Research map / Label-efficient and robust learning / Noisy labels
Prototype-Anchored Learning for Learning with Imperfect Annotations
Xiong Zhou, Xianming Liu, Deming Zhai, Junjun Jiang, Xin Gao, Xiangyang Ji
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 |
|---|---|---|---|
| Embedding PAL into CE and MiSLAS for imbalanced learning (authors state PAL can be embedded in any method where linear classifier and feature extractor are dynamically updated) | CE and MiSLAS imbalanced learning · long-tailed classification (imbalance ratios 100, 50, 10) | accuracy | No clear effect |
| Applying PAL in the second (classifier fine-tuning) stage of MiSLAS | MiSLAS · long-tailed classification | accuracy | No clear effect |
| Normalizing the classifier weights and features with a fixed temperature s=10 in the noise-tolerant loss (FNPAL) instead of noise-rate-dependent s | NCE+RCE+FNPAL and NFL+RCE+FNPAL · noisy label learning | accuracy | Improved |
Closest papers by meaning
- Let the Prototype Guide You: Robust Aggregation of Sparse Multi-Class Annotations via Annotator Prototype Learning (ICML 2026 · similarity 0.86)
- Beyond Prototypes: Semantic Anchor Regularization for Better Representation Learning (AAAI 2024 · similarity 0.86)
- Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss (NeurIPS 2019 · similarity 0.85)
- Balancing the Scales: A Theoretical and Algorithmic Framework for Learning from Imbalanced Data (ICML 2025 · similarity 0.85)
- A Robust Prototype-Based Network with Interpretable RBF Classifier Foundations (AAAI 2025 · similarity 0.84)
- Difficulty-aware Balancing Margin Loss for Long-tailed Recognition (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.
