Research map / Label-efficient and robust learning / Recognition and long-tail
Adaptive Momentum and EMA-weighted Modeling for Imbalanced Label Distribution Learning
Yongbiao Gao, Xiangcheng Sun, Chao Tan, Chunyu Hu, Guohua Lv
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 EMA-based adaptive loss weighting (WEIG) (ablation) | AMEMA · Movie | KL divergence: 0.199 -> 0.192 | Improved |
| add dynamic momentum allocation (MOME) (ablation) | AMEMA · Movie | KL divergence: 0.204 -> 0.192 | Improved |
| add both WEIG and MOME (ablation) | AMEMA · Movie | KL divergence: 0.221 -> 0.192 | Improved |
| add EMA-based adaptive loss weighting (WEIG) (ablation) | AMEMA · Natural Scene | KL divergence: 0.897 -> 0.834 | Improved |
| add dynamic momentum allocation (MOME) (ablation) | AMEMA · Natural Scene | KL divergence: 0.945 -> 0.834 | Improved |
| add both WEIG and MOME (ablation) | AMEMA · Natural Scene | KL divergence: 1.073 -> 0.834 | Improved |
| add WEIG and MOME (ablation) | AMEMA · Movie | Clark distance: 0.768 -> 0.689 | Improved |
| add WEIG and MOME (ablation) | AMEMA · Natural Scene | Cosine: 0.610 -> 0.621 | Improved |
| add adaptive momentum and EMA weighting on top of decoupled DILDL | DILDL · SCUT-FBP | Chebyshev distance: 0.2684 -> 0.2115 | Improved |
| add adaptive momentum and EMA weighting on top of decoupled DILDL | DILDL · Emotion6 | KL divergence: 0.7393 -> 0.6611 | Improved |
| add adaptive momentum and EMA weighting on top of decoupled DILDL | DILDL · RAF-ML | Intersection: 0.5372 -> 0.5488 | Improved |
| add adaptive momentum and EMA weighting on top of decoupled DILDL | DILDL · Natural Scene | Cosine: 0.6103 -> 0.6207 | Improved |
Closest papers by meaning
- Rebalancing Multi-Label Class-Incremental Learning (AAAI 2025 · similarity 0.86)
- Adaptive-Grained Label Distribution Learning (AAAI 2025 · similarity 0.86)
- Toward Robustness in Multi-Label Classification: A Data Augmentation Strategy against Imbalance and Noise (AAAI 2024 · similarity 0.86)
- Semi-supervised Multi-label Learning with Balanced Binary Angular Margin Loss (NeurIPS 2024 · similarity 0.85)
- Predicting Label Distribution from Ternary Labels (NeurIPS 2024 · similarity 0.85)
- Generative Calibration of Inaccurate Annotation for Label Distribution Learning (AAAI 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.
