Noisy Softmax: Improving the Generalization Ability of DCNN via Postponing the Early Softmax Saturation
Open accessThe DOI matches its Crossref record; 14 of the 14 references it cites were found in a registry or an index.
Abstract
Over the past few years, softmax and SGD have become a commonly used component and the default training strategy in CNN frameworks, respectively. However, when optimizing CNNs with SGD, the saturation behavior behind softmax always gives us an illusion of training well and then is omitted. In this paper, we first emphasize that the early saturation behavior of softmax will impede the exploration of SGD, which sometimes is a reason for model converging at a bad local-minima, then propose Noisy Softmax to mitigating this early saturation issue by injecting annealed noise in softmax during each iteration. This operation based on noise injection aims at postponing the early saturation and further bringing continuous gradients propagation so as to significantly encourage SGD solver to be more exploratory and help to find a better local-minima. This paper empirically verifies the superiority of the early softmax desaturation, and our method indeed improves the generalization ability of CNN model by regularization. We experimentally find that this early desaturation helps optimization in many tasks, yielding state-of-the-art or competitive results on several popular benchmark datasets.
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
FaceNet: A unified embedding for face recognition and clustering
Schroff, F., Kalenichenko, D., & Philbin, J. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298682 · Cited by 15,267 · cited 2×
“Many promising techniques have been developed, such as novel network structures [29, 13, 41], non-linear activation functions [12, 7, 6, 38], pooling strategies [11, 8, 53] and objective loss functions [43, 36], etc.”
BackgroundIdentity mappings in deep residual networks
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46493-0_38 · Cited by 10,741
Identity Mappings in Deep Residual Networks
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · arXiv · doi:10.48550/arxiv.1603.05027 · Cited by 10,665
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
Striving for Simplicity: The All Convolutional Net
Springenberg, J. T., Dosovitskiy, A., Brox, T., & Riedmiller, M. (2014) · arXiv · doi:10.48550/arxiv.1412.6806 · Cited by 3,447
What is the best multi-stage architecture for object recognition?
Jarrett, K., Kavukcuoglu, K., Ranzato, M. A., & LeCun, Y. (2009) · 2009 IEEE 12th International Conference on Computer Vision · doi:10.1109/iccv.2009.5459469 · Cited by 2,153
Deep Networks with Stochastic Depth
Huang, G., Sun, Y., Liu, Z., Sedra, D., & Weinberger, K. Q. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46493-0_39 · Cited by 2,104
Deep Learning Face Representation by Joint Identification-Verification
Sun, Y., Wang, X., & Tang, X. (2014) · arXiv · doi:10.48550/arxiv.1406.4773 · Cited by 1,906
Cited by
ArcFace: Additive Angular Margin Loss for Deep Face Recognition
Deng, J., Guo, J., Xue, N., & Zafeiriou, S. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00482 · Cited by 7,781
Deep face recognition: A survey
Wang, M., & Deng, W. (2021) · Neurocomputing · doi:10.1016/j.neucom.2020.10.081 · Cited by 1,466
Self-citationPast, Present, and Future of Face Recognition: A Review
Adjabi, I., Ouahabi, A., Benzaoui, A., & Taleb-Ahmed, A. (2020) · Electronics · doi:10.3390/electronics9081188 · Cited by 560
A survey on deep learning based face recognition
Guo, G., & Zhang, N. (2019) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2019.102805 · Cited by 485
Mixed High-Order Attention Network for Person Re-Identification
Chen, B., Deng, W., & Hu, J. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00046 · Cited by 415
Self-citationDeep Imbalanced Learning for Face Recognition and Attribute Prediction
Huang, C., Li, Y., Loy, C. C., & Tang, X. (2020) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2019.2914680 · Cited by 354
Striking the Right Balance With Uncertainty
Khan, S., Hayat, M., Zamir, S. W., Shen, J., & Shao, L. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00019 · Cited by 180
Cross-Age LFW: A Database for Studying Cross-Age Face Recognition in Unconstrained Environments
Zheng, T., Deng, W., & Hu, J. (2017) · arXiv · doi:10.48550/arxiv.1708.08197
Self-citation
Metadata
- Authors
- Chen, B., Deng, W., & Du, J.
- Venue
- 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2017-07
- Pages
- 4021-4030
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W2963227127
- Cited by
- 146
- References
- 14
- FWCI
- 8.77
- Type
- conference paper
- 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.