Research map / Label-efficient and robust learning / Domain adaptation and generalization
Tackling Long-Tailed Category Distribution under Domain Shifts
Xiao Gu, Yao Guo, Zeju Li, Jianing Qiu, Qi Dou, Yuxuan Liu, Benny Lo, Guang-Zhong Yang
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 |
|---|---|---|---|
| use the full meta-learning method instead of aggregate training (Agg) | ResNet-10 · AWA2-LTS (held-out Original) | Acc-U: 29.4 -> 49.4 | Improved |
| use the full method instead of aggregate training (Agg) | ResNet-10 · ImageNet-LTS (held-out Original) | Acc-U: 19.5 -> 24.3 | Improved |
| use full method instead of the best combination MixStyle+BSCE | ResNet-10 · AWA2-LTS (held-out Original) | Acc-U: 40.0 -> 49.4 | Improved |
| add warm-up pretraining to DAML | DAML · AWA2-LTS (held-out Original) | Acc-U: 13.9 -> 42.2 | Improved |
| add distribution-calibrated loss in place of BSCE (ablation) | long-tail loss · AWA2-LTS / ImageNet-LTS | Acc-U | Improved |
| use domain-specific prototypes for cross-domain alignment instead of a uni-domain prototype (ablation) | visual-semantic mapping · AWA2-LTS | Acc-U | Improved |
| use the n_k weighted term in covariance update (ablation) | augmentation module · AWA2-LTS | Acc-U | Improved |
| change CLIP or GloVe embeddings instead of BERT | Ours · AWA2-LTS | H: 44.6 -> 43.6 (CLIP), 44.5 (GloVe) | No clear effect |
| use Ours instead of Agg at imbalance ratio 10 | ResNet-10 · AWA2-LTS (imbalance ratio 10) | H: 20.7 -> 32.1 | Improved |
| use Ours instead of Agg at imbalance ratio 50 | ResNet-10 · AWA2-LTS (imbalance ratio 50) | H: 32.8 -> 41.0 | Improved |
| use Ours instead of Agg | ResNet-18 pretrained · PACS-ODG (average) | Acc-U: 55.2 -> 67.1 | Improved |
| use Ours instead of DAML | ResNet-18 pretrained · PACS-ODG (average) | H-U: 51.9 -> 56.9 | Improved |
Closest papers by meaning
- Learning from Neighbors: Category Extrapolation for Long-Tail Learning (CVPR 2025 · similarity 0.86)
- Sharpness-Aware Model-Agnostic Long-Tailed Domain Generalization (AAAI 2024 · similarity 0.86)
- Robust Domain Generalization under Divergent Marginal and Conditional Distributions (NeurIPS 2026 · similarity 0.86)
- A Square Peg in a Square Hole: Meta-Expert for Long-Tailed Semi-Supervised Learning (ICML 2025 · similarity 0.85)
- Generalized Category Discovery under Domain Shift: A Frequency Domain Perspective (NeurIPS 2025 · similarity 0.85)
- Breaking Long-Tailed Learning Bottlenecks: A Controllable Paradigm with Hypernetwork-Generated Diverse Experts (NeurIPS 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.
