Research map / Label-efficient and robust learning / Semi-supervised learning
Mitigating Confidence Miscalibration in Open-World Semi-Supervised Learning
Wenqiang Wu, Feng Wang, Jiye Liang, Liang Bai
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.
Addresses confidence miscalibration in open-world semi-supervised learning, where models over-rely on known classes and are overconfident on wrong predictions for unlabeled data containing novel classes.
Problem
Open-world semi-supervised learning must classify unlabeled samples containing both known and novel classes using limited labels for known classes; existing methods over-rely on known classes, producing poor pseudo-labels and overconfident wrong predictions.
Approach
Abstract is truncated; the proposed method (marked by an asterisk) is intended to mitigate confidence miscalibration. Specific mechanism not stated in the available text.
Limitations
- Only the truncated abstract was available; method details and results are unknown.
Closest papers by meaning
- OwMatch: Conditional Self-Labeling with Consistency for Open-World Semi-Supervised Learning (NeurIPS 2024 · similarity 0.88)
- Targeted Representation Alignment for Open-World Semi-Supervised Learning (CVPR 2024 · similarity 0.87)
- Rethinking Confidence Scores and Thresholds in Pseudolabeling-based SSL (ICML 2025 · similarity 0.87)
- Mind the Gap: Confidence Discrepancy Can Guide Federated Semi-Supervised Learning Across Pseudo-Mismatch (CVPR 2025 · similarity 0.87)
- Learning with Open-world Noisy Data via Class-independent Margin in Dual Representation Space (AAAI 2025 · similarity 0.87)
- Contrastive Credibility Propagation for Reliable Semi-supervised Learning (AAAI 2024 · 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.
