Research map / Label-efficient and robust learning / Self-supervised and contrastive
Learning Diverse and Discriminative Representations via the Principle of Maximal Coding Rate Reduction
Yaodong Yu, Kwan Ho Ryan Chan, Chong You, Chaobing Song, Yi Ma
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 |
|---|---|---|---|
| Train the same network with MCR² rather than cross-entropy | ResNet-18 features · CIFAR10, label corruption 0.5 | classification accuracy: 60.37% -> 84.30% | Improved |
| Train the same network with MCR² rather than cross-entropy | ResNet-18 features · CIFAR10, label corruption 0.1 | classification accuracy: 90.91% -> 91.16% | Improved |
| Control the expansion and compression rates during MCR² training (ablation) | MCR² self-supervised clustering · CIFAR10 | ACC: 0.570 -> 0.684 | Improved |
| Use MCR²-Ctrl rather than DCCM | Self-supervised clustering · CIFAR10 | ACC: 0.623 -> 0.684 | Improved |
| Use MCR²-Ctrl rather than DCCM | Self-supervised clustering · CIFAR100 | ARI: 0.173 -> 0.167 | Hurt |
| Use MCR²-Ctrl rather than DCCM | Self-supervised clustering · STL10 | ACC: 0.482 -> 0.491 | Improved |
Closest papers by meaning
- Efficient Maximal Coding Rate Reduction by Variational Forms (CVPR 2022 · similarity 0.89)
- Self-Supervised Learning via Maximum Entropy Coding (NeurIPS 2022 · similarity 0.89)
- A Global Geometric Analysis of Maximal Coding Rate Reduction (ICML 2024 · similarity 0.88)
- Connecting Jensen–Shannon and Kullback–Leibler Divergences: A New Bound for Representation Learning (NeurIPS 2025 · similarity 0.85)
- Supervised Distributional Reduction via Optimal Transport and Dependence Maximization (NeurIPS 2026 · similarity 0.85)
- I-Con: A Unifying Framework for Representation Learning (ICLR 2025 · 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.
