Research map / Label-efficient and robust learning / Recognition and long-tail
Predicting and Enhancing the Fairness of DNNs With the Curvature of Perceptual Manifolds
Yanbiao Ma, Licheng Jiao, Fang Liu, Maoji Wen, Lingling Li, Wenping Ma, Shuyuan Yang, Xu Liu, Puhua Chen
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 curvature regularization (CR) | Cross Entropy · CIFAR-10-LT (IF 200) | Top-1 accuracy: 65.6 -> 67.9 | Improved |
| add CR | Cross Entropy · CIFAR-100-LT (IF 100) | Top-1 accuracy: 38.2 -> 40.5 | Improved |
| add CR | GCL · CIFAR-100-LT (IF 100) | Top-1 accuracy: 48.7 -> 49.8 | Improved |
| add CR | Cross Entropy · ImageNet-LT (overall) | Top-1 accuracy: 44.4 -> 47.3 | Improved |
| add CR | Cross Entropy · ImageNet-LT (Tail) | Top-1 accuracy: 7.70 -> 19.5 | Improved |
| add CR | Cross Entropy · ImageNet-LT (Head) | Top-1 accuracy: 65.9 -> 65.1 | Hurt |
| add CR | BBN · ImageNet-LT (overall) | Top-1 accuracy: 44.7 -> 46.2 | Improved |
| add CR | RIDE + CMO · ImageNet-LT (overall) | Top-1 accuracy: 56.2 -> 57.4 | Improved |
| add CR | Cross Entropy · iNaturalist2018 (overall) | Top-1 accuracy: 61.7 -> 63.4 | Improved |
| add CR | RIDE + CMO · iNaturalist2018 (overall) | Top-1 accuracy: 72.8 -> 73.8 | Improved |
| add CR | Cross Entropy ResNet-18 · CIFAR-100 (balanced) | Top-1 accuracy: 75.6 -> 77.1 | Improved |
| add CR | Cross Entropy ResNet-18 · ImageNet (balanced) | Top-1 accuracy: 70.1 -> 71.3 | Improved |
Closest papers by meaning
- Curvature-Balanced Feature Manifold Learning for Long-Tailed Classification (CVPR 2023 · similarity 0.98)
- Geometric Inductive Biases of Deep Networks: The Role of Data and Architecture (ICLR 2025 · similarity 0.87)
- Estimating Shape Distances on Neural Representations with Limited Samples (ICLR 2024 · similarity 0.87)
- Curvature Clues: Decoding Deep Learning Privacy with Input Loss Curvature (NeurIPS 2024 · similarity 0.86)
- Global curvature for second-order optimization of neural networks (ICML 2025 · similarity 0.86)
- Hardness of Learning Neural Networks under the Manifold Hypothesis (NeurIPS 2024 · 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.
