Research map / Label-efficient and robust learning / Recognition and long-tail
DirMixE: Harnessing Test Agnostic Long-Tail Recognition With Hierarchical Label Vartiations
Zhiyong Yang, Qianqian Xu, Sicong Li, Zitai Wang, Xiaochun Cao, Qingming Huang
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 |
|---|---|---|---|
| replace SADE's fixed-distribution experts with DirMixE Dirichlet-mixture experts | DirMixE · CIFAR-100-LT mean over 9 test distributions | accuracy (%): 51.77 -> 53.34 | Improved |
| replace BalPoE with DirMixE | DirMixE · CIFAR-100-LT Backward-LT test set 1 | accuracy (%): 29.80 -> 44.41 | Improved |
| replace BalPoE with DirMixE | DirMixE · CIFAR-100-LT Forward-LT test set 1 | accuracy (%): 67.75 -> 66.85 | Hurt |
| replace SADE with DirMixE | DirMixE · CIFAR-100-LT Backward-LT test set 2 | accuracy (%): 42.91 -> 47.01 | Improved |
| replace SADE with DirMixE | DirMixE · CIFAR-100-LT Uniform test set 3 | accuracy (%): 45.59 -> 44.21 | Hurt |
| replace SADE with DirMixE | DirMixE · CIFAR-100-LT std across test distributions | std of accuracy: 10.90 -> 10.22 | Improved |
Later papers that compared with this method
1 later accepted paper reports DirMixE as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- IDOL: Meeting Diverse Distribution Shifts with Prior Physics for Tropical Cyclone Multi-Task Estimation (NeurIPS 2025 · better on 1 of 1 shared result)
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Harnessing Hierarchical Label Distribution Variations in Test Agnostic Long-tail Recognition (ICML 2024 · similarity 0.98)
- Learning Label Shift Correction for Test-Agnostic Long-Tailed Recognition (ICML 2024 · similarity 0.90)
- DiffuLT: Diffusion for Long-tail Recognition Without External Knowledge (NeurIPS 2024 · similarity 0.88)
- Continuous Contrastive Learning for Long-Tailed Semi-Supervised Recognition (NeurIPS 2024 · similarity 0.87)
- Long-tailed Recognition with Model Rebalancing (NeurIPS 2025 · similarity 0.86)
- Rectifying Soft-Label Entangled Bias in Long-Tailed Dataset Distillation (NeurIPS 2025 · 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.
