Research map / Label-efficient and robust learning / Recognition and long-tail
Uncertainty-Aware Hierarchical Refinement for Incremental Implicitly-Refined Classification
Jian Yang, Kai Zhu, Kecheng Zheng, Yang Cao
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 hierarchical distribution alignment (HDA) to the baseline (ablation) | UAHR baseline · IIRC-CIFAR config 0, phase 21 | PW-JS: 17.78 -> 18.38 | Improved |
| add global representation extension (GRE) to the baseline (ablation) | UAHR baseline · IIRC-CIFAR config 0, phase 21 | PW-JS: 17.78 -> 18.32 | Improved |
| add both GRE and HDA (ablation) | UAHR baseline · IIRC-CIFAR config 0, phase 21 | PW-JS: 17.78 -> 19.05 | Improved |
| add HDA to the baseline at phase 5 (ablation) | UAHR baseline · IIRC-CIFAR config 0, phase 5 | PW-JS: 26.48 -> 29.31 | Improved |
| add GRE on top of HDA (ablation) | UAHR · IIRC-CIFAR config 0, phase 21 | PW-JS: 18.38 -> 19.05 | Improved |
| add GRE or HDA at phase 0 (initial phase) (ablation) | UAHR · IIRC-CIFAR config 0, phase 0 | PW-JS: 78.35 -> 77.53 | Hurt |
| use hierarchical uncertainty (entropy output + feature std) instead of common entropy uncertainty (ablation) | UAHR · IIRC-CIFAR, phase 5 | PW-JS: 25.70 -> 30.11 | Improved |
| use hierarchical uncertainty instead of common uncertainty (ablation) | UAHR · IIRC-CIFAR, phase 10 | PW-JS: 20.89 -> 25.31 | Improved |
| use hierarchical uncertainty instead of common uncertainty (ablation) | UAHR · IIRC-CIFAR, phase 15 | PW-JS: 19.55 -> 23.56 | Improved |
| use hierarchical uncertainty instead of common uncertainty (ablation) | UAHR · IIRC-CIFAR, phase 21 | PW-JS: 15.32 -> 19.05 | Improved |
Closest papers by meaning
- IIRC: Incremental Implicitly-Refined Classification (CVPR 2021 · similarity 0.87)
- DiAPR: Dimensionally-Allocated Prototype Refinement for Non-Exemplar Class Incremental Learning (AAAI 2026 · similarity 0.86)
- HierUQ: Hierarchical Uncertainty Quantification with Adaptive Granularity Reconciliation for Degraded Image Classification (CVPR 2026 · similarity 0.85)
- Inherit With Distillation and Evolve With Contrast: Exploring Class Incremental Semantic Segmentation Without Exemplar Memory (TPAMI 2023 · similarity 0.85)
- Hierarchical Semantic Tree Anchoring for CLIP-Based Class-Incremental Learning (NeurIPS 2026 · similarity 0.84)
- Adaptive Prototype Replay for Class Incremental Semantic Segmentation (AAAI 2025 · similarity 0.84)
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.
