The DOI matches its Crossref record; 24 of the 24 references it cites were found in a registry or an index.
Towards dropout training for convolutional neural networks
Open accessAbstract
Recently, dropout has seen increasing use in deep learning. For deep convolutional neural networks, dropout is known to work well in fully-connected layers. However, its effect in convolutional and pooling layers is still not clear. This paper demonstrates that max-pooling dropout is equivalent to randomly picking activation based on a multinomial distribution at training time. In light of this insight, we advocate employing our proposed probabilistic weighted pooling, instead of commonly used max-pooling, to act as model averaging at test time. Empirical evidence validates the superiority of probabilistic weighted pooling. We also empirically show that the effect of convolutional dropout is not trivial, despite the dramatically reduced possibility of over-fitting due to the convolutional architecture. Elaborately designing dropout training simultaneously in max-pooling and fully-connected layers, we achieve state-of-the-art performance on MNIST, and very competitive results on CIFAR-10 and CIFAR-100, relative to other approaches without data augmentation. Finally, we compare max-pooling dropout and stochastic pooling, both of which introduce stochasticity based on multinomial distributions at pooling stage.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
Gradient-based learning applied to document recognition
Lecun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998) · Proceedings of the IEEE · doi:10.1109/5.726791 · Cited by 58,805
(2014) · Cited by 33,419
Learning Multiple Layers of Features from Tiny Images
Krizhevsky, A. (2024) · doi:10.57702/zp44cu3g · Cited by 23,395
Reducing the dimensionality of data with neural networks
Hinton, G. E., & Salakhutdinov, R. R. (2006) · Science · doi:10.1126/science.1127647 · Cited by 20,928
Breiman, L. (1996) · Machine Learning · doi:10.1007/bf00058655 · Cited by 16,325 · cited 2×
“It is similar to bagging (Breiman, 1996), in which a set of models are trained on different subsets of the same training data.”
BackgroundMethod(2010) · International Conference on Machine Learning · Cited by 13,995
Representation Learning: A Review and New Perspectives
Bengio, Y., Courville, A., & Vincent, P. (2013) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2013.50 · Cited by 13,001
Advances in Neural Information Processing Systems 25
Zhang, Y., Sutton, C. A., Storkey, A., & Zoubin Ghahramani, A. (2012) · Cited by 12,653
Improving 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
Multi-column deep neural networks for image classification
Ciresan, D., Meier, U., & Schmidhuber, J. (2012) · 2012 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2012.6248110 · Cited by 3,720
(2013) · Cited by 2,056
A Theoretical Analysis of Feature Pooling in Visual Recognition
Boureau, Y.-L., Ponce, J., & LeCun, Y. (2010) · Cited by 1,661
Evaluation of Pooling Operations in Convolutional Architectures for Object Recognition
Scherer, D., Müller, A., & Behnke, S. (2010) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-15825-4_10 · Cited by 1,503
(1976) · Lecture Notes in Mathematics · doi:10.1007/bfb0082336 · Cited by 1,297
Ledoux, M., & Talagrand, M. (1991) · doi:10.1007/978-3-642-20212-4 · Cited by 1,160
(2014) · arXiv (Cornell University) · Cited by 942
Mackay, D. J. C. (1995) · Network Computation in Neural Systems · doi:10.1088/0954-898x/6/3/011 · Cited by 915
ImageNet classification with deep convolutional neural networks
Krizhevsky (2012) · Medical Entomology and Zoology · Cited by 799
Stochastic Pooling for Regularization of Deep Convolutional Neural Networks
Zeiler, M. D., & Fergus, R. (2013) · arXiv (Cornell University) · doi:10.48550/arxiv.1301.3557 · Cited by 755
The dropout learning algorithm
Baldi, P., & Sadowski, P. (2014) · Artificial Intelligence · doi:10.1016/j.artint.2014.02.004 · Cited by 340 · cited 2×
“We also empirically show that the effect of convolutional dropout is not trivial, despite the dramatically reduced possibility of over-fitting due to the convolutional architecture.”
Dropout Training as Adaptive Regularization
Wager, S., Wang, S., & Liang, P. (2013) · arXiv (Cornell University) · doi:10.48550/arxiv.1307.1493 · Cited by 245
An empirical analysis of dropout in piecewise linear networksPreprint
Warde-Farley, D., Goodfellow, I., Courville, A. C., & Bengio, Y. (2013) · arXiv (Cornell University) · doi:10.48550/arxiv.1312.6197 · Cited by 118
Improving Deep Neural Networks with Probabilistic Maxout UnitsPreprint
Springenberg, J. T., & Riedmiller, M. (2013) · arXiv (Cornell University) · doi:10.48550/arxiv.1312.6116 · Cited by 97
Cited by
Improved regularization of convolutional neural networks with cutout
DeVries, T., & Taylor, G. W. (2017) · arXiv · doi:10.48550/arxiv.1708.04552 · Cited by 2,776
“Wu and Gu propose probabilistic weighted pooling [20], wherein activations in each pooling region are dropped with some probability.”
BackgroundAbdeljaber, O., Avci, O., Kiranyaz, M. S., Boashash, B., Sodano, H., & Inman, D. J. (2018) · Neurocomputing · doi:10.1016/j.neucom.2017.09.069 · Cited by 521
Thin MobileNet: An Enhanced MobileNet Architecture
Sinha, D., & El-Sharkawy, M. (2019) · 2019 IEEE 10th Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON) · doi:10.1109/uemcon47517.2019.8993089 · Cited by 379
A Comparison of Pooling Methods for Convolutional Neural Networks
Zafar, A., Aamir, M., Mohd Nawi, N., Arshad, A., Riaz, S., Alruban, A., Dutta, A. K., & Almotairi, S. (2022) · Applied Sciences · doi:10.3390/app12178643 · Cited by 367
Deep Learning Advances in Computer Vision with 3D Data: A Survey
Ioannidou, A., Chatzilari, E., Nikolopoulos, S., & Kompatsiaris, I. (2018) · ACM Computing Surveys · doi:10.1145/3042064 · Cited by 327
Metadata
- Authors
- Wu, H., & Gu, X.
- Venue
- Neural Networks
- Publisher
- Elsevier BV
- Published
- 2015-11
- Volume
- 71
- Pages
- 1-10
- ISSN
- 0893-6080 (ISSN-L)
- OpenAlex
- W1034159276
- Cited by
- 314
- References
- 24
- FWCI
- 15.31
- Type
- journal article
- Language
- en
- Open access
- green
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.
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
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.