2020) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm49941.2020.9313461 · Cited by 1
Adversarial Convolutional Neural Network for Text Classification
Li, L., Zhu, Z. Q., Du, D., et al. (2020) · International Conference on Electronic Information Technology and Computer Engineering (EITCE) · doi:10.1145/3443467.3443837 · Cited by 1
Saliency Detection by Superpixel Ranking for Person Re-identification
Dang-Nguyen, C., Ho-Phuoc, T., & Truong, N. (2020) · NAFOSTED Conference on Information and Computer Science (NICS) · doi:10.1109/nics51282.2020.9335858 · Cited by 1
Variational value learning in advantage actor-critic reinforcement learning
Zhang, Y., Han, J., Hu, X., & Dan, S. (2020) · Chinese Automation Congress · doi:10.1109/cac51589.2020.9327530 · Cited by 1
A Weighted Federated Averaging Framework to Reduce the Negative Influence from the Dishonest Users
Zhao, F., Huang, Y., Zhu, S., Malladi, V. S., & Wu, Y. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-68851-6_17 · Cited by 1
LSTM Based Source Code Generation for Turkish Pseudo Code of Algorithm
İnce, M. (2021) · Düzce Üniversitesi Bilim ve Teknoloji Dergisi · doi:10.29130/dubited.824799 · Cited by 1
Identification Model of Crop Diseases and Insect Pests Based on Convolutional Neural Network
Ai, Y., Sun, C., Liu, A., Ding, F., & Tie, J. (2021) · Lecture notes in electrical engineering · doi:10.1007/978-981-15-8599-9_64 · Cited by 1
Swallowing pattern analysis using image recognition of multi-channel surface electromyography
Suzuki, M., SASAKI, M., Tamada, Y., et al. (2019) · The Journal of Japanese Society of Stomatognathic Function · doi:10.7144/sgf.25.118 · Cited by 1
A Method of Partitioning Convolutional Layer to Multiple FPGAs
Iizuka, K., Ito, K., Hironaka, K., & Amano, H. (2020) · International SoC Design Conference · doi:10.1109/isocc50952.2020.9332929 · Cited by 1
Uma Implementação Baseada em Mask R-CNN para Detecção de Insetos em Imagens Digitais
Júnior, T. D. C., & Rieder, R. (2020) · doi:10.5753/sibgrapi.est.2020.12996 · Cited by 1
Note on the Reliability of Biological vs. Artificial Neural Networks
Stoop, R. (2021) · Frontiers in Physiology · doi:10.3389/fphys.2021.637389 · Cited by 1
The evaluation of synthetic datasets on training AlexNet for surgical tool detection
Ding, N., Jalal, N. A., Alshirbaji, T. A., et al. (2020) · Current Directions in Biomedical Engineering · doi:10.1515/cdbme-2020-3082 · Cited by 1
DeepFacematch: A Convolutional Neural Network Model for Contactless Attendance on e-SIWES Portal
Adetiba, E., Opara, A. E., Ajayi, O. T., et al. (2021) · Communications in computer and information science · doi:10.1007/978-3-030-69143-1_16 · Cited by 1
Application of Deep Learning Methods for Pedestrian Collision Detection Using Dashcam Videos
Kunitomi, S., Takayama, S., & Shirakawa, M. (2021) · SAE technical papers on CD-ROM/SAE technical paper series · doi:10.4271/2020-22-0008 · Cited by 1
Vision-Based Fault Action Detection for Industrial Robots
Peng, Y., & Chen, D. (2021) · OALib · doi:10.4236/oalib.1107189 · Cited by 1
Benchmarking the Accuracy of Algorithms for Memory-Constrained Image Classification
Müksch, S., Olausson, T., Wilhelm, J., & Andreadis, P. (2020) · IEEE/ACM Symposium on Edge Computing (SEC) · doi:10.1109/sec50012.2020.00059 · Cited by 3
Proposing Gesture Recognition Algorithm Using Two-Stream Convolutional Network and LSTM
Huu, P. N., Ngoc, T. L., & Minh, Q. T. (2021) · IEEE International Conference on Communications and Electronics (ICCE) · doi:10.1109/icce48956.2021.9352147 · Cited by 1
Feature Variance Ratio-Guided Channel Pruning for Deep Convolutional Network Acceleration
He, J., Chen, B., Ding, Y., & Li, D. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-69538-5_11 · Cited by 2
Rethinking Offline Personalized Advertising: Challenges and System Design
Sathe, A. B., & Mane, S. B. (2021) · International Journal of Computer Applications · doi:10.5120/ijca2021921074 · Cited by 1
High-Order Triplet CRF-Pcanet for Unsupervised Segmentation of SAR Image
Zhang, P., Jiang, Y., Li, B., et al. (2020) · IEEE International Geoscience and Remote Sensing Symposium (IGARSS) · doi:10.1109/igarss39084.2020.9324235 · Cited by 1
Anti-Interpolation: An Attack Facilitator Hiding Adversaries Into Images
Chen, J., Xiong, H., Zheng, H., Ming, Z., & Liu, Y. (2021) · IEEE Transactions on Circuits & Systems II Express Briefs · doi:10.1109/tcsii.2021.3061154 · Cited by 1
Versatile Auxiliary Classification and Regression With Generative Adversarial Networks
Bazrafkan, S., Varkarakis, V., Lemley, J., Javidnia, H., & Corcoran, P. (2021) · IEEE Access · doi:10.1109/access.2021.3063793 · Cited by 1
Stock Price Prediction Based on an Energy-Efficient Spiking-LSTM Hardware Accelerator
Wu, Y., Liu, Y., & Chen, T. P. (2021) · Journal of Physics Conference Series · doi:10.1088/1742-6596/1828/1/012050 · Cited by 1
Grant‐Jacob, J. A., Praeger, M. F., Loxham, M., Eason, R. W., & Mills, B. (2021) · Environmental Research Communications · doi:10.1088/2515-7620/abed94 · Cited by 1
Variable-length image compression based on controllable learning network
Zhao, D., Sun, J., Chen, L., et al. (2021) · Multimedia Tools and Applications · doi:10.1007/s11042-020-10346-1 · Cited by 1
MohammadiRad, M., & Sojodishijani, O. (2021) · Canadian Journal of Electrical and Computer Engineering · doi:10.1109/icjece.2020.2978403 · Cited by 1
Edge Computing System applying Integrated Object Recognition based on Deep Learning
Kim, K., & Oh, S. W. (2021) · International Conference on Advanced Communication Technology · doi:10.23919/icact51234.2021.9370761 · Cited by 1
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
