The DOI matches its Crossref record; 58 of the 58 references it cites were found in a registry or an index.
Why ResNet Works? Residuals Generalize
Open accessAbstract
Residual connections significantly boost the performance of deep neural networks. However, few theoretical results address the influence of residuals on the hypothesis complexity and the generalization ability of deep neural networks. This article studies the influence of residual connections on the hypothesis complexity of the neural network in terms of the covering number of its hypothesis space. We first present an upper bound of the covering number of networks with residual connections. This bound shares a similar structure with that of neural networks without residual connections. This result suggests that moving a weight matrix or nonlinear activation from the bone to a vine would not increase the hypothesis space. Afterward, an O(1 / √N) margin-based multiclass generalization bound is obtained for ResNet, as an exemplary case of any deep neural network with residual connections. Generalization guarantees for similar state-of-the-art neural network architectures, such as DenseNet and ResNeXt, are straightforward. According to the obtained generalization bound, we should introduce regularization terms to control the magnitude of the norms of weight matrices not to increase too much, in practice, to ensure a good generalization ability, which justifies the technique of weight decay.
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
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
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
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
Densely Connected Convolutional Networks
Huang, G., Liu, Z., Van Der Maaten, L., & Weinberger, K. Q. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.243 · Cited by 48,566
Feature Pyramid Networks for Object Detection
Lin, T.-Y., Dollar, P., Girshick, R., He, K., Hariharan, B., & Belongie, S. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.106 · Cited by 30,939
He, K., Gkioxari, G., Dollar, P., & Girshick, R. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.322 · Cited by 29,137
Data Mining: Practical Machine Learning Tools and Techniques
(2011) · Elsevier eBooks · doi:10.1016/c2009-0-19715-5 · Cited by 25,437
Learning Multiple Layers of Features from Tiny Images
Krizhevsky, A. (2024) · doi:10.57702/zp44cu3g · Cited by 23,395
Chen, L.-C., Papandreou, G., Kokkinos, I., Murphy, K., & Yuille, A. L. (2016) · arXiv · doi:10.48550/arxiv.1606.00915 · Cited by 22,392
Chen, L.-C., Papandreou, G., Kokkinos, I., Murphy, K., & Yuille, A. L. (2018) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2017.2699184 · Cited by 22,392
Mastering the game of Go with deep neural networks and tree search
Silver, D., Huang, A., Maddison, C. J., Guez, A., Sifre, L., van den Driessche, G., Schrittwieser, J., Antonoglou, I., Panneershelvam, V., Lanctot, M., et al. (2016) · Nature · doi:10.1038/nature16961 · Cited by 15,612
A survey on deep learning in medical image analysis
Litjens, G., Kooi, T., Bejnordi, B. E., Setio, A. A. A., Ciompi, F., Ghafoorian, M., van der Laak, J. A. W. M., van Ginneken, B., & Sánchez, C. I. (2017) · Medical Image Analysis · doi:10.1016/j.media.2017.07.005 · Cited by 15,332
Dermatologist-level classification of skin cancer with deep neural networks
Esteva, A., Kuprel, B., Novoa, R. A., Ko, J., Swetter, S. M., Blau, H. M., & Thrun, S. (2017) · Nature · doi:10.1038/nature21056 · Cited by 14,362
Aggregated Residual Transformations for Deep Neural Networks
Xie, S., Girshick, R., Dollar, P., Tu, Z., & He, K. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.634 · Cited by 12,465
TensorFlow: A system for large-scale machine learning
Abadi, M., Barham, P., Chen, J., Chen, Z., Davis, A., Dean, J., Devin, M., Ghemawat, S., Irving, G., Isard, M., et al. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1605.08695 · Cited by 11,822
Greff, K., Srivastava, R. K., Koutnik, J., Steunebrink, B. R., & Schmidhuber, J. (2017) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2016.2582924 · Cited by 6,955 · cited 1×
“The recent years saw dramatic progress of deep neural networks [29, 16, 44, 46, 34, 7].”
BackgroundUnderstanding deep learning requires rethinking generalization
Zhang, C., Bengio, S., Hardt, M., Recht, B., & Vinyals, O. (2016) · arXiv · doi:10.48550/arxiv.1611.03530 · Cited by 2,838 · cited 1×
“Zhang et al. conduct systematic experiments to explore the generalization ability of deep neural networks [52].”
BackgroundRademacher and Gaussian Complexities: Risk Bounds and Structural Results
Bartlett, P. L., & Mendelson, S. (2001) · Lecture Notes in Computer Science · doi:10.1007/3-540-44581-1_15 · Cited by 1,949
(1992) · Cited by 1,405
Foundations of Machine Learning
Mohri, M., Rostamizadeh, A., & Talwalkar, A. (2018) · doi:10.7551/mitpress/10290.001.0001 · Cited by 1,122
Foundations of Machine Learning
(2012) · Boosting · doi:10.7551/mitpress/8291.003.0006 · Cited by 1,074
Visualizing the Loss Landscape of Neural Nets
Li, H., Xu, Z., Taylor, G., Studer, C., & Goldstein, T. (2017) · Repository for Publications and Research Data (ETH Zurich) · doi:10.3929/ethz-b-000461393 · Cited by 926
Computer Vision for Autonomous Vehicles: Problems, Datasets and State of the Art
Janai, J., Güney, F., Behl, A., & Geiger, A. (2020) · Foundations and Trends® in Computer Graphics and Vision · doi:10.1561/0600000079 · Cited by 643
Sharp Minima Can Generalize For Deep NetsPreprint
Dinh, L., Pascanu, R., Bengio, S., & Bengio, Y. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1703.04933 · Cited by 602
Bartlett, P. L., Bousquet, O., & Mendelson, S. (2002) · Cited by 533
A Theory of Pattern Recognition
Амари, Ш.-И. (1968) · Jidō seigyo/Jido seigyo · Cited by 443
The Sizes of Compact Subsets of Hilbert Space and Continuity of Gaussian Processes
Dudley, R. M. (2010) · Selected Works of R.M. Dudley · doi:10.1007/978-1-4419-5821-1_11 · Cited by 438
Bartlett, P. L., Bousquet, O., & Mendelson, S. (2005) · The Annals of Statistics · doi:10.1214/009053605000000282 · Cited by 372
Theoretical Insights Into the Optimization Landscape of Over-Parameterized Shallow Neural Networks
Soltanolkotabi, M., Javanmard, A., & Lee, J. D. (2019) · IEEE Transactions on Information Theory · doi:10.1109/tit.2018.2854560 · Cited by 356
Sphere packing numbers for subsets of the Boolean n-cube with bounded Vapnik-Chervonenkis dimension
Haussler, D. (1995) · Journal of Combinatorial Theory, Series A · doi:10.1016/0097-3165(95)90052-7 · Cited by 288
Exploring Generalization in Deep Learning
Neyshabur, B., Bhojanapalli, S., McAllester, D., & Srebro, N. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1706.08947 · Cited by 284
A PAC-Bayesian Approach to Spectrally-Normalized Margin Bounds for Neural Networks
Neyshabur, B., Bhojanapalli, S., & Srebro, N. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1707.09564 · Cited by 283
Sensitivity and Generalization in Neural Networks: an Empirical Study
Novak, R., Bahri, Y., Abolafia, D. A., Pennington, J., & Sohl‐Dickstein, J. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1802.08760 · Cited by 275
Emergence of Invariance and Disentanglement in Deep Representations
Achille, A., & Soatto, S. (2018) · 2018 Information Theory and Applications Workshop (ITA) · doi:10.1109/ita.2018.8503149 · Cited by 267
Fisher-Rao Metric, Geometry, and Complexity of Neural NetworksPreprint
Liang, T., Poggio, T., Rakhlin, A., & Stokes, J. (2017) · International Conference on Artificial Intelligence and Statistics · doi:10.48550/arxiv.1711.01530 · Cited by 265
Closing the Generalization Gap of Adaptive Gradient Methods in Training Deep Neural Networks
Chen, J., Zhou, D., Tang, Y., Yang, Z., Cao, Y. J., & Gu, Q. (2020) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2020/452 · Cited by 237
Statistical Analysis of Some Multi-Category Large Margin Classification Methods
Zhang, T. (2004) · doi:10.5555/1005332.1044701 · Cited by 215
Generalization in Deep Learning
Kawaguchi, K., Bengio, Y., & Kaelbling, L. (2022) · Mathematical Aspects of Deep Learning · doi:10.1017/9781009025096.003 · Cited by 197
Generalization with Deep Learning: For Improvement on Sensing Capability
Chen, Z., Wu, M., & Li, X. (2020) · WORLD SCIENTIFIC eBooks · doi:10.1142/11784 · Cited by 179
Size-independent sample complexity of neural networks
Golowich, N., Rakhlin, A., & Shamir, O. (2020) · Information and Inference: A Journal of the IMA · doi:10.1093/imaiai/iaz007 · Cited by 177
When and Why Are Deep Networks Better Than Shallow Ones?
Mhaskar, H., Liao, Q., & Poggio, T. (2017) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v31i1.10913 · Cited by 168
Computer Vision for Autonomous Vehicles: Problems, Datasets and State of the Art
Janai, J., Güney, F., Behl, A., & Geiger, A. (2017) · arXiv · doi:10.48550/arxiv.1704.05519 · Cited by 141
Universal Donsker Classes and Metric Entropy
Dudley, R. M. (2010) · Springer eBooks · doi:10.1007/978-1-4419-5821-1_19 · Cited by 141
Control Batch Size and Learning Rate to Generalize Well: Theoretical and Empirical Evidence
He, F., Liu, T., & Tao, D. (2019) · neural information processing systems · Cited by 132
Self-citationNearly-tight VC-dimension bounds for piecewise linear neural networksPreprint
Harvey, N., Liaw, C., & Mehrabian, A. (2017) · arXiv (Cornell University) · Cited by 103
Algorithmic Stability and Generalization Performance
Bousquet, O., Elisseeff, A., & Bioinformatics, B. (2000) · Cited by 87
Depth with nonlinearity creates no bad local minima in ResNets
Kawaguchi, K., & Bengio, Y. (2019) · Neural Networks · doi:10.1016/j.neunet.2019.06.009 · Cited by 70
Face Alignment With Deep Regression
Shi, B., Bai, X., Liu, W., & Wang, J. (2016) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2016.2618340 · Cited by 64
Li, Y., Tian, X., Liu, T., & Tao, D. (2017) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2017.2690683 · Cited by 50
Self-citationAre ResNets Provably Better than Linear Predictors?Preprint
Shamir, O. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1804.06739 · Cited by 45
Adversarial Training Versus Weight DecayPreprint
Galloway, A., Tanay, T., & Taylor, G. W. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1804.03308 · Cited by 21
Matrix-Regularized Multiple Kernel Learning via $(r,~p)$ Norms
Han, Y., Yang, Y., Li, X., et al. (2018) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2017.2785329 · Cited by 20
Understanding Generalization in Recurrent Neural Networks
Tu, Z., He, F., & Tao, D. (2020) · International Conference on Learning Representations · Cited by 20
Self-citationEigenfunction-Based Multitask Learning in a Reproducing Kernel Hilbert Space
Tian, X., Li, Y., Liu, T., Wang, X., & Tao, D. (2018) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2018.2873649 · Cited by 18
Self-citationBayesian Weight Decay on Bounded Approximation for Deep Convolutional Neural Networks
Park, J.-G., & Jo, S. (2019) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2018.2886995 · Cited by 13
Chang, D., Lin, M., & Zhang, C. (2018) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2017.2764960 · Cited by 11
Generalization Error Bounds for Optimization Algorithms via Stability
Meng, Q., Wang, Y., Chen, W., Wang, T., Ma, Z.-M., & Liu, T. (2017) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v31i1.10919 · Cited by 7
Self-citationOpening the Black Box of Deep Neural Networks via Information
Shwartz-Ziv, R., & Tishby, N. (2017) · arXiv · doi:10.48550/arxiv.1703.00810
Cited by
Knowledge Distillation: A Survey
Gou, J., Yu, B., Maybank, S. J., & Tao, D. (2021) · International Journal of Computer Vision · doi:10.1007/s11263-021-01453-z · Cited by 3,931
Self-citationSelf-augmented Unpaired Image Dehazing via Density and Depth Decomposition
Yang, Y., Wang, C., Liu, R., Zhang, L., Guo, X., & Tao, D. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.00208 · Cited by 317
Self-citationDispersed Pixel Perturbation-Based Imperceptible Backdoor Trigger for Image Classifier Models
Wang, Y., Zhao, M., Li, S., Yuan, X., & Ni, W. (2022) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2022.3202687 · Cited by 26
Metadata
- Authors
- He, F., Liu, T., & Tao, D.
- Venue
- IEEE Transactions on Neural Networks and Learning Systems
- Published
- 2020-12
- Volume
- 31
- Issue
- 12
- Pages
- 5349-5362
- ISSN
- 2162-237X (ISSN-L)
- 2162-2388
- OpenAlex
- W3004591935
- Cited by
- 406
- References
- 58
- FWCI
- 11.55
- 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.