Research map / Label-efficient and robust learning / Recognition and long-tail
Distribution-Balanced Loss for Multi-Label Classification in Long-Tailed Datasets
Tong Wu, Qingqiu Huang, Ziwei Liu, Yu Wang, Dahua Lin
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 re-balanced weighting to class-aware re-sampling BCE (ablation) | BCE with re-sampling · VOC-MLT | total mAP: 75.38 -> 76.34 | Improved |
| add re-balanced weighting to class-aware re-sampling BCE (ablation) | BCE with re-sampling · COCO-MLT | total mAP: 46.97 -> 49.43 | Improved |
| add negative-tolerant regularization to R-BCE (ablation) | R-BCE · VOC-MLT | total mAP: 76.34 -> 78.65 | Improved |
| add negative-tolerant regularization to R-BCE (ablation) | R-BCE · COCO-MLT | total mAP: 49.43 -> 52.53 | Improved |
| add focal loss to DB loss (ablation) | DB · VOC-MLT | total mAP: 78.65 -> 78.94 | Improved |
| add focal loss to DB loss (ablation) | DB · COCO-MLT | total mAP: 52.53 -> 53.55 | Improved |
| add focal loss to re-sampling (ablation) | RS · COCO-MLT | total mAP: 46.97 -> 51.14 | Improved |
| add re-balanced weighting to RS-Focal (ablation) | RS-Focal · VOC-MLT | medium-class mAP: drop 0.3% for medium classes | Hurt |
| add class-aware re-sampling to ERM | ERM · COCO-MLT | head-class mAP: drops by about 0.9% | Hurt |
| add class-level re-weighting (RW) on top of re-sampling with focal loss | RS-Focal · VOC-MLT | total mAP: 76.45 -> 71.96 | Hurt |
| add class-balanced re-weighting on top of re-sampling with focal loss | RS-Focal · COCO-MLT | total mAP: 51.14 -> 50.07 | Hurt |
| use re-balanced weighting instead of traditional re-weighting with re-sampling and focal loss | RS-Focal · COCO-MLT | total mAP: 50.07 -> 52.75 | Improved |
Closest papers by meaning
- Semi-supervised Multi-label Learning with Balanced Binary Angular Margin Loss (NeurIPS 2024 · similarity 0.88)
- Multi-Label Learning with Stronger Consistency Guarantees (NeurIPS 2024 · similarity 0.88)
- Long-tailed Recognition with Model Rebalancing (NeurIPS 2025 · similarity 0.88)
- Difficulty-aware Balancing Margin Loss for Long-tailed Recognition (AAAI 2025 · similarity 0.88)
- MLC-NC: Long-Tailed Multi-Label Image Classification Through the Lens of Neural Collapse (AAAI 2025 · similarity 0.88)
- Exploring Weight Balancing on Long-Tailed Recognition Problem (ICLR 2024 · 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.
