Research map / Label-efficient and robust learning / Recognition and long-tail
Curvature-Balanced Feature Manifold Learning for Long-Tailed Classification
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 curvature regularization to GCL | GCL with ResNet-32 · CIFAR-100-LT, IF 100 | Top-1 accuracy: 48.7 -> 49.8 | Helped |
| Add curvature regularization to RIDE + CMO | RIDE + CMO with ResNet-32 · CIFAR-100-LT, IF 10 | Top-1 accuracy: 60.2 -> 61.4 | Helped |
| Add curvature regularization to GCL | GCL with ResNet-32 · CIFAR-10-LT, IF 200 | Top-1 accuracy: 79.0 -> 79.9 | Helped |
| Add curvature regularization to RIDE | RIDE with ResNext-50 · ImageNet-LT | Overall Top-1 accuracy: 56.6 -> 57.8 | Helped |
| Add curvature regularization to cross-entropy training | CE with ResNext-50 · ImageNet-LT | Overall Top-1 accuracy: 44.4 -> 47.3 | Helped |
| Add curvature regularization to RIDE + CMO | RIDE + CMO with ResNet-50 · iNaturalist2018 | Overall Top-1 accuracy: 72.8 -> 73.8 | Helped |
| Add curvature regularization to cross-entropy training | CE with ResNet-50 · iNaturalist2018 | Overall Top-1 accuracy: 61.7 -> 63.4 | Helped |
| Add curvature regularization to cross-entropy training | CE with ResNet-18 · CIFAR-100 | Top-1 accuracy: 75.6 -> 77.1 | Helped |
| Add curvature regularization to cross-entropy training | CE with ResNet-50 · ImageNet | Top-1 accuracy: 76.0 -> 76.8 | Helped |
Closest papers by meaning
- Data Representations' Study of Latent Image Manifolds (ICML 2023 · similarity 0.89)
- Dual Manifold Regularization Steered Robust Representation Learning for Point Cloud Analysis (AAAI 2025 · similarity 0.86)
- Hardness of Learning Neural Networks under the Manifold Hypothesis (NeurIPS 2024 · similarity 0.86)
- Curvature Enhanced Data Augmentation for Regression (ICML 2025 · similarity 0.85)
- Difficulty-aware Balancing Margin Loss for Long-tailed Recognition (AAAI 2025 · similarity 0.85)
- Connecting Neural Models Latent Geometries with Relative Geodesic Representations (NeurIPS 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.