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 106,201–106,300 of 108,435
PAL-net: a light correction method for pears based on image information characteristics
Zhang, G., Zheng, W., Zhang, L., Pan, Z., Li, Y., & Wei, X. (2026) · Results in Engineering · doi:10.1016/j.rineng.2026.109102
Liao, Y., Chen, Y., Li, P., et al. (2025) · doi:10.1109/cyberscitech68397.2025.00076
“To enhance the efficiency of MedViMamba in medical image modeling, we integrate the concept of grouped convolution—originally proposed in AlexNet [26] for multi-GPU training—into a novel lightweight dual-branch block, termed SS-Conv-SSM.”
Widiasri, M., Siswantoro, J., & Duanto, A. K. (2026) · E3S Web of Conferences · doi:10.1051/e3sconf/202668702012
A novel method to learn unit cost and weight for soft consensus based on deep neural network
Zhang, H., Guo, D., & Ma, Y. (2026) · Knowledge-Based Systems · doi:10.1016/j.knosys.2026.115339 · Cited by 1
Comparative Study of Pre-Trained Models for BISINDO Sign Language Recognition
Dexter, A., Edberg, Ferdinand, F., Masaling, N. A. P., & Chowanda, A. (2025) · International Conference on Informatics and Computational Sciences (ICICoS) · doi:10.1109/icicos68590.2025.11329789
基于bi-mission ResNet18与PSF图像的光学系统失调量误差估计
Junnan, 韩. H., Wenlong, 乔. Q., Cunli, 段. D., Zhiguo, 李. L., Yu, 雷. L., & Xing, 付. F. (2025) · Infrared and Laser Engineering · doi:10.3788/irla20250400
Zeng, X., Xiang, Y., Zhang, J., & Lu, B. (2026) · Neural Networks · doi:10.1016/j.neunet.2026.108611 · Cited by 1
A Coverless Image Steganography Technique Based on Multi-Object Mapping Rules
Lin, C.-Y., & Liang, S.-W. (2026) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2026.3654470
Bhowmik, A. K. (2026) · Wiley eBooks · doi:10.1002/9781119615996.ch6
Research on Few-Shot Defect Detection Integrating Hybrid Attention Mechanism and Siamese Network
Bi, Y., Li, Q., & Wang, Y. (2025) · International Conference on Artificial Intelligence and Automation Control (AIAC) · doi:10.1109/aiac68175.2025.11332471
“CNN-based deep learning methods [6],[7] have advanced detection accuracy, but rely heavily on large annotated datasets, which are difficult to obtain in real scenarios with few defect samples.”
Chen, X., Chen, Y., Song, J., Jin, Y., Zhang, H., Li, M., & Nandi, A. K. (2025) · Proceedings of the Institution of Mechanical Engineers Part D Journal of Automobile Engineering · doi:10.1177/09544070241310021
FCN-Pose: A Pruned and Quantized CNN for Robot Pose Estimation for Constrained Devices
Dantas, M. S. M., Filho, A. T. D. O., Sadok, D. F. H., Kelner, J., & Silva, R. A. (2026) · Journal of Intelligent & Robotic Systems · doi:10.1007/s10846-025-02336-y · Cited by 21
The D3CNN text classification model based on multi-scale textual feature maps
Kang, C., & Li, K. (2025) · The Computer Journal · doi:10.1093/comjnl/bxaf151
121Chapter 6 Artificial intelligence in breast cancer management
Malviya, R., Rajput, S., Roy, M., Sridhar, S. B., & Thomas, S. (2025) · De Gruyter eBooks · doi:10.1515/9783111670744-006
M2CR: A primary liver cancer diagnosis system with multimodal multitask collaborative reasoning
Huang, S., Luo, J., Wan, X., & Nie, X. (2026) · Expert Systems with Applications · doi:10.1016/j.eswa.2026.131275
Jiang, W., Zhou, L., Yu, A., et al. (2026) · IEEE Sensors Journal · doi:10.1109/jsen.2026.3652980
“Building upon the basic CN architecture, researchers have developed several efficient and classical DCN models, such as AlexNet [28], VGG-19 [29], GoogLeNet [30], and ResNet-18 [31].”
Asri, M. A. A., Rajagopal, H., Mokhtar, N. B., et al. (2026) · PLoS ONE · doi:10.1371/journal.pone.0341160
“The study utilized Deep Convolutional Neural Networks (DCNNs), employing nine distinct models: EfficientNet-B0 [40], DarkNet-53 [41,42], Inception-ResNet-v2 [43], DarkNet-19 [44], ResNet-18 [45], ResNet-50 [45], ResNet-101 [45], Goo-gLeNet [46], and AlexNet [47].”
Multi-Dimensional Road Extraction from Medium Resolution Imagery using U-Net and YOLO Concepts
Sutichavengkul, C., & Goldin, S. E. (2025) · International Conferences on Information Technologies and Electrical Engineering · doi:10.1109/icitee66631.2025.11338258
“Past research has demonstrated that DL-based road segmentation methods can learn subtle and complex spatial, structural and spectral patterns from remote sensing imagery, beyond what can be expressed through explicitly defined rules [24], [25].”
Improving Image Classification Accuracy with First Place Weight
Tang, L., & Huang, Z. (2025) · International Conference on Algorithms, Software and Network Security (ASNS) · doi:10.1109/asns67347.2025.11346056
“With the development of deep learning technology, computer vision, including image classification, object detection, object segmentation, object tracking, and so on, has made significant progress in recent years [1-6].”
Tang, J.-C., Cheng, W.-Y., & Chen, D.-Y. (2026) · IEEE Access · doi:10.1109/access.2026.3655389
G, S., & Manoj, M. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6100679
A Lightweight Student Posture Recognition Method Based on Dilated Convolution and Pruning
Fang, J., Zhao, C.-Q., Wang, S.-W., et al. (2025) · 2025 International Conference on Advanced Computing and Intelligent Robotics Applications (ACIRA) · doi:10.1109/acira67680.2025.11335011
“In terms of lightweight network design, the Vgg Laboratory effectively reduced network computational overheads through convolutional kernel replacement [18] .”
Research on Risk Identification for Computer Room Operations Based on ConvNeXt
Liu, H. F., Hu, W., Qin, Y., Feng, X., & Tian, X. (2025) · IEEE Advanced Information Management, Communicates, Electronic and Automation Control Conference (IMCEC) · doi:10.1109/imcec66174.2025.11332166
“To address LeNet's limited fitting capacity, AlexNet expanded the network's breadth and depth[2], providing enhanced computational capabilities.”
Content-Based Image Retrieval for Guava Images Using Deep Learning Techniques
Rangkuti, A. H., Samiaji, T. A., & Sebastian, J. (2025) · International Conference on Informatics, Multimedia, Cyber and Information System (ICIMCIS) · doi:10.1109/icimcis68501.2025.11327431
“The rise of deep learning changed CBIR by allowing automated feature extraction from raw pixel data, eliminating the need for manual descriptor engineering [3].”
Ahmed, T., Ahmed, A., Imran, A. S., Ullah, M., Manaf, A., & Soylu, A. (2026) · IEEE Access · doi:10.1109/access.2026.3655022 · Cited by 3
Enhancing Lung Cancer Diagnosis with ResNet-34: A Deep Learning Approach on Chest CT Images
Du, W., & Su, Z. (2025) · International Conference on Machine Learning and Computer Application (ICMLCA) · doi:10.1109/icmlca66850.2025.11336657
“These operations make image features more consistent and better suited for model training [1] .”
Kim, D. H., Kim, G., Kim, M. J., Lee, S. Y., & Yang, Y. S. (2026) · IEEE Access · doi:10.1109/access.2026.3655178
AI-Powered Medical Data Breach Detection System
Blessy, S. A., & Jebaseeli, T. J. (2025) · International Conference on Applied Artificial Intelligence and Computing (ICAAIC) · doi:10.1109/icaaic64647.2025.11331116
“…industries globally, and breaches have cost organizations millions of dollars, whether in government fines, remediation costs, or reputational harm traditional security measures such as firewalls, encryption, and signature-based Intrusion Detection Systems (IDS) offer only limited protection [3-5].”
Seismic Trend Analysis and Prediction
Suma, D., Menda, A. S., Sree, B. M., & Yesuraj, R. (2025) · International Conference on Applied Artificial Intelligence and Computing (ICAAIC) · doi:10.1109/icaaic64647.2025.11330661
“Section III outlines data sources, preprocessing, and model architecture [6,12].”
InfluentialWan, S., Zhao, Z., Bian, X., & Li, B. (2025) · IEEE International Conference on Advances in Electrical Engineering and Computer Applications (AEECA) · doi:10.1109/aeeca65693.2025.00112
“Currently, Convolutional Neural Networks (CNNs) [5–7] are the predominant method for extracting discriminative optical features from such data, and have shown excellent performance and application value.”
Hevea Clone Identification using Deep Learning
Romruensukharom, T., & Nonsiri, S. (2025) · International Conferences on Information Technologies and Electrical Engineering · doi:10.1109/icitee66631.2025.11338251
“Its success was demonstrated on the ImageNet Large Scale Visual Recognition Challenge (ILSVRC) [12].”
Local–global synergistic enhanced perception network for lightweight super-resolution
Dong, L., Zhang, H., Wang, G., et al. (2026) · The Journal of Supercomputing · doi:10.1007/s11227-025-08201-x
Srivastava, S., Kumar, R., & Hamid, A. B. A. (2025) · IEEE International Conference on Computing, Communication and Automation (ICCCA) · doi:10.1109/iccca66364.2025.11325703
“Classical CNNs have shown impressive performance in extracting low-to mid-level spatial features from images, such as edges, textures, and local patterns, by using hierarchical layers of convolution and pooling operations [17].”
Forest fire prediction using image processing
Li, Y., Chen, J., Zeng, Y., et al. (2026) · PLoS ONE · doi:10.1371/journal.pone.0338794
“The paper first introduces a variety of deep learning methods commonly used for forest fire detection, such as convolutional Neural Network (CNN), U-Net, InceptionV3 [10–12], etc.”
Ship Abnormal Behavior Recognition System Based on YOLOv5
Li, D., Han, Z., Du, M., et al. (2025) · International Conference on Image Processing, Computer Vision and Machine Learning (ICICML) · doi:10.1109/icicml67980.2025.11333720
“Representative models include CNN [2] , Faster R-CNN [3] , SSD, and YOLO.”
Ban, G., Xi, G., Xu, M., et al. (2025) · IEEE Advanced Information Management, Communicates, Electronic and Automation Control Conference (IMCEC) · doi:10.1109/imcec66174.2025.11332131
A DeepLabV3+ Based Encoder-Decoder Framework for Street View Semantic Segmentation
Hao, B. (2025) · International Conference on Machine Learning and Computer Application (ICMLCA) · doi:10.1109/icmlca66850.2025.11336603
“The DeepLabV3+ architecture is adopted, integrating an encoder-decoder structure with atrous spatial pyramid pooling (ASPP) [13,14] .”
A Unified Lightweight Network for Complex Scene Image Understanding via Multi-Task Joint Learning
Guo, T., Yang, S., Fu, Y., et al. (2026) · IEEE Access · doi:10.1109/access.2026.3655826
Li, S., Chen, J., Huo, H., et al. (2026) · Frontiers in Earth Science · doi:10.3389/feart.2025.1694635
He, Z., Zhang, W., Huang, X., et al. (2025) · International Conference on Image Processing, Computer Vision and Machine Learning (ICICML) · doi:10.1109/icicml67980.2025.11333475
“Following standard practice [31], the dataset is 1 https://robotics.pkusz.edu.cn/resources/dataset/ split into 560 training (80%), 63 validation (10%), and 70 testing (10”
Violence Video Recognition Based on Two-Stage Collaborative Data Augmentation
文, 晨. (2026) · Journal of Image and Signal Processing · doi:10.12677/jisp.2026.151008
Yıldırım, B., & Aydın, E. (2025) · National Conference on Electrical and Electronics Engineering (ELECO) · doi:10.1109/eleco69582.2025.11329263
“Object detection has achieved accuracy and robustness improvements along with the advent of deep learning, particularly with convolutional neural networks (CNNs), under dynamic traffic conditions [4][5].”
Binary Image Classification with CNNs, Transfer Learning and Classical Models
Oikonomou, N. V., Oikonomou, D. V., Chaliasou, S. P., et al. (2026) · Journal of Engineering Research and Sciences · doi:10.55708/js0501006
AEMT-DETR: adaptive enhanced multi-scale tiny DETR for Yangtze River fishing boat detection
Cui, X., & Chen, K. (2026) · Engineering Research Express · doi:10.1088/2631-8695/ae3a40
Man, X., Sun, C., Chen, Z., Ji, Y., Du, J., & Yu, B. (2026) · ACS Synthetic Biology · doi:10.1021/acssynbio.5c00722
Zhou, H., Luo, Y., Chen, Z., Zhuo, M., Qian, Q., Gong, W., Lin, Z., & Lin, W. (2026) · Soft Computing · doi:10.1007/s00500-025-10967-4
“This module replaces traditional convolutions in skip connections with group convolu-tions (Krizhevsky et al. 2017 ), significantly reducing the encoder’s computational burden.”
Micheal, A. A., Micheal, A. A., Anurekha, G., & Barathi, B. U. A. (2026) · Journal of the Indian Society of Remote Sensing · doi:10.1007/s12524-025-02402-w
ZHONG, J., Zou, Z., Xu, J., et al. (2026) · Chinese Journal of Space Science · doi:10.11728/cjss2026.01.2025-0097
Vargova, P., Varga, M., Hernández, B. I., Gutierrez-Alonso, C., Esgueda, A. J. G., Atuán, R. L. F., Hernández, M. V. C., Santinno-Tenorio, A., & Bellostas, C. C. (2026) · European Radiology · doi:10.1007/s00330-025-12267-9
Few-Shot Learning in Vision-Language Models: A Survey
Deshpande, V., Shelke, G., Jaiswal, R. C., et al. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-14044-9_10
Classification of Ancient Writing Systems with Limited DataPreprint
BAYRAKLI, İ., & Ölçer, D. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6114183
Fault Injection in Logic-in-Memory Architectures
Staudigl, F., & Leupers, R. (2026) · Synthesis lectures on engineering, science, and technology · doi:10.1007/978-3-032-09586-2_4
Deep Learning–Based Classification of Slit-Lamp Photograph Quality in Microbial Keratitis
Ong, J., Lu, M.-C., Thanitcul, C., et al. (2026) · Ophthalmology Science · doi:10.1016/j.xops.2026.101086
Personalized supervised and unsupervised intracranial sleep decoding during deep brain stimulation
Smyth, C., Anjum, M. F., Zhang, J., Yao, J., Abbasi-Asl, R., Starr, P. A., & Little, S. J. (2026) · npj Digital Medicine · doi:10.1038/s41746-026-02368-0 · Cited by 2
Saad, M., Arafa, A. A., Kamel, M., et al. (2026) · Nuclear Technology · doi:10.1080/00295450.2025.2580201
Image processing strategy and target device
Mishra, V. P., & Roy, A. (2026) · Elsevier eBooks · doi:10.1016/b978-0-443-34266-0.00015-2
Application of artificial intelligence in gynecologic cancers: A bibliometric analysis
Liu, N., Jiang, F., Lou, Y., & Guan, J. (2026) · Digital Health · doi:10.1177/20552076261416708
Enhancing software reliability models through neural network driven weight adaptation
Kumar, A., Yadav, S. S., Johri, P., et al. (2026) · Elsevier eBooks · doi:10.1016/b978-0-443-34266-0.00050-4
Lu, Q., Zheng, L., Su, J., Ma, W., Ma, H., & Zhang, Y. (2026) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2026.109672
Co-Optimization and Deployment of Lightweight Convolutional Neural Networks on FPGAs
Huang, J. (2025) · International Conference on Electronic Information Engineering and Computer Technology (EIECT) · doi:10.1109/eiect68017.2025.11331770
“For example, depthwise separable convolution[10] decomposes standard convolutions to greatly reduce computation and parameter count, while grouped convolution[11] lowers computational cost and supports parallelism.”
Patel, K., & Patel, K. (2025) · International Conference on Communication and Electronics Systems (ICCES) · doi:10.1109/icces67310.2025.11337045
“Transfer learning is a method that utilizes knowledge acquired by already trained models to enhance the performance of new tasks, leading to more accurate and faster models [4].”
Wang, Z., Gao, Y., Ye, L., et al. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6110592
YOLO with Gradient-Aware Dynamic Detection Head for Dense Small Object Detection in Complex Scenes
Cun, X., & Ding, Y. (2025) · International Conference on Robotics and Computer Vision (ICRCV) · doi:10.1109/icrcv67407.2025.11349196
“CNNs[3] and their variants (including YOLO[4], SSD[5] and Faster R-CNN[6]) have enhanced detection accuracy and speed through automatic feature learning.”
Sivarathinabala, M., Vignesh, V., Naveen, D., et al. (2025) · doi:10.1109/ciscon66933.2025.11337859
Fangzhen, W. A. N. G., Liang, S., Zhang, X., & Zhou, Y. (2026) · Journal of Vibration and Control · doi:10.1177/10775463261420022
Kong, K., Yang, X., Zhang, C., et al. (2026) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2026.3656823
Atif, N., Mazhar, S., Ameen, M., et al. (2026) · IEEE Transactions on Circuits and Systems I Regular Papers · doi:10.1109/tcsi.2025.3649392
Lightweight Feature-Based Object Detection in Natural Scenes Using SIFT and Homography
Godbin, A. B., Mithra, C., Dar, S. A., et al. (2025) · 2025 International Conference on Electrical, Electronics, and Computer Science with Advance Power Technologies - A Future Trends (ICE2CPT) · doi:10.1109/ice2cpt66440.2025.11340141
“Traditional approaches to object detection and recognition have largely shifted toward deep learning-based methods in recent years, driven by advances in convolutional neural networks (CNNs) and the availability of large annotated datasets [1,2].”
Choudhary, P., Jaiswal, A., Pandey, P., et al. (2025) · International Conference on Intelligent Information Processing · doi:10.1109/iciip68302.2025.11346115
“MRI sequences such as PD, T1, T2, and 3D matsc, along with advanced techniques like T2 mapping, enable detailed assessment of tissue integrity and early cartilage degeneration, although high costs restrict widespread use [13].”
Lightweight Feature-Based Object Detection in Natural Scenes Using SIFT and Homography
Godbin, A. B., Mithra, C., Dar, S. A., et al. (2025) · 2025 International Conference on Electrical, Electronics, and Computer Science with Advance Power Technologies - A Future Trends (ICE2CPT) · doi:10.1109/ice2cpt66440.2025.11340081
“Traditional approaches to object detection and recognition have largely shifted toward deep learning-based methods in recent years, driven by advances in convolutional neural networks (CNNs) and the availability of large annotated datasets [1,2].”
BioNIC: Biologically Inspired Neural Network for Image Classification Using Connectomics PrinciplesPreprint
Prasanth, D., & Tivnan, M. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6127005
Transformers for Image Super-Resolution: A Comprehensive Review
Choksy, P., Sarvaiya, A., & Upla, K. P. (2025) · International Conference on Image Information Processing (ICIIP) · doi:10.1109/iciip68302.2025.11346297
Multi-Model Federated Learning for Predicting Childbirth Mode
Pathak, A., & Rathor, S. (2025) · International Conference on Information Systems and Computer Networks (ISCON) · doi:10.1109/iscon65210.2025.11341271
Effect of Bias Matrix in Linear Self-Attention for In-Context Learning
Hagiwara, K. (2026) · IEICE Transactions on Information and Systems · doi:10.1587/transinf.2025edp7161
AFFNet: Adaptive feature fusion network for defect detection of industrial product surface
Jia, Z., Wang, S., Zheng, J., et al. (2026) · Applied Intelligence · doi:10.1007/s10489-026-07099-z
“AlexNet [1] lays the foundation for research on product surface defect detection.”
Du, S., & Wen, Y. (2025) · IEEE International Conference on Control, Electronics and Computer Technology (ICCECT) · doi:10.1109/iccect64621.2025.11339646
Image-driven analysis of tensile mechanical properties of 2.5D woven composites
Liao, Y., Wang, Z., Wang, B., et al. (2026) · Composites Science and Technology · doi:10.1016/j.compscitech.2026.111538
Approaches for Brain Tumor Detection Using Imaging and AI Based Methods
Kasilingam, N., R, L. K. S., Patil, S., et al. (2025) · doi:10.1109/ssitcon66133.2025.11342098
“Brain tumors represent abnormal cellular proliferation within cerebral tissues, constituting one of the most challenging malignancies in modern oncology [2][3][4].”
Adaptive Robotics Benchmarking: A Modular Framework for Evaluating Manipulation Systems
Nishad, K. A. (2025) · doi:10.1109/ssitcon66133.2025.11342125
“• Recognition: Employs SVM or CNN-based object classification [11].”
A Domain Adaptation Framework for Fault Diagnosis Using Manifold Features and Deep Learning
Lin, Y. (2025) · IEEE International Conference on Control, Electronics and Computer Technology (ICCECT) · doi:10.1109/iccect64621.2025.11339786
Huang, W., Yang, S., Hou, X., et al. (2026) · Physical Communication · doi:10.1016/j.phycom.2026.103018
YOLO–DE: An enhanced YOLOv11 model for the study of pipeline flow monitoring technology
Wen, X., Weng, M., dong, J., et al. (2026) · Engineering Research Express · doi:10.1088/2631-8695/ae3cfb
Classifying High-Accuracy Photos with Convolutional Neural Networks
Singh, G., Raj, R., Singh, A., Vijaybhai, B. S., Purohit, D. M., & Kori, S. (2025) · IEEE International Conference on Information Technology, Electronics and Intelligent Communication Systems (ICITEICS) · doi:10.1109/iciteics64870.2025.11341721
“DL models have attained notable progress in multiple domains, such as text and picture classification [3] and natural language processing [4].”
Engineering Safe Machine Learning for Automated Driving Systems
Frtunikj, J., & Fürst, S. (2019) · Safety-Critical Systems Symposium (SSS) · doi:10.65391/r1070
DeepSched: Neural Network-Based Task Scheduling for Heterogeneous Distributed Systems
Panwar, P. (2025) · IEEE International Conference on Control, Electronics and Computer Technology (ICCECT) · doi:10.1109/iccect64621.2025.11339673
Skin Disease Detection: Implementing Hybrid Classification Model to Detect Skin Cancer
Efendy, C. L., Yeshe, D., Faria, E. J., & Yulianto, B. (2025) · International Conference on Information and Communications Technology (ICOIACT) · doi:10.1109/icoiact67584.2025.11344937
“With the current advancement in artificial intelligence, specifically convolution neural network (CNN) based deep learning algorithms, images can be classified efficiently from large labeled datasets [7].”
Singh, D., & Kumar, S. (2026) · IEEE Transactions on Reliability · doi:10.1109/tr.2026.3657526
Langener, A. M., Haddox, D., Mackin, D. M., Price, G. D., Lekkas, D., Collins, A. C., Griffin, T. Z., Heinz, M. V., Nemesure, M. D., Nepal, S. K., et al. (2026) · Addictive Behaviors · doi:10.1016/j.addbeh.2026.108624
“…learn meaningful patterns from individual sensor types, while the fourth head processes time-series physiological data by converting it into 2D images via Gramian Angular Fields and applying a 2D convolutional neural network architecture to capture temporal dependencies (Krizhevsky et al., 2017).”
Artificial Intelligence-Based Depression Detection
Kiss, G., & Viktor, P. (2026) · Sensors · doi:10.3390/s26020748
“Compared to traditional statistical approaches, neural networks are able to automatically reveal complex, hidden patterns that may be associated with depression [29].”
Jia, J., Zhang, R., Yuan, D., et al. (2026) · Journal of Neural Engineering · doi:10.1088/1741-2552/ae3d68
“First, although traditional deep learning tends to have increasingly complex models [38, 39], neuroscience studies suggest that EEG features are relatively simple [10, 16, 40].”
Scattering-Based Self-Supervised Learning for Label-Efficient Cardiac Image Segmentation
Alasu, S., & Talu, M. F. (2026) · Electronics · doi:10.3390/electronics15030506
Radar Signal Modulation Recognition Based on Improved YOLOv11
Lei, L., Zhu, Y., Ruan, H., et al. (2025) · International Conference on Signal Processing Systems · doi:10.1109/icsps66615.2025.11347953
“To further evaluate the performance of the proposed LEF-YOLO network, we compare it with four classical convolutional neural networks—AlexNet [18], VGG [19], GoogleNet [20], and ResNet [21].”
Sanders, B. J., MORRISON, D. L., & Harris‐Birtill, D. (2026) · PLoS ONE · doi:10.1371/journal.pone.0339917 · Cited by 1
“Using a Convolutional Neural Networks (CNNs) are widely known for their high performance in image classification tasks [36].”
Fang, D., Wang, J., & Hu, W. (2026) · Security and Privacy · doi:10.1002/spy2.70195
“We selected commonly used models in RSI classification tasks, including AlexNet [33], VGG16 [34], ResNet18 [35], ResNet101 [35], DenseNet121 [36], DenseNet201 [36], and RegNetX400MF [37] as target models.”
Huaysrijan, A., & Pongpinigpinyo, S. (2026) · Multimedia Tools and Applications · doi:10.1007/s11042-026-21300-y
“In the realm of audio signal processing, Convolutional Neural Network (CNN) stands out as a state-of-the-art and widely adopted approach due to its effectiveness in supervised learning, demonstrating remarkable performance on highly challenging datasets [ 23].”
A novel deep reinforcement learning framework with human activation function to control quadrotor
Norouzi, P., Shahbazi, H., & Torabi, K. (2026) · International Journal of Dynamics and Control · doi:10.1007/s40435-026-02006-3
Multi-modal Object Detection with Improved Faster R-CNN
Qian, J., Liu, J., & Ju, R. (2026) · Lecture notes in electrical engineering · doi:10.1007/978-981-95-3320-6_5
MSTnet: Multimodal Soft Threshold Fusion Network Based on BERT
Xu, G., Yuan, Y., & Huang, X. Y. (2025) · IEEE International Conference on Data Science in Cyberspace · doi:10.1109/dsc67331.2025.00051
“The development of visual-verbal tasks has benefited greatly from advances in pre-training strategies across vision and language [9][10].”
Wang, P., Zuo, Y., Xie, Q., et al. (2025) · IEEE International Conference on Power, Intelligent Computing and Systems (ICPICS) · doi:10.1109/icpics66386.2025.11347431
“[9 ] The efficient dual attention mechanism EDANet proposed in this article also consists of two parallel attention modules, as shown in Fig.”
Xu, L., & Yu, X. (2025) · IEEE International Conference on Power, Intelligent Computing and Systems (ICPICS) · doi:10.1109/icpics66386.2025.11347365
“Since the introduction of AlexNet, CNNs have become the dominant approach for FER due to their powerful feature extraction capabilities [12] .”
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
