Research map / Label-efficient and robust learning / Semi-supervised learning
Rebalancing Using Estimated Class Distribution for Imbalanced Semi-Supervised Learning under Class Distribution Mismatch
Taemin Park, Hyuck Lee, Heeyoung Kim
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 |
|---|---|---|---|
| replace ABC's labeled-distribution-based mask with RECD's estimated unlabeled class distribution | ReMixMatch+ABC · CIFAR-10-LT (gamma_l = 100, gamma_u = 1) | bACC: 76.4 -> 90.3 | Improved |
| replace ABC's mask with RECD estimated class distribution (FixMatch) | FixMatch+ABC · CIFAR-10-LT (gamma_l = 100, gamma_u = 1) | bACC: 82.7 -> 90.2 | Improved |
| add RECD under matched class distributions | FixMatch+ABC · CIFAR-10-LT (gamma = 100) | bACC: 81.1 -> 84.0 | Improved |
| add RECD under matched class distributions with ReMixMatch backbone | ReMixMatch+ABC · CIFAR-10-LT (gamma = 100) | bACC: 84.5 -> 85.4 | No clear effect |
| add logit adjustment (LA) to SAW under severe class distribution mismatch | ReMixMatch*+SAW · CIFAR-10-LT (gamma_l = 100, gamma_u = 1) | bACC: 87.0 -> 74.2 | Hurt |
| add adaptively adjusted feature multiplier (AAFM) to RECD (ablation) | FixMatch+RECD · CIFAR-10-LT (gamma_l = 100, gamma_u = 1) | minority-class test loss | Improved |
| estimate unlabeled class distribution with EMA of predictions in RECD | RECD · CIFAR-10-LT (gamma_l = 100, gamma_u = 1) | estimated versus true class distribution | Improved |
Closest papers by meaning
- CDMAD: Class-Distribution-Mismatch-Aware Debiasing for Class-Imbalanced Semi-Supervised Learning (CVPR 2024 · similarity 0.90)
- Twice Class Bias Correction for Imbalanced Semi-supervised Learning (AAAI 2024 · similarity 0.89)
- Balancing the Scales: A Theoretical and Algorithmic Framework for Learning from Imbalanced Data (ICML 2025 · similarity 0.88)
- LCGC: Learning from Consistency Gradient Conflicting for Class-Imbalanced Semi-Supervised Debiasing (AAAI 2025 · similarity 0.88)
- BaCon: Boosting Imbalanced Semi-supervised Learning via Balanced Feature-Level Contrastive Learning (AAAI 2024 · similarity 0.87)
- Learning under Localized Minority Imbalance (NeurIPS 2026 · similarity 0.87)
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.
