Research map / Learning theory and algorithms / Fairness
Unveiling and Mitigating Generalized Biases of DNNs Through the Intrinsic Dimensions of Perceptual Manifolds
Yanbiao Ma, Licheng Jiao, Fang Liu, 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 Intrinsic Dimension Regularization (IDR) to the training loss | CNN and transformer image classifiers · CIFAR-10, CIFAR-100, Mini-ImageNet and a fourth benchmark (class-balanced) | overall accuracy and class-accuracy bias | Improved |
| use IDR instead of Focal Loss or SeeSaw Loss | baseline classifiers · four class-balanced datasets | overall performance and model bias | Improved |
| increase the weight of L_ID in mid-to-late training (smaller alpha schedule) (ablation) | IDR · benchmark image datasets | overall performance | Improved |
Closest papers by meaning
- Predicting and Enhancing the Fairness of DNNs With the Curvature of Perceptual Manifolds (TPAMI 2025 · similarity 0.92)
- Curvature-Balanced Feature Manifold Learning for Long-Tailed Classification (CVPR 2023 · similarity 0.88)
- Towards Debiasing DNN Models from Spurious Feature Influence (AAAI 2022 · similarity 0.87)
- Benchmarking Bias Mitigation Algorithms in Representation Learning through Fairness Metrics (NeurIPS 2021 · similarity 0.87)
- Recover Fair Deep Classification Models via Altering Pre-trained Structure (ECCV 2022 · similarity 0.87)
- Classes Are Not Equal: An Empirical Study on Image Recognition Fairness (CVPR 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.
