Research map / Label-efficient and robust learning / Recognition and long-tail
Self Supervision to Distillation for Long-Tailed Visual Recognition
Tianhao Li, Limin Wang, Gangshan Wu
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 instance-discrimination self-supervision to feature learning (ablation) | CE baseline · ImageNet-LT | top-1 accuracy: 46.3 -> 48.9 | Improved |
| add self-supervision to teacher training (ablation) | SSD · ImageNet-LT | top-1 accuracy: 54.4 -> 56.0 | Improved |
| add 1.5x training schedule (ablation) | CE · ImageNet-LT | top-1 accuracy: 45.1 -> 46.3 | Improved |
| add 1.5x training schedule (ablation) | LWS · ImageNet-LT | top-1 accuracy: 50.7 -> 52.1 | Improved |
| use soft-label self-distillation student instead of teacher (ablation) | SSD · ImageNet-LT | top-1 accuracy: 54.1 -> 55.7 | Improved |
| use hybrid hard+soft supervision (two classifiers) instead of single soft-only (ablation) | SSD · ImageNet-LT | top-1 accuracy: 55.1 -> 55.7 | Improved |
| use two-classifier hybrid supervision instead of coupled distillation (ablation) | SSD · ImageNet-LT | top-1 accuracy: 53.2 -> 55.7 | Improved |
| fine-tune hard-label student with LWS (stage IV) (ablation) | SSD · ImageNet-LT | top-1 accuracy: 0.3% | Improved |
| add soft-label student to hard-label student (ablation) | SSD · ImageNet-LT | top-1 accuracy: 51.6 -> 55.7 | Improved |
| replace LWS* with SSD (1.5x) | LWS* · ImageNet-LT | top-1 accuracy: 52.1 -> 56.0 | Improved |
| replace LWS* with SSD | LWS* · CIFAR100-LT (imbalance 100) | top-1 accuracy: 42.3 -> 46.0 | Improved |
| replace LWS with SSD | LWS‡* · iNaturalist 2018 (1x) | top-1 accuracy: 66.6 -> 69.3 | Improved |
Closest papers by meaning
- Long-Tailed Multi-Label Visual Recognition by Collaborative Training on Uniform and Re-Balanced Samplings (CVPR 2021 · similarity 0.92)
- Decoupled Contrastive Learning for Long-Tailed Recognition (AAAI 2024 · similarity 0.89)
- Long-tailed Recognition with Model Rebalancing (NeurIPS 2025 · similarity 0.89)
- Feature Fusion from Head to Tail for Long-Tailed Visual Recognition (AAAI 2024 · similarity 0.89)
- DiffuLT: Diffusion for Long-tail Recognition Without External Knowledge (NeurIPS 2024 · similarity 0.89)
- MLC-NC: Long-Tailed Multi-Label Image Classification Through the Lens of Neural Collapse (AAAI 2025 · similarity 0.88)
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.
