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
2 of 14 cited sources checked · 2 supported · 0 flagged
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)
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passes- 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)
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passes- 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
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesThe 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
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesThe 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
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesA 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
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesA 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
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesThe 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
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesA 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
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesA 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
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passes
- 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
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt 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
Strength:plain· not yet calibratedCausal:correlational· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✗ Based: failsProbably 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
Load-bearingStrength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt 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
Strength:plain· not yet calibratedCausal:conditional· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably 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
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesIt 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
Load-bearingStrength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesProbably 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
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesIt 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
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably 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
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt 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
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt 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
Strength:plain· not yet calibratedSingle caseTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably 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
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably 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
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably 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
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesThe 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
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesIt 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
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✗ Based: failsProbably 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
Strength:boosted· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesIt 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
Load-bearingStrength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt 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
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesThe 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
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably 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
Strength:plain· not yet calibratedSingle caseTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably 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
Strength:hedged· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably 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
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✗ Based: failsProbably 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).
Load-bearingStrength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt 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
Tests✓ Asserted: passes✗ Checkable: fails✓ Load-bearing: passes✓ Based: passesProbably 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
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt 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
Tests✓ Asserted: passes✗ Checkable: fails✓ Load-bearing: passes✗ Based: failsProbably 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
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✗ Based: failsProbably 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
Load-bearingStrength:boosted· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✗ Based: failsProbably 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
Load-bearingStrength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✗ Based: failsProbably 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
Load-bearingStrength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesProbably 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
Load-bearingStrength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt 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
Tests✓ Asserted: passes✗ Checkable: fails✓ Load-bearing: passes✗ Based: failsProbably 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
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✗ Based: failsProbably 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
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesProbably 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
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✗ Based: failsProbably 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
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesProbably 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
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably 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
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesIt 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
Load-bearingStrength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt 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
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesProbably 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
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesProbably 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
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesIt 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.
Third convolutional layer exceeds the stated 1% parameter limit
MinorThe third layer alone has 384 × 3 × 3 × 256 = 884,736 kernel weights. That is about 1.47% of the network's stated 60 million parameters, contradicting the claim that every convolutional layer contains no more than 1%.
“we found that removing any convolutional layer (each of which contains no more than 1% of the model's parameters) resulted in inferior performance.”
“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
Flagged first, then by citations
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 107,901–108,000 of 108,434
Yu, X., Li, Y., & Lu, Y. (2026) · Cluster Computing · doi:10.1007/s10586-026-06364-7
Zhou, C., Fu, T., Shi, C., et al. (2026) · Information Processing in Agriculture · doi:10.1016/j.inpa.2026.07.012
Jiang, Z., Wang, M., Liu, K., & Kurths, J. (2026) · Climate Dynamics · doi:10.1007/s00382-026-08203-2
“CNN-based architecture such as AlexNet (Krizhevsky et al. 2017), LeNet (Lecun et al. 1998), GoogLeNet (Szegedy et al. 2014) have been successfully applied to remote sensing (Moniruzzaman et al. 2017), geographical analysis (Jiang et al. 2023) and atmospheric research (Yip and Yau 2012; Mercer and Grimes 2017).”
Qodri, K. N., Desmana, S., Putri, B. A., Ratih, R., & Muin, M. A. (2026) · Blend Sains Jurnal Teknik · doi:10.56211/blendsains.v5i1.1841
“Arsitektur-arsitektur lain seperti AlexNet [6], ResNet [7], GoogLeNet [8], dan VGGNet [9] telah membuktikan kekuatan pembelajaran fitur konvolusi yang dalam pada skala besar.”
Data-driven optimization and rheology-guided machine learning of geopolymer direct ink writing
Huang, Z., Yan, W., Chen, W., Islam, S. A., Liu, F., Sun, Q., Lin, H., Kvan, T., & Hao, L. (2026) · Materials Today Communications · doi:10.2139/ssrn.7205852
An improved lightweight model based on MobileNetV3 for noise-resistant fiber laser mode recognition
Chai, J., Wu, C., Song, Z., et al. (2026) · Optics & Laser Technology · doi:10.1016/j.optlastec.2026.116058
Advanced Deep Learning Approaches for Image-based Diagnosis of Banana Leaf Diseases
Vidhya, N., & Priya, R. S. (2026) · AI Computer Science and Robotics Technology · doi:10.5772/acrt.20250204
Guo, Z. (2026) · Frontiers in Earth Science · doi:10.3389/feart.2026.1822287
Cloud classification using transfer convolutional neural network for short term rainfall prediction
Sarwade, M. P., Patil, V. S., & Shinde, S. A. (2026) · AIP conference proceedings · doi:10.1063/5.0328700
Evolutionary chemical learning in dimerization networks
Anonymous, Mognetti, B. M., & Maslov, S. (2026) · Physical review. E · doi:10.1103/bszq-gftl
Bimodal-frequency-aware hashing network for screen content images
Huang, Z., Guo, L., Zhang, Y., Zhang, S., & Tang, Z. (2026) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2026.104917
Few Shot Pet Emotion Recognition Using Prototypical Networks with ResNet34 Backbone
Gilhotra, K., Yadav, V., Diwakar, M., Lohumi, Y., Singh, P., & Roka, S. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-32476-4_27
PSMamba: Progressive self-supervised vision Mamba for plant disease recognition
Mamun, A. A., Zhang, M., Ahmedt‐Aristizabal, D., et al. (2026) · Expert Systems with Applications · doi:10.1016/j.eswa.2026.133775
Data-Driven Optimization and Rheology-Guided Machine Learning of Geopolymer Direct Ink WritingPreprint
Huang, Z., Yan, W., Chen, W., Islam, S. A., Liu, F., Sun, Q., Lin, H., Kvan, T., & Liang, H. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7205854
ObjectVisA-120: Object-based Visual Attention Prediction in Interactive Street-crossing Environments
Vozniak, I., Müller, P., Lipp, N., et al. (2026) · 2026 IEEE Intelligent Vehicles Symposium (IV) · doi:10.1109/iv66570.2026.11624005
“Salient features are often extracted by CNN back-bone models [33]–[36].”
AI Vision for Health Care: AI-Powered Smart Glasses for Visually Impaired Individual
Ali, A., Ali, M., Farooq, M., et al. (2026) · International Journal of Innovations in Science and Technology · doi:10.33411/ijist/1884
Embedding-Consistent Contrastive Learning: A Robust Approach for Imbalanced Classification
Siamak, S., & Mansoori, E. G. (2025) · International Conference on Information and Knowledge Technology (IKT) · doi:10.1109/ikt69652.2025.11626677
“While the 2012 breakthrough of deep CNNs [2] revolutionized computer vision and later dominated medical imaging, their application in this domain is persistently challenged by class imbalance, which can lead to biased models that underperform on rare but clinically critical disease.”
Wang, Z., & Jiang, Y. (2026) · IEEE Internet of Things Journal · doi:10.1109/jiot.2026.3718868
Lee, H., Burd, J., Ling, T., Yang, Y.-K., Chang, N.-S., Chen, W.-C., Chen, C., Chiueh, T., Lee, M. K.-T., Yang, C., et al. (2026) · IEEE Journal of Solid-State Circuits · doi:10.1109/jssc.2026.3715500
Demir, S., & Akgül, M. (2026) · Bilişim Teknolojileri Dergisi · doi:10.17671/gazibtd.1852936
Development of Explainable Audio-Based Deep Learning for Gender-Aware Dysarthria Classification
Nengsih, W., Fadhli, M., & Mohammad, M. (2026) · International Conference on Smart Computing, IoT and Machine Learning (SIML) · doi:10.1109/siml69834.2026.11621254
“Convolutional Neural Networks (CNNs) and other data-driven architectures have demonstrated strong performance in capturing complex acoustic representations directly from time–frequency features such as spectrograms and Mel-frequency cepstral coefficients (MFCCs)[8],[9].”
Load-Aware Offline Scheduling for Heterogeneous Edge Deep Learning Inference
Fefey, E. G., & Islam, T. Z. (2026) · IEEE Cloud Summit · doi:10.1109/cloudsummit68932.2026.00023
“In our work, we use the pre-trained AlexNet [14] model.”
Evaluating Attention-Enhanced CNNs for Image Classification with Grad-CAM Visualization
Tran, L. B., Zhang, B., Chen, L., Zhao, L., Qin, H., & Khokhar, R. H. (2026) · IEEE/ACIS International Conference on Software Engineering Research, Management and Applications (SERA) · doi:10.1109/sera69989.2026.11618613
“It achieved an unprecedented top-5 error rate of 15.3%, a substantial improvement over the previous best result of 26.2% [1].”
InfluentialApplications and prospects of AI/ML in electric vehicle regenerative braking systems: A review
Qin, Y., Xu, X., Zheng, Z., He, C., Liang, C., Chen, T., Xu, T., & Wang, Y. (2026) · Renewable and Sustainable Energy Reviews · doi:10.1016/j.rser.2026.117355
RCAGFusion: Recursive cross-attention guided deep feature fusion for indoor scene recognition
Wang, C., Wei, J., Qiu, H., et al. (2026) · Image and Vision Computing · doi:10.1016/j.imavis.2026.106146
Early Diagnosis of Alzheimer’s Disease USING DEEP learning MRI Images: A Systematic Review
Obaid, A. K., & Farjami, Y. (2026) · Kufa Journal of Engineering · doi:10.30572/2018/kje/170329
Multimodal Feature Fusion with Illumination Adaptation for Robust Household Waste Detection
Hu, Z., Wu, X., Zhou, J., et al. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-31663-9_1
BenHabireche, M. L., Belhadj, M., Tamzalit, D., et al. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-31920-3_32
Pushpa, G. M., & Adbhilash, D. K. S. (2026) · International Journal of Latest Technology in Engineering Management & Applied Science · doi:10.51583/ijltemas.2026.150600253
Shao, D., Ji, W., Hao, X., & Kokhanovsky, A. A. (2026) · Springer series in light scattering · doi:10.1007/978-3-032-18867-0_4
Ejigu, B. E., Sinshaw, N. T., Assefa, B. G., et al. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-26370-4_30
Jacquier-Bret, J., & Gorce, P. (2026) · Theoretical and Applied Ergonomics · doi:10.3390/tae2030016
Kien, N. M., Chau, M. T., Long, V. T., et al. (2026) · Communications in computer and information science · doi:10.1007/978-981-92-2590-3_11
Developments in Fruits Detection, Localization, and Harvest Robotics
Saeed, A. I., Zhang, Z., El-Sayed, W., Mossad, A., Mayhoub, M., Abdelhamid, M. A., Gu, F., Cheng, H., Li, X., & Cao, W. (2026) · Smart agriculture · doi:10.1007/978-981-92-0205-8_4
Learning Context Enhanced Features for Image Classification
Wang, B., Ma, C., & Zhang, T. (2026) · Smart innovation, systems and technologies · doi:10.1007/978-3-032-25609-6_15
Pasbanigoloojeh, R., Rehman, M. U., Dhahbi, A., & Rakhmanov, Z. (2026) · Applied Artificial Intelligence · doi:10.1080/08839514.2026.2705617
Shioya, K., Hayashi, K., Li, B., et al. (2026) · Frontiers in Neural Circuits · doi:10.3389/fncir.2026.1783892
Chang, X., Zhang, B., Gao, Z. W., Chen, S., & Liu, J. (2026) · Sensors · doi:10.3390/s26154857
“In such inspection tasks, effective use of image information requires digital image representation, visual feature extraction, and convolutional representation learning to support morphology recognition and discriminative feature extraction [1–3].”
Ahmad, I., Khan, M. S., Nisa, K., et al. (2026) · Research Square · doi:10.21203/rs.3.rs-9737870/v1
Li, B., Sang, J., & Wang, K. (2026) · Systems Science & Control Engineering · doi:10.1080/21642583.2026.2709950
SE-Enhanced Ensembled Deep Learning Framework for Parking Space Classification
Navpreet, Sharma, P. K., Sofian, H., et al. (2026) · Machine Learning and Knowledge Extraction · doi:10.3390/make8080226
“The architecture of AlexNet, which was modified in [40], proved to be capable of detecting objects despite partially covering them or being subjected to different lighting conditions, and this is a testament to how resistant the architecture is to these distortions.”
Gumma, L., & Gumma, B. (2026) · Naunyn-Schmiedeberg s Archives of Pharmacology · doi:10.1007/s00210-026-05700-3
Li, Y., Li, C., Jin, Y., Wang, H., Sheng, M., & Ren, J. (2026) · Archives of Computational Methods in Engineering · doi:10.1007/s11831-026-10750-0
A Collapse Pressure Prediction Method Based on Virtual-Well Constraints and Deep Sequence Learning
Li, N., Luo, J., Fan, W., Xia, Y., & Zhang, Z. (2026) · Applied Sciences · doi:10.3390/app16157780
Batchmon: Exploiting Serverless Functions for Cost-Effective, SLO-Driven Batch Inference Serving
Calero-Santo, J., & Sánchez-Artigas, M. (2026) · IEEE International Conference on Distributed Computing Systems · doi:10.1109/2575-8411.2026.00081
“For ResNet 50 and VGG 19 , each inference request is an ImageNet image [41].”
CBAM-Enhanced EfficientFormerV2 for Combustion State Recognition in Cement Rotary Kilns
Liu, Y., Yu, H.-L., Zhang, R.-F., et al. (2026) · Youth Academic Annual Conference of Chinese Association of Automation · doi:10.1109/yac71005.2026.11615942
MambaCNN: A hybrid Mamba-convolution vision backbone
Liu, K.-H., Lu, T., Xie, Y., et al. (2026) · Applied Soft Computing · doi:10.1016/j.asoc.2026.116077
TMSA‐Net: Transformer‐Based Multi‐Scale Attention U‐Net for Flood Image Segmentation
Charandabi, P. I., Shivakumara, P., Antonacopoulos, A., & Clausner, C. (2026) · CAAI Transactions on Intelligence Technology · doi:10.1049/cit2.70169
PowerGrad: Hierarchical Power Management for Power-Limited ML Inference Clusters
Nam, H., Pothukuchi, R. P., Buyuktosunoglu, A., Amarnath, A., Bose, P. K., & Torrellas, J. (2026) · Proceedings - International Symposium on Computer Architecture/Proceedings · doi:10.1109/isca66397.2026.00166
“It combines a convolution neural network (CNN) [22] and a transformer to encode both image and text data together to generate an output image over multiple iterations.”
Pisse, J. C., & Shekhar, R. (2026) · International Conference on Data Science for Cyber-Physical Systems Resilience using Advanced Applications (ICDCA) · doi:10.1109/icdca69396.2026.11620059
Structured proxy features for multimodal NSCLC survival prediction from pretreatment CT
Nguyen, H. P., Hossain, D., Saghapour, E., et al. (2026) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2026.1865458
Liu, C., Shao, S., Cai, Z., et al. (2026) · AgriEngineering · doi:10.3390/agriengineering8080323
“During the acquisition of wheat spike images, variations in weather conditions, illumination and imaging devices may lead to uneven exposure, shadow interference and image blurring, thereby affecting image quality and increasing the difficulty of subsequent image processing and analysis [24].”
Cheeseman, T., Miller, B., Madhusudhana, S., & Hodgson, A. J. (2026) · Marine Mammal Science · doi:10.1111/mms.70238
Can Neural Networks Think Like Geomorphologists?
Martin, J., & Tucker, G. E. (2026) · Geophysical Research Letters · doi:10.1029/2026gl124040
“While convolutional neural networks have been used for decades for targeted image recognition tasks (LeCun et al., 1989), the success of the AlexNet CNN on the ImageNet database (Krizhevsky et al., 2017) began the wide adoption of the method in computer vision.”
Robust Zero-Watermarking Algorithm for Medical Images Based on RegNet-DCT
Yang, X., Li, J., Liu, J., et al. (2026) · Smart innovation, systems and technologies · doi:10.1007/978-3-032-21376-1_22
A Hybrid Xception-ViT Architecture for Enhanced Deepfake Video Detection
Huang, P., Lin, P., Odle, E., & Arbaiy, N. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-25638-6_20
Cardiovascular Disease Diagnosis Method Based on AMEsim Simulation and Convolutional Neural Networks
Zhang, X., Zhang, H., Dang, W., Wu, K., Ren, X., & Zhang, Y. (2026) · Communications in computer and information science · doi:10.1007/978-981-95-9938-7_13
Nagata, F., Tokuno, K., Matsui, K., et al. (2026) · Signals and communication technology · doi:10.1007/978-3-032-18566-2_18
A Fourier Optoelectronic Synapse with Single‐Wavelength Modulation
Wang, K., Peng, B., Jiang, S., Xing, Q., Zhang, H., Cheng, S., Ren, Y., Shi, K., Cui, H., Wang, B., et al. (2026) · Advanced Materials · doi:10.1002/adma.74518
“The four DNN are LeNet [ 49 ], AlexNet [ 50 ], VGG16 [ 51 ], and VGG [ 52 ], respectively.”
Comparative Analysis of Machine Learning Models for Lung Cancer Detection Using CT Scan Images
Osama, M., Ahmed, E., Batool, M., Saleem, M., & Salim, A. (2025) · International Journal of Innovations in Science and Technology · doi:10.33411/ijist/1223
A Gear Coupling Network for Infrared Dim and Small Target Detection in Complex Backgrounds
Zhu, B., Feng, X., Chen, Y., Xiaotong, Y., & Gaoxiang, H. (2026) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2026.3720893
CA-LWNet: A Lightweight Network for Handwritten Dongba Character Recognition
Xiao, Y., Li, X., He, F., & Gu, J. (2026) · Communications in computer and information science · doi:10.1007/978-981-95-9938-7_6
Rahmoune, H., Boutrid, N., & Benchoufi, I. (2026) · Artificial Intelligence in Gastroenterology · doi:10.35712/aig.v7.i2.116570
ASTRA: Architectural inSights for post-ToRnado damAge recognition
Umeike, R., Dao, T., Crawford, S., et al. (2026) · Expert Systems with Applications · doi:10.1016/j.eswa.2026.133915
Sonsare, P. M., Agrawal, P., Chand, H. V., & Banait, S. S. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-28293-4_11
Jing, Y., & Wang, C. (2026) · Journal of Materials Chemistry C · doi:10.1039/d6tc02099b
Guo, R., Gong, W., Song, E., Zhang, C., Wang, Y., Ming, H., Chen, Z., Peng, Z., He, Z., & Zhang, Q. (2026) · Advanced Materials · doi:10.1002/adma.202521971
“Adapting the image classification architecture [ 61 ], we utilize the PPG time series as input and configure the output to return systolic and diastolic BP values instead of class predictions.”
Intelligent nanotechnology based approaches for agricultural disease surveillance and management
Yadav, A., & Yadav, K. (2026) · Discover Sensors · doi:10.1007/s44397-026-00075-9
“Integrating advanced imaging and real-time data collection indicates that combining deep learning with nanotechnology can improve detection accuracy and efficiency [113, 114].”
Li, P., Pan, D., Xie, Y. J., Yu, H., Li, Z., Zhang, P., & Wang, R. (2026) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2026.3721501
Peña, E. C. Q., Bonilla, C. C. Q., Hunter, L., et al. (2026) · Journal of Natural Fibers · doi:10.1080/15440478.2026.2708477
BriRet: ML-Based Image-to-3D Retrieval of Synthetic Bridge InfrastructurePreprint
Güneş, M. C., Bleker, L., Zhang, X., Dai, A., & D’Acunto, P. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7243540
Ma, J., Wen, S., Sun, L., Ying, L., Yang, Y., Yang, Y., Cao, Y., Yao, J., Qin, J., Xing, J., et al. (2026) · Information Processing & Management · doi:10.1016/j.ipm.2026.105079
BactoMate: an integrated platform for reproducible bacterial microscopy analysisPreprint
Hallenga, L., Fornoff, S., Pesch, M., et al. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.08.06.743177
“Users can construct training datasets from paired raw images and manually curated ground-truth masks and multiply the data by applying augmentation (flipping, rotation, adding noise) to increase data diversity and achieve over all better models for their specific experimental setups [24].”
Wang, Y., Sun, J., 贾文珅, et al. (2026) · Journal of Future Foods · doi:10.1016/j.jfutfo.2026.08.015
Wang, S., Wang, X., Yuan, X., et al. (2026) · Artificial Intelligence in Geosciences · doi:10.1016/j.aiig.2026.100259
Wang, S., Li, Y., Zhang, Z., & Qiao, S. (2026) · Reliability Engineering & System Safety · doi:10.1016/j.ress.2026.113265
Convolutional Neural Networks (CNNs)
Hemmati, A., Rahmani, A. M., Bazikar, F., Moosaei, H., & Pardalos, P. M. (2026) · Springer optimization and its applications · doi:10.1007/978-3-032-20703-6_3
Fault diagnosis of wind turbine gearboxes using SABO-optimised VMD and CNN-SVM integrated model
Tang, M., Fan, Z., Li, J., et al. (2026) · Transactions of the Institute of Measurement and Control · doi:10.1177/01423312261470466
FwNet-ECA: A Lightweight Fourier-Attention Network for Fine-Grained Image Classification
Li, X., Wang, Y., Gu, N., Wang, Y., & Mian, S. (2026) · The European Journal on Artificial Intelligence · doi:10.1177/30504554261468533 · Cited by 1
Pradhan, U., Ray, S., Aditya, M. N., & Anand, V. (2026) · Springer eBooks · doi:10.1007/978-3-032-26858-7_19
Cheng, H.-Y., Wu, X., Qiu, X., et al. (2026) · Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2 · doi:10.1145/3770855.3817648 · Cited by 6
“In this context, applying Convolutional Networks (CNNs) [25, 33, 64, 67] to the Channel-Frequency and Channel-Scale views has proven to be an efficient and effective strategy.”
Wavelet scattering networks for stable classification in adversarial settings
Ghizi, I. E., Omar, A. A., Hamouichou, K., Fariss, M., Habouz, Y. E., & Mourabit, Y. E. (2026) · EPJ Web of Conferences · doi:10.1051/epjconf/202638100008
An Explainable Deep Learning Approach for Multi-Region Bone Fracture Detection in X-Ray Images
R, T. N., Shamsudeen, F. M., Jacob, C., et al. (2026) · doi:10.1109/iehns68708.2026.11606813
“All models were initialized with weights pre-trained on the ImageNet large-scale image corpus [19], and their original top-layer classification heads were stripped and replaced with a custom binary classification block.”
Genetic Algorithm and EfficientNet-Based Diabetic Retinopathy Identification
Singh, A., & Kumar, R. (2026) · Communications in computer and information science · doi:10.1007/978-3-032-30990-7_21
Veerapandiyan, R., Thaiyalnayaki, S., & Kumari, G. R. N. (2026) · doi:10.1109/gseact68539.2026.11620063
Kashyapkumar, J., Chiari, G., & Guderian, J. (2026) · Digital Chemical Engineering · doi:10.1016/j.dche.2026.100332
Zhang, Y., Qiu, Z., Chen, T., Todo, Y., & Tang, Z. (2026) · Electronics · doi:10.3390/electronics15163516
An Intelligent Computing Framework for Smart Healthcare Applications
Karne, R., Archana Devi, G., Talwar, S., Srivani, N., Ramakrishna, C., & Mohandas, R. (2026) · IEEE Global Symposium on Emerging and Communication Technologies (GSEACT) · doi:10.1109/gseact68539.2026.11620301
Dai, M., Chiyu, H., & Miao, H. (2026) · Insects · doi:10.3390/insects17080822
Xiong, Y., Liang, Z., Chen, Z., Fan, Y., & Zuo, R. (2026) · Journal of Geophysical Research Machine Learning and Computation · doi:10.1029/2026jh001368
Chen, X., & Cheng, K. (2026) · International Journal of Computer Integrated Manufacturing · doi:10.1080/0951192x.2026.2714117 · Cited by 2
The future of consumer intelligence: A systematic literature review of AI in neuromarketing
Aprilianty, F., Matsuura, Y., & Takahashi, M. (2026) · Computers in Human Behavior Reports · doi:10.1016/j.chbr.2026.101239
Deep Learning Sensitivity Analysis for Computer Vision
Matos-Carvalho, J. P., Fernandes, D. F. S., Pavia, J. P., et al. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-23317-2_8
YCENet: a high-precision one-stage infrared target detector for complex scenarios
Yang, X., Wang, Y., Liang, R., Zhou, H., & Gu, J. (2026) · Infrared Physics & Technology · doi:10.1016/j.infrared.2026.106792
Underwater Acoustic Target Recognition Based on Multi-Scale Features Fusion
Yang, G., & Li, W. (2026) · doi:10.1109/oceans66983.2026.11617174
“[10] 0.29 56.10M Resnet18 [11] 11.17 1.14G GAT [12] 0.14 0.14M CNN [13] 1.14 319.82M UMFNet 5.07 34.89M On the validation dataset, the average accuracy of UMFNet was 93.50%.”
InfluentialDBSSM: A Dual-Branch Spectral–Spatial Mamba Network for Hyperspectral Image Classification
Li, H., Huang, H., Li, H., et al. (2026) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2026.3721475
Exploring the Limits of AI Cryptanalysis with Semantic Discrimination Evaluation: From Enigma to RSA
Yusa, K., & Nakamura, A. (2026) · International Conference on Control, Decision and Information Technologies (CoDIT) · doi:10.1109/codit70676.2026.11630745
YOLOv11-ASE: fabric defect detection algorithm based on improved YOLOv11
Wang, J., Wang, M., Xing, Y., et al. (2026) · Journal of the Textile Institute · doi:10.1080/00405000.2026.2713315
Alhalawani, N., Cirillo, L., & Amerini, I. (2026) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2026.104899
Wang, A., Zhang, Z., Luo, J., et al. (2026) · International Journal of Intelligent Transportation Systems Research · doi:10.1007/s13177-026-00709-7
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
