Research map / Architectures and efficiency / RNNs and normalization
New Interpretations of Normalization Methods in Deep Learning
Jiacheng Sun, Xiangyong Cao, Hanwen Liang, Weiran Huang, Zewei Chen, Zhenguo Li
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add weight decay to BN | BN with ResNet-101 · CIFAR-10, Gaussian Noise | test accuracy: 0.8125 -> 0.7812 | Hurt |
| add weight decay to BN | BN with ResNet-101 · CIFAR-10, BIM-$l_\infty$ | test accuracy: 0.5380 -> 0.6000 | Improved |
| add weight decay to BN | BN with ResNet-101 · CIFAR-100, Gaussian Noise | test accuracy: 0.4596 -> 0.4953 | Improved |
| add weight decay to BN | BN with ResNet-101 · CIFAR-100, BIM-$l_\infty$ | test accuracy: 0.1397 -> 0.1558 | Improved |
| add weight decay to normalization training | BN, GN, LN, and WN · CIFAR-10 and CIFAR-100 under Gaussian noise and BIM attacks | test accuracy | Mixed |
| train with a scaling-invariant normalization method | BN, LN, GN, or WN · CIFAR-10 and CIFAR-100 | adversarial robustness | Hurt |
Closest papers by meaning
- Normalization Techniques in Training DNNs: Methodology, Analysis and Application (TPAMI 2023 · similarity 0.90)
- Norm matters: efficient and accurate normalization schemes in deep networks (NeurIPS 2018 · similarity 0.89)
- Beyond BatchNorm: Towards a Unified Understanding of Normalization in Deep Learning (NeurIPS 2021 · similarity 0.89)
- Understanding Batch Normalization (NeurIPS 2018 · similarity 0.88)
- Normalization Propagation: A Parametric Technique for Removing Internal Covariate Shift in Deep Networks (ICML 2016 · similarity 0.88)
- Towards Training Without Depth Limits: Batch Normalization Without Gradient Explosion (ICLR 2024 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
