Research map / Label-efficient and robust learning / Recognition and long-tail
Divisiveness-Consistent Label Distribution Learning
Yunan Lu, Haitao Wu, Weiwei Li, Lei Yang, Xiuyi Jia
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 pairwise divisiveness loss to KL loss | LDL-DVS · RAF-ML | DVSE: δ-LDL .0829 -> LDL-DVS .0764 | Improved |
| add pairwise divisiveness loss to KL loss | LDL-DVS · Music | DVSE: δ-LDL .0573 -> LDL-DVS .0571 | No clear effect |
| add pairwise divisiveness loss to KL loss | LDL-DVS · Painting | DVSE: AA-kNN .1416 vs LDL-DVS .1523 | Hurt |
| add pairwise divisiveness loss to KL loss | LDL-DVS · RAF-ML | Clark: 1.4159 -> 1.4210 | Hurt |
| add divisiveness loss term (either direct or pairwise) with moderate alpha (ablation) | KL baseline · M2B | Spearman | Improved |
| use pairwise surrogate instead of directly minimizing divisiveness error at large alpha (ablation) | LDL-DVS · M2B | Spearman | Improved |
| increase alpha too large (up to 1000) (ablation) | LDL-DVS · M2B | KLD | Hurt |
| use alpha in [0.01, 1] (ablation) | LDL-DVS · M2B | KLD | Improved |
| increase smoothness parameter k (ablation) | LDL-DVS · M2B | KLD and DVSE | No clear effect |
| increase k up to 2^8 (ablation) | LDL-DVS · M2B | training stability and time | Hurt |
Closest papers by meaning
- Approximately Correct Label Distribution Learning (ICML 2025 · similarity 0.89)
- Generative Calibration of Inaccurate Annotation for Label Distribution Learning (AAAI 2024 · similarity 0.87)
- Divide and Conquer: Learning Label Distribution with Subtasks (ICML 2025 · similarity 0.87)
- Adaptive-Grained Label Distribution Learning (AAAI 2025 · similarity 0.86)
- Predicting Label Distribution from Ternary Labels (NeurIPS 2024 · similarity 0.86)
- LIMEFLDL: A Local Interpretable Model-Agnostic Explanations Approach for Label Distribution Learning (ICML 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.
