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 108,301–108,400 of 108,435
Zhu, G., Li, Z., Bao, R., & Chen, W. (2026) · International Journal of Mechanical Sciences · doi:10.1016/j.ijmecsci.2026.112126
An Adversarial Example Generation Method Based on Backward Dynamic Slope Gating
Du, X., Jiang, J., Pu, C., et al. (2026) · Concurrency and Computation Practice and Experience · doi:10.1002/cpe.70933
Intelligent Recognition of Kick Fluid Types Based on Time-Series Features: Method and Case
Feng, R., Zhang, R., Zang, Y., Zhou, H., Zhang, Z., Yang, Y., & Fu, S. (2026) · SPE Journal · doi:10.2118/236610-pa
Artificial Intelligence in Orthodontics: Part 1—Basic Concepts
Sohrabniya, F., Naveed, K., Mohammad‐Rahimi, H., Woolley, J., Haghighat, S., Stoustrup, P. B., & Pauwels, R. (2026) · Orthodontics and Craniofacial Research · doi:10.1111/ocr.70179
A Dual-Path Attention and Multi-Scale Fusion Network for Crop Disease and Pest Identification
Zhang, H., Song, F.-G., Yuan, Y.-Q., et al. (2026) · Entropy · doi:10.3390/e28091032
“Early work applied models like AlexNet [6], VGGNet [7], and ResNet [8] to the PlantVillage dataset and reported over 95% accuracy [9].”
Automatic construction productivity monitoring based on object detection using pose-augmented images
Muhtarom, A., Chen, H.-M., Chiang, C.-Y., et al. (2026) · KSCE Journal of Civil Engineering · doi:10.1016/j.kscej.2026.100752
Deep Meta-Learner Stacking with Explainable AI for Vision-Based Plastic Waste Classification
Shareena, T. V., & Padmavathi, S. (2026) · SN Computer Science · doi:10.1007/s42979-026-05342-5
“BasicCNN serves as foundational model [ 22], whereas ResNet50V2 and VGG16 provide deeper networks with enhanced accuracy via skip connections [23] and sophisticated feature extraction [ 24], respec - tively.”
Advanced Lung Cancer Detection Leveraging 3D CNN Transfer Learning and Ensemble Methods
Althaph, B., Gadde, S. S., Govindarajana, S., et al. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-28924-7_12
Han, S., Lin, Y., Miao, N., Shu, Y., Li, Z., Zhu, L., Zhou, J., & Sun, Z. (2026) · Applied Energy · doi:10.1016/j.apenergy.2026.128925
Fang, K., Zhang, Y., Han, Y., et al. (2026) · Journal of Physics Conference Series · doi:10.1088/1742-6596/3310/1/012026
Intelligent prediction of tool wear in Inconel 718 laser-assisted micro-milling based on CNN-BiLSTM
Lü, X. (2026) · The International Journal of Advanced Manufacturing Technology · doi:10.1007/s00170-026-19178-z
Multiscale Stepwise Learning Network for Seismic Impedance Inversion
Zhang, Y., Cao, H., Yang, Z., et al. (2026) · Applied Sciences · doi:10.3390/app16189358
Bayraktar, Y. E., Karaağaç, E., Şenyurt, A. Y., et al. (2026) · Journal of Imaging Informatics in Medicine · doi:10.1007/s10278-026-02314-2
Gao, X., Wang, W., Xie, J., et al. (2026) · Journal of Magnesium and Alloys · doi:10.1016/j.jma.2026.102330
Elastic Deep Neural Network for Adaptive Feature Extraction in Remote Sensing Image Retrieval
Kasetty, S. B., Rajakumar, K., Margret, I. N., Manikandan, S., & Mohammad, A. (2026) · IEEE Access · doi:10.1109/access.2026.3734223
A YOLOv8-Based Model for Small-Target Road Defect Detection
Liu, D., Long, T., Hu, Z., Yang, P., & Wang, Y. (2026) · Applied Sciences · doi:10.3390/app16199409
Wang, F., Jiang, J., Zhang, K., et al. (2026) · Materials Testing · doi:10.1515/mt-2026-0236
Facial Expression Recognition Using Capped Adaptive Ensemble of Deep Learning Models
Sharma, M., Eapen, N. A., & Khanna, G. (2026) · International Conference on Computing, Intelligence, and Application (CIACON) · doi:10.1109/ciacon70148.2026.11689576
“The success of CNN architectures, including AlexNet [8] and VGG [9], has illustrated the efficiency of deep and hierarchical feature extraction.”
Semi-Supervised Fast Food Classification Using Vision Transformers and FixMatch
Bandyopadhyay, S., Koner, S., Ghorui, S., Roy, N. D., Mondal, R. K., & Patra, J. (2026) · International Conference on Computing, Intelligence, and Application (CIACON) · doi:10.1109/ciacon70148.2026.11689583
“CNN families such as VGG, Inception, ResNet, and EfficientNet established strong supervised baselines and shaped early food-recognition pipelines [2], [3], [11], [12].”
A Lightweight Convolutional Neural Network for Crop Leaf Disease Recognition
Hu, J.-J., Lv, L.-P., Yang, H.-K., et al. (2026) · 2026 International Conference on Computational Intelligence and Machine Learning (CIML) · doi:10.1109/ciml69155.2026.11692718
“SqueezeNet [14] achieves accuracy comparable to AlexNet [15] on the ImageNet dataset while using 50 times fewer parameters than AlexNet, and through model compression techniques, can reduce the SqueezeNet model file to less than 0.5MB, 510 times smaller than AlexNet.”
Didi, Y., Walha, A., & Wali, A. (2026) · Multimedia Tools and Applications · doi:10.1007/s11042-026-21915-1
Li, H., Li, X., Liu, J., Luo, S., & Zhang, Y. (2026) · Natural hazards and earth system sciences · doi:10.5194/nhess-26-4529-2026
“Furthermore, to validate the efficacy of the purpose-built lightweight design in MSCI-Net for small-sample scenarios, the proposed structure was substituted with deeper network architectures, including Alex-Net (Krizhevsky et al., 2017), Visual Geometry Group (VGG)-16, and VGG-19, to compare the classification performan…”
Lightweighted and Structural Simplified Network for the Object Detection with Re-Parameterization
Zhou, Y., Zou, X., Xu, S., et al. (2026) · IEEE International Conference on Cyber Technology in Automation, Control, and Intelligent Systems · doi:10.1109/cyber71431.2026.11695485
Belli, M., & Schmorell, D. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7513376
Soto, I. L., Concha-Sánchez, Y., & Raya, A. (2026) · Modeling Earth Systems and Environment · doi:10.1007/s40808-026-02904-7
“AlexNet (Krizhevsky et al. 2012 ) is included as the baseline architecture given its predominant use in existing TSS-related CNN research (4 of 5 prior studies), enabling direct comparison with established methodologies.”
Image Demoiréing With Image Classification Priors
Song, M., & Kim, H. (2026) · IEEE Access · doi:10.1109/access.2026.3734076
Deep Joint Source-Channel Coding Over Multi-User Access Channels With Random Activities
Ma, K., Zhong, Z., Shao, S., et al. (2026) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2026.3733405
A Decomposition-Driven Deep Learning Model for Intelligent Irrigation Decision-Making
Kumar, R., & Garg, A. (2026) · International Research Journal of Multidisciplinary Technovation · doi:10.54392/irjmt26512
“This reduction lowers computational complexity and helps control overfitting [51].”
Hybrid Fractal Zeiler and Fergus Network for Text Classification Using Large Language Models
Kumar, S. N. P., Patil, V. V., & Jondhle, S. (2026) · Web Intelligence · doi:10.1177/24056456261462617
Multi-scale time series decomposition for water demand forecasting based on LSTM_Mixer
Hou, B., Wang, D., Li, Y., Jia, R., & Wu, S. (2026) · Journal of Water Process Engineering · doi:10.1016/j.jwpe.2026.110945
AI in actuarial science – a review of recent advances – part 1
Richman, R. (2020) · Annals of Actuarial Science · doi:10.1017/s1748499520000238 · Cited by 8
Kaur, M., Singh, D., Gaur, P., et al. (2026) · IEEE Access · doi:10.1109/access.2026.3733409
Liang, X., Wang, Q., Xie, K., et al. (2026) · International Journal of Molecular Sciences · doi:10.3390/ijms27198519
Zhu, C., Zhang, X., Walt, A. V. D., Taylor, B. V., Monif, M., Kalincik, T., Lechner-Scott, J., Buzzard, K. A., Kilpatrick, T. J., Barnett, M. H., et al. (2026) · PLOS Digital Health · doi:10.1371/journal.pdig.0001722
“CNN has proven highly effective in recognising patterns within image data and handling complex image recognition tasks [33,34].”
Dynamic Routing-Based Capsule Networks for Handwritten Digit Classification
Bhatnagar, P., Gupta, V., Sodhi, M. S., et al. (2026) · International Conference on Intelligent Systems, Metaheuristics & Swarm Intelligence (ISMSI) · doi:10.1145/3820820.3820838
“Krizhevsky et al. [2] make convolutional architectures go even further by showing how deep CNNs is not inefficient for big image tasks.”
Long-term dynamic root monitoring based on classification fusion and attention mechanism
Fu, Y., Zhang, P., Zhao, Y., et al. (2026) · Biosystems Engineering · doi:10.1016/j.biosystemseng.2026.104602
Artificial intelligence methods for mechatronics: Enhancing functionality and efficiency
May, L., & Mellal, M. A. (2026) · Elsevier eBooks · doi:10.1016/b978-0-443-27580-7.00008-1
Firoozi, T., Abroampah, D., Mohammadi, H., & Gierl, M. J. (2026) · International Journal of Testing · doi:10.1080/15305058.2026.2730013
Li, Y., Jia, K., & Chen, Q. (2026) · Neurocomputing · doi:10.1016/j.neucom.2026.135250
Contour-aware diffusion model for restoring atmospheric turbulence-degraded facial images
Sun, S.-Y., Meng, P.-C., Yin, W.-S., et al. (2026) · Optics & Laser Technology · doi:10.1016/j.optlastec.2026.116513
Pandey, V., Pandey, M., & Pathak, Y. (2026) · Discover Computing · doi:10.1007/s10791-026-10613-z
“Concurrently, Convolutional Neural Networks (CNNs), originally developed for image processing, have been successfully adapted for time series analysis through their ability to detect local patterns and hierarchical features through learnable filters [8].”
NeuroAlign: A Unified Plug-and-Play Enhancer for Visual and Linguistic Brain Decoding
Li, J., Huang, Y., Xue, L., Zhang, Y., Liu, Y., Zheng, W., Yu, L., Yao, Z., & Fu, Y. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-38239-9_39
Artificial intelligence and radiomics in lung cancer: from imaging to clinical care
Naidu, J. S., & Baskaradoss, V. K. (2026) · doi:10.20935/medimaging8536
Kasambya, M. K., Mystère, K. K., Mpia, H. N., et al. (2026) · Procedia Computer Science · doi:10.1016/j.procs.2026.08.437
Wan, F., Shen, L., Qu, M., Zhong, H., Li, M., & Jiang, Z. (2026) · Environmental Science & Technology · doi:10.1021/acs.est.6c04494
Kumar, B., Mansour, S., Alyounis, E., et al. (2026) · Microchemical Journal · doi:10.1016/j.microc.2026.119779
孙有学, Ding, S., Wang, C., & Liu, D. (2026) · ACS Earth and Space Chemistry · doi:10.1021/acsearthspacechem.6c00213
WESE: Enabling Sound Claim Verification with Ownership Transfer for Deep Neural Networks
Liu, Y., Jiang, P., Tang, S., et al. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-38695-3_4
Ticona, W., Infantes, E., Ccompi, W., & Figueiredo, K. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-38800-1_9
Higher-order spatial mode detection leveraging deep learning on random optical patterns
Mutupuri, S. S., Ansari, M., Anamalamudi, S., et al. (2026) · Applied physics B · doi:10.1007/s00340-026-08717-x
“…provides a more stable optimisation path than random weight initialisation, resulting in faster convergence and improved generalisation [33–37 We have used a pretrained VGG16 model along with the fine tuning for extracting the TC by using the captured speckle images and now onwards…”
InfluentialDeep Learning-Based Microscopic Analysis of Medical Plant Images
Hlubuček, R., Štekerová, K., Husáková, M., et al. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-38803-2_2
From Artificial Intelligence to Algoraceutics: An Evolutionary Overview
Rotino, G. (2026) · Law for professionals · doi:10.1007/978-3-032-38537-6_2
Behzad, M., Aljunaid, R., Aburaed, N., et al. (2026) · Information Fusion · doi:10.1016/j.inffus.2026.104814
AI-Driven Bridge Crack Detection: A Review of Deep Learning Applications for Durability Assessment
Li, F., & Rana, M. S. (2026) · Journal of Nondestructive Evaluation · doi:10.1007/s10921-026-01437-4
“4, which shows the various output forms for classification, segmentation, and bounding box detection [63].”
Vrind, T., Kumar, C., & Das, D. (2026) · IEEE International Conference on Electronics, Computing and Communication Technologies (CONECCT) · doi:10.1109/conecct68978.2026.11700638
“The compute and memory requirements of the LLama2-7B model is different from image and object detection models like AlexNet, ResNet [18] or Yolov8m, which show variations across the layers.”
Kim, Y., Kim, C., Yun, C., & Joo, G. (2026) · Ecological Solutions and Evidence · doi:10.1002/2688-8319.70322 · Cited by 1
A Deep Learning Galerkin Method for the Second-Order Linear Elliptic Equations
Li, J., Zhang, W., & Yue, J. (2021) · International Journal of Numerical Analysis and Modeling · doi:10.4208/ijnam.v18.n4.p427
Mut, B., Kılıç, İ., & Yaman, O. (2026) · International Conference on Advanced Computer Information Technologies (ACIT) · doi:10.1109/acit69831.2026.11700169
“In particular, convolutional neural networks (CNNs) have made significant contributions to developments in the field of image processing [8].”
When code does not run: reproducibility challenges in materials machine learning benchmarks
Lyu, B., Bonini, J., Zhang, M., et al. (2026) · AI Agent · doi:10.20517/aiagent.2026.31
Abdelsalam, M. S., & Sayed, G. I. (2026) · Intelligent Methods, Systems, and Applications (IMSA) · doi:10.1109/imsa70415.2026.11700341
“The first deep convolutional neural network (CNN) was constructed by Krizhevsky et al. [12] in 2012 to classify images into different categories.”
Piromalis, D. D., Alexandris, C., & Papageorgas, P. G. (2026) · Sensors · doi:10.3390/s26196127
Generative diffusion models for geophysical classification problems
Gong, X., Chen, Y., Breton, C., Siervo, D., Yang, L., & Savvaidis, A. (2026) · Geophysical Journal International · doi:10.1093/gji/ggag383
Generative Neural Y-Model for Versatile Concept Drift Detection
Dolgikh, S. (2026) · International Conference on Advanced Computer Information Technologies (ACIT) · doi:10.1109/acit69831.2026.11700095
“Deep learning has achieved remarkable success in modeling complex, high-dimensional data across domains, from computer vision [1] to natural language processing [2].”
Towards Real-time Object Detection for Safety Analysis in an ML-Enabled System Simulation
Adigun, J. G., Aschenbrenner, P., & Felderer, M. (2024) · WiPiEC Journal - Works in Progress in Embedded Computing Journal · doi:10.64552/wipiec.v10i2.69
Deep Learning-Based Classification of Military Aircraft Types from Satellite Imagery
Varlik, F., & Özdemir, C. (2026) · Turkish Journal of Science and Technology · doi:10.55525/tjst.1928640
Sakthivel, V., & Suresh Joseph, K. (2026) · Journal of Electronics and Informatics · doi:10.36548/jei.2026.4.002
“Deep Learning techniques have been found very efficient in learning discriminative facial representations automatically, especially Convolutional Neural Networks (CNN) [5], [6], [10].”
Low-Latency Foundation Models in Multi-Cloud Environments Using Neural Network
Bhasin, S., Venugopal, S., Khanna, D., & Sanikal, V. (2026) · Technology and Innovation Conference (TIC) · doi:10.1109/tic68483.2026.11702837
“…improvements in large language models [16], [17], sequence-to-sequence translation architectures [18], deep convolutional residual networks [19], [20], advanced reinforcement learning algorithms [21], generative adversarial frameworks [22], and general deep learning methodologies [23], [24]…”
Measurement-Driven Structured Pruning for Energy-Efficient Deep Neural Networks on Edge Devices
Russell, C., & Godinez, J. C. (2026) · IEEE Jornadas Costarricenses de Investigación en Computación e Informática (JoCICI) · doi:10.1109/jocici69279.2026.11701725
“• AlexNet [16] — adapted for a wood-defect dataset [17].”
A Deep Learning Framework for Real-Time Cyber Anomaly Detection in Critical Infrastructure Systems
Mohan, S., Kumari, V. S., Pillai, N. M., Paul, T. S., Abinaya, S. M., & Shree Smeka, J. (2026) · Technology and Innovation Conference (TIC) · doi:10.1109/tic68483.2026.11701780
“CNN architectures have been widely adopted for pattern recognition tasks due to their ability to automatically extract hierarchical features from high-dimensional data [24].”
Kummarikunta, S., Raju, P. R., & Anandarao, A. (2026) · International Journal of Emerging Research in Engineering Science and Management · doi:10.58482/ijeresm.v5i3.10
Jin, W., Jin, W., Chen, X., et al. (2026) · Frontiers in Genome Editing · doi:10.3389/fgeed.2026.1954329
Be, M. C., Yang, B., Liu, S., Han, Y., Lei, Y., Zhi, X., Xiong, S., Jiao, Y., Ma, Y., Shang, S., et al. (2026) · Remote Sensing Applications Society and Environment · doi:10.1016/j.rsase.2026.102295
Representation-similarity network stitching for efficient parameter reduction in multi-exit networks
Zhang, L., Li, J., & Guo, Y. (2026) · Applied Soft Computing · doi:10.1016/j.asoc.2026.116538
Su, K.-D. (2026) · Interactive Learning Environments · doi:10.1080/10494820.2026.2735911
Chen, C., Wei, W., & Zeng, P. (2026) · Discover Computing · doi:10.1007/s10791-026-10635-7
Multi-scale hybrid neural network method for impact load localization
He, W., 耿继超, Xie, J., et al. (2026) · Aerospace Science and Technology · doi:10.1016/j.ast.2026.113937
Ganesan, D., Balasubramanie, P., Subramanian, J. A., et al. (2026) · doi:10.1109/iccubea69821.2026.11702075
“AlexNet was the first Deep Convolution Neural Network designed with 60000 million parameters with a 15.3% Error Rate [26].”
InfluentialPeluso, G., Conversano, F., Bellone, M., Lombardi, F. A., Pisani, P., Epicoco, I., Cafaro, M., & Casciaro, S. (2026) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2026.109655
Polat, O., Söğüt, E., & Nebi, Z. Ş. (2026) · Türk doğa ve fen dergisi :/Türk doğa ve fen dergisi · doi:10.46810/tdfd.1995088
Tiwari, A. K., & Bhandari, A. K. (2026) · EngMedicine · doi:10.1016/j.engmed.2026.100166
AI and ML Use in Modern Electronic Devices
Thorat, P. P., & Agrawal, R. (2026) · Springer eBooks · doi:10.1007/978-981-96-8867-8_51-1
Zhang, L., Yu, H., Zhou, C., et al. (2026) · doi:10.2196/preprints.113317
Patil, A., deshmukh, T., Sukre, G., et al. (2026) · doi:10.1109/ignite69592.2026.11706065
“Convolutional Neural Networks demonstrated superior performance in visual recognition and defect detection by automatically learning hierarchical features from images [7].”
From Pixels to Discovery: Microscopy Image Analysis in the Age of Artificial Intelligence
Uhlmann, V., Jug, F., & Kreshuk, A. (2026) · Annual Review of Cell and Developmental Biology · doi:10.1146/annurev-cellbio-111524-111428
A review on speech emotion recognition: a survey, recent advances, challenges
Turakne, S. S., More, V. A., Panchbhai, S., & Warule, P. (2026) · International Journal of Speech Technology · doi:10.1007/s10772-026-10292-7
“Various DL approaches, includ - ing deep neural networks (Hinton & Salakhutdinov, 2006), deep convolutional neural networks (CNN) (Krizhevsky et al., 2017 ), and long short-term memory (LSTM)-based recurrent neural networks (RNN), have been employed to address the complex feature learning…”
A GLOBAL-LOCAL FEATURE LEARNING FOR RETINAL VESSEL SEsGMENTATION USING AN IMPROVED U-NET
Akhtar, N., Bhushan, P., Amit, M., et al. (2026) · JOURNAL OF MECHANICS OF CONTINUA AND MATHEMATICAL SCIENCES · doi:10.26782/jmcms.2026.09.00006
Luo, X., Yang, C., & Xiong, S. (2026) · Electronics Letters · doi:10.1049/ell2.70722
Cross-Attention Fusion Based Multimodal Vital Signal Anomaly Detection Using Deep Learning
Nair, A. M., Meenatchi, K. V., Thomas, A. R., Thajudheen, A., Sajith, D. P., & Gokul, P. (2026) · International Conference on Innovations in Mechanical, Robotics, Computing and Biomedical Engineering (ICIMRBE) · doi:10.1109/icimrbe70745.2026.11710044
“The temporal convolutional layers process the activity signals [10], [14] and identify motion patterns over time windows.”
Heikal, F. N., Hamdy, O., Faid, A. H., & Ismail, T. (2026) · International Conference on Transparent Optical Networks · doi:10.1109/icton71309.2026.11705350
Artificial Intelligence in Environmental Monitoring, Pollution Control, and Low-Carbon Management
Tan, J., Cai, H., Liu, Z., Yu, F., Lao, G., Liu, Y., Yang, Y., Xie, Z., Jiang, H., & Han, S. (2026) · Clean Technologies · doi:10.3390/cleantechnol8050160
Superpixels as an Alternative to Patches in Vision Transformers for Segmentation
Santos, D. B. S., Costa, N. J. C., Ferro, R. J. C., & Santos, A. M. S. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-39904-5_36
Vmamba-DETR: An Object Detection Network Based on Vision Transformer and Visual State Space Model
Ni, Y., Wang, Y.-L., Fei, M., & Du, D. (2026) · Asian Control Conference (ASCC) · doi:10.1109/ascc70886.2026.11702455
Boufares, O., Affi, S., Miraoui, I., et al. (2026) · Sci · doi:10.3390/sci8100277
Feisa, T. T., Kibrete, F., Tadesse, Y. G., Seid, A. M., Enyew, S. Y., Enyew, G. G., Tariku, M. L., & Mulat, Z. A. (2026) · Engineering Reports · doi:10.1002/eng2.71097
Multi-Modal Bearing Fault Diagnosis Based on Multiscale Feature Enhancement and Adaptive Fusion
Zhu, W., Du, Z., Liu, T., Huang, J., Jin, F., & Zhang, C. (2026) · Machines · doi:10.3390/machines14101143
Hadri, H., Fail, A., & Mohamed, S. (2026) · International Journal of Biomedical Imaging · doi:10.1155/ijbi/4617573
“The emergence of convolutional neural networks (CNNs) [19, 20, 52], in image segmentation tasks has revolutionized various fields, including medical imaging.”
Gunti, U., & Veerappa, B. N. (2026) · Engineering Technology & Applied Science Research · doi:10.48084/etasr.20030
“Existing studies have also explored multimodal fusion frameworks to improve facial emotion recognition performance [8].”
Improving Image Classification Performance with Modern Data Augmentation and Vision Transformer
Bouidi, A., & Oughdir, L. (2026) · Engineering Technology & Applied Science Research · doi:10.48084/etasr.20583
“Deep learning architectures refers to the way the artificial neurons are structured and organized, e.g., AlexNet [5], VGGNet [6], GoogleNet [7] and ResNet [8].”
CNN-Based Classification of Feline Facial Behavioral Signals Using Augmented Datasets
Veeresha, R. K., Hegde, D. A., Salian, B. S., Usman, D. D., & Karegoudra, S. (2026) · Engineering Technology & Applied Science Research · doi:10.48084/etasr.19663
“The scalability of deep learning was demonstrated in [18], whereas authors in [19] highlighted the importance of network depth along with the use of small filters.”
InfluentialColumn-streaming optical convolution with programmable MZIs processor
Wan, Y., Cheng, Y., Yu, X., Han, X., Yi, S., Chu, Y., & Xie, P. (2026) · PhotoniX Synergy · doi:10.1007/s44519-026-00016-4
“Among these operations, convolution remains one of the most representative and important forms [7, 8].”
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
