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 105,801–105,900 of 108,435
Noda, S., Saito, H., Kusa, K., et al. (2025) · Smart Agricultural Technology · doi:10.1016/j.atech.2025.101687
Staging pleural mesothelioma revitalized
Benamore, R. E., Xie, C., & Sobirov, I. (2025) · British Journal of Radiology · doi:10.1093/bjr/tqaf297
Liu, H., Qu, J., Li, J., Li, C., Sun, W., & Zhang, T. (2025) · The Journal of Supercomputing · doi:10.1007/s11227-025-08117-6
“The rise of convolutional neural networks (CNN) has led to the rapid development of machine vision, making it widely used in many application scenarios, such as image classification, object detection, pose estimation, image segmentation, face recognition, and many other fields [1–4].”
Zhou, R., & Xu, M. (2025) · Computers and Geotechnics · doi:10.1016/j.compgeo.2025.107806
OSLCNN: On-Demand Scheduling for Large-Scale CNN Inference Acceleration on Heterogeneous DevicesPreprint
Yang, L., zhong, D., Liu, S., Zheng, C., Li, R., & 程, 鑫. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5859191
Target Perception Attention: A New Attention Module for Multi-Scale Object Detection
Hong, C., Liu, Y., Liu, C., Chen, D., & Xu, M. (2025) · International Conference on Image Processing, Intelligent Control and Computer Engineering (IPICE) · doi:10.1145/3768184.3768215
Li, L., Sun, L., Meng, X., et al. (2025) · Research Square · doi:10.21203/rs.3.rs-8152295/v1
Wang, W., Li, Z., Zheng, L., Dai, Z., & Huang, C. (2025) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2025.3640152
Design of Transpose Convolution Layer on FPGA
Lee, J. Y., Seo, J. Y., Lee, H., & Lee, Y. H. (2025) · National Conference on Electrical and Electronics Engineering (ELECO) · doi:10.1109/iceee67194.2025.11261918
Hyperspectral imaging and artificial neural networks for oil spills automatic detection
Carrasco-García, M. G., Rodríguez-García, M. I., González-Enrique, J., Ruíz-Aguilar, J. J., Pérez, J. M. A., & Turias, I. J. (2025) · Logic Journal of IGPL · doi:10.1093/jigpal/jzaf032 · Cited by 1
Maity, S., Sahu, B., Singh, N., et al. (2025) · ACS ES&T Engineering · doi:10.1021/acsestengg.5c00760
Girdhar, N., Coustaty, M., & Doucet, A. (2025) · International Journal on Digital Libraries · doi:10.1007/s00799-025-00437-5 · Cited by 1
Pankratov, A. S., Golovin, O. L., Grinin, V. M., et al. (2025) · Annals of the Russian academy of medical sciences · doi:10.15690/vramn18060
MACHINE LEARNING AIDED APPROACH TO ESTIMATE IMPRESSION FOR RESIDENTIAL LIGHTING IMAGES
Ishihara, K., Yumine, M., Mukai, K., et al. (2025) · doi:10.25039/x051.2025/c3z8qu
ExplainNet: A Hybrid Visual-Linguistic Model for Human-Centered Autism Diagnosis
Sefat, S. M., Adnan, M. H. B. M., & Hasan, M. M. (2025) · IEEE International Conference on Artificial Intelligence in Engineering and Technology (IICAIET) · doi:10.1109/iicaiet67254.2025.11265039
“Each activation map is then passed through a non-linear activation function, which is typically ReLU [14].”
Demonstration of Reconfigurable All-Optical Matrix-Matrix Multiplication Using Nonlinear Wave Mixing
Ko, W., Alhaddad, A., Minoofar, A., et al. (2025) · European Conference on Optical Communication · doi:10.1109/ecoc66593.2025.11263063
“Matrix-vector multiplication (MVM) and matrix-matrix multiplication (MMM) are fundamental signal-processing operations with broad applications in neural networks, communications, and high-performance computing [1-3].”
Dual-modal WGAN-VAE for Fault Detection in Non-stationary Dynamical Processes
Yang, W., & Chen, M. (2025) · CAA Symposium on Fault Detection, Supervision and Safety for Technical Processes (SAFEPROCESS) · doi:10.1109/safeprocess67117.2025.11268046
“In recent years, deep learning has provided a new direction for fault detection in non-stationary processes The multi-scale feature fusion architecture based on convolutional neural networks (CNNs) can adaptively extract the time-frequency local patterns [12].”
Remote Sensing Image Classification Using Deep Residual Networks
Kahar, M. I. A., Saleh, H. M., & Nelson, C. C. (2025) · IEEE International Conference on Artificial Intelligence in Engineering and Technology (IICAIET) · doi:10.1109/iicaiet67254.2025.11265498
“The pre-trained models used publicly available ImageNet [20] weights.”
RTAD-YOLO: a real-time agglomerate detection algorithm for corn straw in screw conveying
Guo, W., Zhang, X., & Wulantuya (2025) · Signal Image and Video Processing · doi:10.1007/s11760-025-04998-5
ChronoSelect: Robust Learning with Noisy Labels via Dynamics Temporal Memory
Wang, J., Li, Q., Zheng, P., et al. (2025) · ACM International Conference on Multimedia in Asia (MMAsia) · doi:10.1145/3743093.3770952
Xiong, X. T. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5874969
Djordjević, I. B. (2025) · Elsevier eBooks · doi:10.1016/b978-0-443-40568-6.00006-9
DBRS-Net: A Hybrid Framework for Food Image Classification
Dongmei, M., & Wang, D. (2025) · Journal of Computer Science and Frontier Technologies · doi:10.63313/jcsft.9029
Hallur, A. G., Settibhaktini, H., Chintanpalli, A., et al. (2025) · IEEE Access · doi:10.1109/access.2025.3640391
Wu, X., Zhang, X., Xiao, Z., Hu, L., Higashita, R., & Liu, J. (2025) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2025.3641192 · Cited by 2
Robust Charging Vehicle Detection in Complex Weather via Collaborative Optimization
Jiang, X., Sun, W., Chen, X., et al. (2025) · IEEE World Forum on Internet of Things (WF-IoT) · doi:10.1109/wf-iot64238.2025.11270644
“Since its inception, CNNs have received great attention in the field of computer vision, and have demonstrated unpar-alleled advantages, especially in vehicle detection tasks [9].”
GENPHIRE: Enhancing Disease Risk Prediction Using Large Language ModelPreprint
Yao, D., Liu, C., Yan, S., et al. (2025) · medRxiv · doi:10.64898/2025.12.03.25341576
Zhang, R., Chen, Z., Huo, G., Zhang, X., Luo, W., & Mu, L. (2025) · Remote Sensing · doi:10.3390/rs17243971
TorsoTrack: Fine-Grained Nonintrusive Torso Inclination Assessment Using mmwave Radar
Ding, L., Jiao, Z., Yang, S., et al. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3641891
A Unified Decision Rule for Generalized Out-of-Distribution Detection
Ma, X., Wu, J., Zou, X., & Liu, W. (2025) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2025.3642151 · Cited by 1
Parameter reduction in convolutional neural networks with kernel transposition
Osuto, D. A., Absaloms, H. O., & Mwema, W. N. (2025) · Journal of Electrical Systems and Information Technology · doi:10.1186/s43067-025-00287-w
“The use of inception modules in GoogLeNet (now also called Inceptio-v1) allowed it to have 12 × fewer parameters than the 2012’s AlexNet [3], despite being deeper and more accurate.”
InfluentialLee, H.-B., & Choi, J. (2025) · The Knee · doi:10.1016/j.knee.2025.11.016 · Cited by 1
Baum, J., Büchner, T., Volk, G. F., Joachim, & Guntinas‐Lichius, O. (2025) · Research Square · doi:10.21203/rs.3.rs-8275999/v1
A Study of Computational Vision Methods for Corrosion Detection in Industrial Assets
Marco, A. G., de Oliveira, M., Prates, R. L., Lopes, M. C., Casal, R. G., & Guimarães, C. V. R. (2025) · SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI) · doi:10.5753/sibgrapi.est.2025.38322
“Most of the pretrained encoder backbones evaluated in this study, such as ResNet152, VGG16, InceptionV4, and MobileNetV2 were originally trained on the ImageNet dataset [29], which uses 224 × 224 as the standard input size.”
A Resource Reuse Strategy for Large-Scale Matrix Operations in HLS-Based FPGA Design
Lei, Z., Liu, C.-B., Xiao, Z., et al. (2026) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2025.3625947
Progressive Hierarchical Feature Periodic Transformer for Robust UAV Tracking
Qu, H., & Wang, H. (2025) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2025.3643331
Zhao, S.-C., Chen, J., Shi, S., et al. (2025) · Biomedical Physics & Engineering Express · doi:10.1088/2057-1976/ae2b74
Engineering and causality: A centenary response to Claudius
Naser, M. Z. (2025) · TAO. · doi:10.1016/j.tao.2025.100022
Hammad, M. S., Ghoneim, V. F., Al‐Atabany, W., & Mabrouk, M. S. (2025) · Soft Computing · doi:10.1007/s00500-025-10936-x
Aphorisms for Collaborative Intelligence
Chang, E. Y. (2025) · ACM eBooks · doi:10.1145/3749421.3749441
Bias Correction and Data Synthesis through Reflective LLM Collaboration
Chang, E. Y. (2025) · ACM eBooks · doi:10.1145/3749421.3749432
Time-Domain Sound Field Estimation Using 3D-CNN for Sound Field Reproduction*
Horikoshi, K., Sato, G., Tsunokuni, I., et al. (2025) · IEEE Global Conference on Consumer Electronics (GCCE) · doi:10.1109/gcce65946.2025.11274850
“In addition, a deep learning-based pressure matching (DLPM) method has been proposed, which uses a convolutional neural network (CNN) to perform spatial interpolation of the desired sound field while deriving the driving function directly from the recorded signal [21], [22].”
Zhang, H., Jia, J., & Huang, H. (2025) · Computational Biology and Chemistry · doi:10.1016/j.compbiolchem.2025.108842
A Multichannel Attention Residual Fusion for Enhanced Radio Frequency Fingerprinting
Feng, J., & Xu, W. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3643455
Rajitha Rajeshwar, T., Lagergren, J. H., Smith, J. C., & Demerdash, O. (2025) · Biophysical Journal · doi:10.1016/j.bpj.2025.12.011
Visual saliency fixation via deeply tri-layered multi blended trans-encoder framework
Caroline, S., & Raj, Y. J. V. (2025) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2025.104676
Wickramanayaka, N. R., & Oizumi, M. (2025) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2025.12.10.693611 · Cited by 1
“DNNs have emerged as powerful tools in computer vision [16–22]; they have achieved remarkable performance across a wide range of perceptual tasks [23–27] and are increasingly regarded as effective computational proxies for the human visual perception [28–30].”
Qiao, S., & Liu, H. (2025) · Scientific Reports · doi:10.1038/s41598-025-30199-8
“Image classification gained crucial advantages through deep CNNs 24 demonstrated their potential in classification tasks which eventually translated into surveillance applications.”
InfluentialSun, J., Bu, Y., Zhang, M., et al. (2025) · The Astrophysical Journal · doi:10.3847/1538-4357/ae1692
Nguyen, Q. M., Önür, M., & Alpak, F. O. (2025) · SPE Journal · doi:10.2118/220783-pa
Alguliyev, R. M., Aliguliyev, R. M., & Sukhostat, L. V. (2025) · SN Computer Science · doi:10.1007/s42979-025-04561-6
A feature-based generalizable prediction model for both perceptual and abstract reasoning
Do, Q. H., Morin, T., Stern, C. E., & Hasselmo, M. E. (2025) · Cognitive Neuroscience · doi:10.1080/17588928.2025.2599784 · Cited by 1
Визначення масштабу та кута повороту для довгострокового відстеження об’єкта у відео
Kiiko, V. M. (2025) · Information Technologies and Systems (Інформаційні технології та системи) · doi:10.15407/intechsys.2025.05.022
End-to-End Shipping Container Code Spotting Based on Visual Sensors for Intelligent Inspection
Chen, H., Piao, X., You, S., Jiang, M., Chen, C., & Chen, P. (2025) · IEEE Sensors Journal · doi:10.1109/jsen.2025.3641379
“The backbone is pretrained on ImageNet [54] for weight initialization.”
Image Enhancement Using CLAHE and CNN for Underwater Lighting Effects
Shahareyar, S., Kumar, A., Agrawal, P., et al. (2025) · International Conference on Computing Communication Control and automation · doi:10.1109/iccubea65967.2025.11284088
Ghadekar, P. P., Jain, R., Jasuja, I., et al. (2025) · International Conference on Computing Communication Control and automation · doi:10.1109/iccubea65967.2025.11284059
Modular Enhancement of Oneformer via Cbam-Augmented Fastervit for Semantic Segmentation
Mhatre, M., Zhang, L., & Rothnie, S. (2025) · International Conference on Machine Learning and Cybernetics · doi:10.1109/icmlc66258.2025.11280087
“FasterViT yields state-of-the-art throughput (images per second) for a given accuracy on ImageNet [9], COCO [10], and ADE20K [17].”
Wang, Y. C., Chen, J. J., Wang, F., Gao, Z. Y., Ma, L., Yao, B., Ou, X. L., He, Y. X., Lu, D., & Deng, T. (2025) · Optics & Laser Technology · doi:10.1016/j.optlastec.2025.114476
Optimize Winograd Convolution for a Novel MIMD Many-core Architecture PEZY-SC3s
Zhou, Y., Wang, Q., Wang, L., et al. (2025) · International Conference on Parallel Architectures and Compilation Techniques · doi:10.1109/pact65351.2025.00045
Li, M., Hei, W., Tan, X., Sun, Z., & Qi, P. (2025) · International Conference on Control, Robotics and Cybernetics (CRC) · doi:10.1109/crc67523.2025.11288270
“Pollini et al. installed artificial features (e.g., light-emitting diodes (LEDs) [2-5], painted markers [6-8]) at target positions to assist in position measurement and pose estimation.”
Warehouse Management Models Using Artificial Intelligence: A Review
Kaur, N., Kaur, S., Kaur, G., & Ali, A. (2025) · IEEE International Conference on Advances in Computing Research on Science Engineering and Technology (ACROSET) · doi:10.1109/acroset66531.2025.11281155
Comprehensive Models and Techniques for Processing Image, Text, Time Series, and Graph Data
Kumar, V. S., Nidhya, M. S., Nath, I., Ramineni, K., Sherin, K. M., & Maram, B. (2025) · International Conference on Innovative Data Communication Technologies and Application (ICIDCA) · doi:10.1109/icidca66325.2025.11280572
“It works this way because of LSTM and Transformer models such as BERT and GPT [7],[2].”
A Noval Method for Detecting Dental Caries using a Swin Transformer Framework Based on ResML
Kapoor, S., & Maheshwary, P. (2025) · doi:10.1109/acroset66531.2025.11281251
“These modules work couple to streamline highlight extraction and upgrade model execution with regards to dental caries examination[23].”
Enabling Efficient Synergistic Multi-view Inference Across Heterogeneous Edge Devices
Dong, F., Chen, R., Fu, S., Cheng, W., Zhou, R., & Zhang, X. (2025) · ACM Transactions on Sensor Networks · doi:10.1145/3785358
“…has spurred the development and deployment of DNN-powered computer vision applications across various domains, including image recognition [18], defect detection in industrial settings [37], and video analysis for security monitoring [43], which demand high-accuracy and low-latency…”
Deep survival analysis from adult and pediatric electrocardiograms: a multi-center benchmark study
Lukyanenko, P., Mayourian, J., Liu, M., Triedman, J. K., Ghelani, S. J., & Cava, W. L. (2025) · BioData Mining · doi:10.1186/s13040-025-00510-4 · Cited by 1
Structure-Aware Alignment for Day-Night Cross-Domain Vehicle Re-Identification
Zhuang, J., Sa, B., Zheng, J., et al. (2025) · IEEE Signal Processing Letters · doi:10.1109/lsp.2025.3645215
Multi-Modal Cross-Attention-Based Multi-Label Weather and Severity Level Classification
Ju, H., Nalçakan, Y., Park, I., Jin, Y., Yeo, S. D., & Kim, S. (2025) · IEEE Access · doi:10.1109/access.2025.3645363 · Cited by 1
Saha, S., Misra, T., Jha, R. R., Chakraborty, D., Deb, D., Sharma, J., Sharma, A., Singh, B., Mridha, N., Ray, M., et al. (2025) · IEEE Access · doi:10.1109/access.2025.3644179
A Strategy for Fusing Semantic Information in Neural Machine Translation of Classical Chinese
Su, Y., Cao, H., & Zhou, Y. (2025) · IEEE Access · doi:10.1109/access.2025.3644925
Spurious Local Minima Provably Exist for Deep CNNs: Theory and Application
Liu, B., Fu, K., Yuan, T., & Geng, S. (2025) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2025.3640733
LFODet:Lightweight Few-Shot Object Detection with Meta-Learningin Remote Sensing ImagesPreprint
Fang, X., Hou, Y. F., Yang, X., Wu, H., & Xiong, H. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5936819
Higher-Order LaSDI: Reduced Order Modeling with Multiple Time DerivativesPreprint
Stephany, R., Choi, Y., & Anderson, W. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5936721
Sun, Y., Si, X., He, R., et al. (2025) · npj Digital Medicine · doi:10.1038/s41746-025-02154-4
“Even more critically, most models utilize one-dimensional EEG signals as input, lacking the robust and versatile pre-trained models that are prevalent in the field of computer vision, such as ResNet, ViT, Swin Transformer trained on ImageNet[10, 11].”
Zheng, M., Lin, Y., & Li, B. (2025) · International Conference on Computer Vision and Data Mining (ICCVDM) · doi:10.1109/iccvdm66874.2025.11290463
Application of Co-located Fusion Deep Neural Networks in Multi-source Image Data
Shen, Y., Zheng, T., & Yang, M. (2025) · 2025 3rd International Conference on Algorithm, Image Processing and Machine Vision (AIPMV) · doi:10.1109/aipmv67185.2025.11290091
“To enhance performance in this task and beyond, numerous strategies have been explored for improving convolutional neural networks (CNNs) and Transformer-based architectures, including novel network designs, task-specific loss functions and advanced optimization techniques [8-10] .”
CBAM-Enhanced Tri-Scale Synergistic Fusion for Tomato Disease Identification
Sun, W.-X., Zhang, W.-B., Luo, S., et al. (2025) · 2025 5th International Conference on Artificial Intelligence, Automation and High Performance Computing (AIAHPC) · doi:10.1109/aiahpc66801.2025.11290232
“Early research, such as AlexNet [2] , validated the feasibility of CNN on the Plant Village dataset.”
Enhancing Neural Network Performance with a Pre-Trained Low-Level Feature Detection Unit
Gudkov, P., & Podmarkova, E. (2025) · doi:10.1109/apeie66761.2025.11289270
“A decisive breakthrough in visual data analysis was achieved with the widespread adoption of convolutional neural networks [1].”
3D multi-modal fusion networks based on association mapping for quality assurance of treatment plans
Hu, T., Liu, S., Lu, T., et al. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.130785
Im, J., Lee, S., Oh, Y.-J., et al. (2025) · Nuclear Engineering and Technology · doi:10.1016/j.net.2025.104089
Crop pest classification using micro-doppler signatures via C-band radar in an anechoic chamber
Salas, A. L. A., Hakvoort, R. B. J., Yamamoto, P. T., & Hernandez-Figueroa, H. E. (2025) · Smart Agricultural Technology · doi:10.1016/j.atech.2025.101736
A Study of Automated Image Classification Based on the EasyDL Platform
Hong, H. (2025) · International Conference on Computer Information Science and Artificial Intelligence (CISAI) · doi:10.1145/3773365.3773465
“Among its foundational research areas, image classification has emerged as a key driver for promoting intelligent transformation across various industries [1].”
Qin, Y., Li, X., Sun, H., et al. (2025) · Scientific Reports · doi:10.1038/s41598-025-32579-6
“These four commonly used CNNs were pre-trained on the large-scale, well-annotated ImageNet database 21 .”
Huang, D.-H., Duan, X.-F., & Ding, Y. (2026) · Future Generation Computer Systems · doi:10.1016/j.future.2026.108635 · Cited by 1
Rogannagari, R. K., & Islam, K. A. (2025) · Remote Sensing · doi:10.3390/rs18010008
CFDM: Cascaded fractal diffusion model for visible-to-infrared image synthesis
Xiang, Y., Zeng, X., Liao, T., & Liu, X. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.132472
AI Controlled Automated Hydroponic Farming System
Preetham, N., Hithesh, M. P., R, P. K., et al. (2025) · doi:10.1109/csitss67709.2025.11294257
MAC Protocol Recognition using Transformer-based Neural Network
Lin, Y., Zhuang, J., Lan, J., & Peng, S. (2025) · Information Communication Technologies Conference (ICTC) · doi:10.1109/ictc67375.2025.11292346
“To highlight the superiority of our method, we selected baseline models for comparison, using single networks of CNN [14], RNN [15], or LSTM [16] respectively.”
YOLO-3DCA: Lightweight Road Defect Detection with Multi-Directional Stereo Convolution
Wang, X., Mao, Z., & Wang, Y. F. (2025) · doi:10.1109/iccs67844.2025.11292148
A multi-scale cross attention stage darknet model for remaining useful life prediction of bearings
Zhou, Y., Sun, Y., Lu, Y., et al. (2025) · Engineering Research Express · doi:10.1088/2631-8695/ae2f8e
Ge, M., & Wang, C. (2025) · Journal of Sensors · doi:10.1155/js/7221555
Gebregiorgis, A., Yousefzadeh, A., Eissa, S., Siddiqi, M. A., Frenkel, C., Zenke, F., Bohté, S. M., Mahmoud, A. N., Das, A. K., Hamdioui, S., et al. (2025) · Microprocessors and Microsystems · doi:10.1016/j.micpro.2025.105240 · Cited by 6
Using deep learning to distinguish cryptic traits in animal colour patterns
Ortenzi, L., Costa, C., Reinke, B. A., & Angelini, C. (2025) · Journal of Zoology · doi:10.1111/jzo.70096 · Cited by 1
REM-Net: MEMS-Based Synchronized PCG-ECG Analysis Framework for High-Precision CAD Diagnosis
Chen, F., Wang, R., Shi, P., et al. (2025) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2025.3588969
Additional file 1 of Learning protein-ligand binding affinity with atomic environment vectors
Meli, R., Anighoro, A., Bodkin, M. J., Morris, G. M., & Biggin, P. C. (2021) · Figshare · doi:10.6084/m9.figshare.15178929
Additional file 2 of Deep learning model for classifying endometrial lesions
Zhang, Y., Wang, Z., Zhang, J., Wang, C., Wang, Y., Chen, H., Shan, L., Huo, J., Gu, J., & Ma, X. (2021) · Figshare · doi:10.6084/m9.figshare.13532522
Wang, C., Caragea, D., Kodadinne Narayana, N., Hein, N. T., Bheemanahalli, R., Somayanda, I. M., & Jagadish, S. V. K. (2022) · Figshare · doi:10.6084/m9.figshare.18866688
Ahsan, M. U., Liu, Q., Fang, L., & Wang, K. (2021) · Figshare · doi:10.6084/m9.figshare.16575777
Ali, H., Mohsen, F., & Shah, Z. (2024) · Figshare · doi:10.6084/m9.figshare.26617579
Wang, C., Caragea, D., Kodadinne Narayana, N., Hein, N. T., Bheemanahalli, R., Somayanda, I. M., & Jagadish, S. V. K. (2022) · Figshare · doi:10.6084/m9.figshare.18866682
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
