Research map / Label-efficient and robust learning / Self-supervised and contrastive
Interventional Contrastive Learning with Meta Semantic Regularizer
Wenwen Qiang, Jiangmeng Li, Changwen Zheng, Bing Su, Hui Xiong
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 MSR to LMCL | LMCL · CIFAR-10 | linear accuracy: 91.91 -> 92.45 | Improved |
| Add MSR to BYOL | BYOL · CIFAR-10 | 5-nn accuracy: 89.45 -> 90.12 | Improved |
| Add MSR to BYOL | BYOL · CIFAR-100 | linear accuracy: 66.60 -> 66.97 | Improved |
| Add MSR to BYOL | BYOL · STL-10 | linear accuracy: 91.99 -> 93.22 | Improved |
| Add MSR to BYOL | BYOL · Tiny ImageNet | 5-nn accuracy: 36.24 -> 37.54 | Improved |
| Add MSR to ReSSL | ReSSL · CIFAR-100 | linear accuracy: 63.79 -> 65.12 | Hurt |
| Add MSR to SimCLR | SimCLR · ImageNet-100 | top-1 accuracy: 70.15 -> 72.08 | Improved |
| Add MSR to SimCLR | SimCLR · ImageNet | top-1 accuracy: 69.3 -> 70.9 | Improved |
| Add MSR to BYOL | BYOL · ImageNet | top-1 accuracy: 74.3 -> 75.4 | Improved |
| Add MSR to BYOL | BYOL · ImageNet 1% labels | top-1 accuracy: 53.2 -> 55.5 | Improved |
| Add MSR to BYOL | BYOL · ImageNet 10% labels | top-5 accuracy: 89.0 -> 90.7 | Improved |
| Set gamma to 1 for uniformity loss (ablation) | ICL-MSR (SimCLR) · CIFAR-10 | accuracy | Improved |
Closest papers by meaning
- When Does Contrastive Visual Representation Learning Work? (CVPR 2022 · similarity 0.87)
- Decoupled Contrastive Learning (ECCV 2022 · similarity 0.87)
- A Simple Framework for Contrastive Learning of Visual Representations (ICML 2020 · similarity 0.87)
- Unleashing the Power of Contrastive Self-Supervised Visual Models via Contrast-Regularized Fine-Tuning (NeurIPS 2021 · similarity 0.87)
- Seed the Views: Hierarchical Semantic Alignment for Contrastive Representation Learning (TPAMI 2022 · similarity 0.87)
- Self-Supervised Contrastive Learning is Approximately Supervised Contrastive Learning (NeurIPS 2025 · similarity 0.86)
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.
