Research map / Label-efficient and robust learning / Semi-supervised learning
Towards Unbiased Learning in Semi-Supervised Semantic Segmentation
Rui Sun, Huayu Mai, Wangkai Li, Tianzhu Zhang
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 class imbalance in semi-supervised semantic segmentation, where biased predictions toward majority classes (Matthew effect) hurt pseudo-label quality, via an unbiased learning approach.
Problem
Semi-supervised semantic segmentation suffers from class imbalance, causing the Matthew effect: poorly calibrated models bias predictions toward majority classes.
Approach
Treats class imbalance in semi-supervised segmentation as the source of a Matthew effect in pseudo-labeling and proposes an unbiased learning framework to counteract the majority-class bias. Details beyond the abstract are not available.
Closest papers by meaning
- DAW: Exploring the Better Weighting Function for Semi-supervised Semantic Segmentation (NeurIPS 2023 · similarity 0.90)
- Unbiased Subclass Regularization for Semi-Supervised Semantic Segmentation (CVPR 2022 · similarity 0.90)
- Re-Distributing Biased Pseudo Labels for Semi-Supervised Semantic Segmentation: A Baseline Investigation (ICCV 2021 · similarity 0.90)
- SemiDAViL: Semi-supervised Domain Adaptation with Vision-Language Guidance for Semantic Segmentation (CVPR 2025 · similarity 0.90)
- Semi-Supervised Semantic Segmentation With Cross-Consistency Training (CVPR 2020 · similarity 0.90)
- Relaxed Class-consensus Consistency for Semi-supervised Semantic Segmentation (AAAI 2025 · similarity 0.88)
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.
