Research map / Label-efficient and robust learning / Recognition and long-tail
HGLTR: Hierarchical Knowledge Injection for Calibrating Pre-trained Models in Long-Tail Recognition
Jinpeng Zheng, Shao-Yuan Li, Gan Xu, Wenhai Wan, Zijian Tao, Songcan Chen, Kangkan Wang
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 Ldis (hierarchical distillation) to Lmse (ablation) | HGLTR · ImageNet-LT | tail accuracy: 68.5 -> 72.1 | Improved |
| add Lmse (feature alignment) to Ldis (ablation) | HGLTR · ImageNet-LT | tail accuracy: 69.5 -> 72.1 | Improved |
| add both hierarchical losses (ablation) | HGLTR · ImageNet-LT | overall accuracy: 76.3 -> 77.4 (Lmse only -> both) | Improved |
| use Adapter instead of LoRA/VPT (ablation) | HGLTR · ImageNet-LT | overall accuracy: 75.7 -> 77.4 (LoRA -> Adapter) | Improved |
| HGLTR vs BALLAD with fewer params | CLIP ViT-B/16 · ImageNet-LT | overall accuracy: 75.7 -> 77.4 | Improved |
| HGLTR vs GML using extra data | CLIP ViT-B/16 · ImageNet-LT | overall accuracy: 78.0 vs 77.4 | Hurt |
| HGLTR vs LPT on iNaturalist tail | CLIP ViT-B/16 · iNaturalist 2018 | tail accuracy: 79.3 vs 78.8 | Hurt |
| HGLTR on Places-LT | CLIP ViT-B/16 · Places-LT | overall accuracy: 50.1 -> 51.4 (vs LPT/GNM-PT) | Improved |
| vary alpha (feature loss weight) (ablation) | HGLTR · ImageNet-LT | overall accuracy | No clear effect |
| vary beta (distillation weight) (ablation) | HGLTR · ImageNet-LT | overall accuracy | Mixed |
Closest papers by meaning
- Feature Fusion from Head to Tail for Long-Tailed Visual Recognition (AAAI 2024 · similarity 0.87)
- Large-Scale Long-Tailed Recognition in an Open World (CVPR 2019 · similarity 0.87)
- Adaptive Hierarchical Representation Learning for Long-Tailed Object Detection (CVPR 2022 · similarity 0.86)
- DiffuLT: Diffusion for Long-tail Recognition Without External Knowledge (NeurIPS 2024 · similarity 0.86)
- Semantic-Guided Fine-Tuning of Foundation Model for Long-Tailed Visual Recognition (IJCV 2026 · similarity 0.86)
- Learning Structured Representations with Hyperbolic Embeddings (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.
