Research map / Label-efficient and robust learning / Recognition and long-tail
Learning to Reject Meets Long-tail Learning
Harikrishna Narasimhan, Aditya Krishna Menon, Wittawat Jitkrittum, Neha Gupta, Sanjiv Kumar
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Studies learning to reject under long-tail label imbalance, targeting balanced and worst-group error rather than standard misclassification error.
Problem
Learning to reject (abstaining on low-confidence samples) has mostly minimized standard misclassification error, which is inadequate when label distributions are highly imbalanced and fairness-oriented metrics such as balanced error or worst-group error are needed.
Approach
Connects learning to reject with long-tail learning by optimizing abstention under balanced and worst-group error objectives instead of standard misclassification error. Full method details are not available from the abstract.
Experimental setup
Metrics: balanced error worst-group error
Closest papers by meaning
- Rethinking the Value of Labels for Improving Class-Imbalanced Learning (NeurIPS 2020 · similarity 0.87)
- Don’t Label Twice: Quantity Beats Quality when Comparing Binary Classifiers on a Budget (ICML 2024 · similarity 0.86)
- Long-Tailed Partial Label Learning by Head Classifier and Tail Classifier Cooperation (AAAI 2024 · similarity 0.86)
- Decoupled Optimisation for Long-Tailed Visual Recognition (AAAI 2024 · similarity 0.85)
- Improving Generalization via Meta-Learning on Hard Samples (CVPR 2024 · similarity 0.85)
- Rejection via Learning Density Ratios (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.
