Research map / Label-efficient and robust learning / Semi-supervised learning
Imbalanced Semi-supervised Learning with Bias Adaptive Classifier
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 L2AC's bias adaptive classifier and bi-level learning to FixMatch | FixMatch · CIFAR-10, γ=100 (labeled and unlabeled) | bACC: 71.5_{\pm0.72} -> 82.1_{\pm0.57} | Helped |
| Add L2AC's bias adaptive classifier and bi-level learning to FixMatch | FixMatch · CIFAR-10, γ=100 (labeled and unlabeled) | GM: 66.8_{\pm1.51} -> 81.5_{\pm0.64} | Helped |
| Add L2AC's bias adaptive classifier and bi-level learning to FixMatch | FixMatch · CIFAR-10, γ_l=100, γ_u=100 (reversed) | bACC: 65.5_{\pm0.05} -> 82.2_{\pm1.23} | Helped |
| Add L2AC's bias adaptive classifier and bi-level learning to FixMatch | FixMatch · CIFAR-10, γ_l=100, γ_u=100 (reversed) | GM: 26.0_{\pm0.44} -> 81.7_{\pm1.36} | Helped |
| Add L2AC's bias adaptive classifier and bi-level learning to FixMatch | FixMatch · STL-10, γ_l=10 | bACC: 69.6_{\pm0.60} -> 79.9_{\pm0.52} | Helped |
| Add L2AC's bias adaptive classifier and bi-level learning to FixMatch | FixMatch · STL-10, γ_l=10 | GM: 62.6_{\pm1.11} -> 79.1_{\pm0.49} | Helped |
| Add the bias attractor without bi-level optimization (ablation) | FixMatch · CIFAR-10, γ_l=γ_u=100 | performance | Helped |
| Replace bi-level optimization with single-level loss L + λL_bal (ablation) | FixMatch with bias attractor · CIFAR-10, γ_l=γ_u=100 and γ_l=100, γ_u=100 reversed | performance | Hurt |
Closest papers by meaning
- Twice Class Bias Correction for Imbalanced Semi-supervised Learning (AAAI 2024 · similarity 0.89)
- CDMAD: Class-Distribution-Mismatch-Aware Debiasing for Class-Imbalanced Semi-Supervised Learning (CVPR 2024 · similarity 0.89)
- 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)
- Semi-supervised Multi-label Learning with Balanced Binary Angular Margin Loss (NeurIPS 2024 · similarity 0.87)
- Bi-Level Optimization for Semi-Supervised Learning with Pseudo-Labeling (AAAI 2025 · 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.