Research map / Label-efficient and robust learning / Recognition and long-tail
Towards Calibrated Model for Long-Tailed Visual Recognition from Prior Perspective
Zhengzhuo Xu, Zenghao Chai, Chun Yuan
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 UniMix mixing to CE (ablation) | ERM · CIFAR-10-LT rho=100 | top-1 accuracy: 70.36 -> 76.47 | Improved |
| add UniMix mixing to CE (ablation) | ERM · CIFAR-100-LT rho=100 | top-1 accuracy: 38.32 -> 41.46 | Improved |
| replace mixup with UniMix (CE loss) (ablation) | mixup · CIFAR-10-LT rho=200 | top-1 accuracy: 67.73 -> 68.42 | Improved |
| replace CE with Bayias-compensated CE (ablation) | ERM · CIFAR-10-LT rho=100 | top-1 accuracy: 70.36 -> 78.70 | Improved |
| replace CE with Bayias-compensated CE (ablation) | ERM · CIFAR-100-LT rho=100 | top-1 accuracy: 38.32 -> 43.52 | Improved |
| add UniMix to Bayias (ablation) | Bayias CE · CIFAR-10-LT rho=100 | top-1 accuracy: 78.70 -> 82.75 | Improved |
| add UniMix to Bayias (ablation) | Bayias CE · CIFAR-100-LT rho=200 | top-1 accuracy: 38.83 -> 42.07 | Improved |
| add mixup to LDAM (ablation) | LDAM · CIFAR-10-LT rho=100 | top-1 accuracy: 74.47 -> 73.96 | Hurt |
| add mixup to LDAM (ablation) | LDAM · CIFAR-100-LT rho=100 | top-1 accuracy: 41.76 -> 40.22 | Hurt |
| add UniMix to LDAM (ablation) | LDAM · CIFAR-100-LT rho=100 | top-1 accuracy: 41.76 -> 41.67 | No clear effect |
| add UniMix to LDAM (ablation) | LDAM · CIFAR-10-LT rho=100 | top-1 accuracy: 74.47 -> 75.35 | Improved |
| use UniMix+Bayias instead of ERM for calibration | ERM · CIFAR-100-LT rho=100 | ECE: 38.23 -> 23.04 | Improved |
Closest papers by meaning
- Decoupling Representation and Classifier for Long-Tailed Recognition (ICLR 2020 · similarity 0.89)
- Decoupled Optimisation for Long-Tailed Visual Recognition (AAAI 2024 · similarity 0.89)
- Deep Long-Tailed Learning: A Survey (TPAMI 2023 · similarity 0.89)
- Global and Local Mixture Consistency Cumulative Learning for Long-Tailed Visual Recognitions (CVPR 2023 · similarity 0.89)
- Robust Visual Recognition with Class-Imbalanced Open-World Noisy Data (AAAI 2024 · similarity 0.87)
- Long-tailed Recognition with Model Rebalancing (NeurIPS 2025 · similarity 0.87)
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.
