Research map / Label-efficient and robust learning / Semi-supervised learning
ABC: Auxiliary Balanced Classifier for Class-imbalanced Semi-supervised Learning
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| add ABC to ReMixMatch | ReMixMatch · CIFAR-10-LT gamma=100 beta=20% | overall accuracy (%): 73.7 -> 82.4 | Helped |
| add ABC to FixMatch | FixMatch · CIFAR-10-LT gamma=100 beta=20% | overall accuracy (%): 72.3 -> 81.1 | Helped |
| add ABC to ReMixMatch, minority-class accuracy | ReMixMatch · CIFAR-10-LT gamma=100 beta=20% | minority-class accuracy (%): 55.9 -> 75.7 | Helped |
| replace DARP+cRT with ABC | ReMixMatch · CIFAR-10-LT gamma=100 beta=20% | overall accuracy (%): 78.5 -> 82.4 | Helped |
| add ABC on large-scale LSUN | FixMatch · LSUN gamma=100 | overall accuracy (%): 73.1 -> 78.9 | Helped |
| add DARP pseudo-label refinement on LSUN | FixMatch · LSUN gamma=100 | overall accuracy (%): 73.1 -> 71.0 | Hurt |
| add 0/1 mask to classification loss (ablation) | ReMixMatch+ABC · CIFAR-10-LT | overall accuracy (%): 74.4 -> 82.4 | Helped |
| add 0/1 mask to consistency loss (ablation) | ReMixMatch+ABC · CIFAR-10-LT | overall accuracy (%): 79.0 -> 82.4 | Helped |
| add consistency regularization for ABC (ablation) | ReMixMatch+ABC · CIFAR-10-LT | overall accuracy (%): 79.4 -> 82.4 | Helped |
| use soft instead of hard pseudo-labels in consistency regularization (ablation) | ReMixMatch+ABC · CIFAR-10-LT | overall accuracy (%): 70.2 -> 82.4 | Helped |
| add confidence threshold tau (ablation) | ReMixMatch+ABC · CIFAR-10-LT | overall accuracy (%): 74.3 -> 82.4 | Helped |
| train the SSL backbone together with the ABC (ablation) | ABC · CIFAR-10-LT | overall accuracy (%): 68.7 -> 82.4 | Helped |
Closest papers by meaning
- CDMAD: Class-Distribution-Mismatch-Aware Debiasing for Class-Imbalanced Semi-Supervised Learning (CVPR 2024 · similarity 0.90)
- LCGC: Learning from Consistency Gradient Conflicting for Class-Imbalanced Semi-Supervised Debiasing (AAAI 2025 · similarity 0.89)
- BaCon: Boosting Imbalanced Semi-supervised Learning via Balanced Feature-Level Contrastive Learning (AAAI 2024 · similarity 0.88)
- Twice Class Bias Correction for Imbalanced Semi-supervised Learning (AAAI 2024 · similarity 0.88)
- Semi-supervised Multi-label Learning with Balanced Binary Angular Margin Loss (NeurIPS 2024 · similarity 0.88)
- BEM: Balanced and Entropy-based Mix for Long-Tailed Semi-Supervised Learning (CVPR 2024 · 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.