Research map / Label-efficient and robust learning / Semi-supervised learning
Distribution Aligning Refinery of Pseudo-label for 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 distribution-aligning pseudo-label refinement to MixMatch | MixMatch · CIFAR-10, γ_l=100, γ_u=1 | bACC: 41.5\ms{0.76} -> 86.7\ms{0.80} | Helped |
| Add distribution-aligning pseudo-label refinement to ReMixMatch | ReMixMatch · CIFAR-10, γ_l=100, γ_u=100 reversed | bACC: 75.3\ms{0.03} -> 80.1\ms{0.11} | Helped |
| Add distribution-aligning pseudo-label refinement to ReMixMatch | ReMixMatch · STL-10, γ_l=10 | GM: 61.1\ms{0.92} -> 78.2\ms{0.10} | Helped |
| Add distribution-aligning pseudo-label refinement to FixMatch | FixMatch · CIFAR-100, γ_l=γ_u=20 | GM: 44.4\ms{0.17} -> 46.4\ms{0.41} | Helped |
| Add distribution-aligning pseudo-label refinement to FixMatch | FixMatch · SUN-397, γ≈46 | GM: 35.7\ms{0.66} -> 37.5\ms{0.04} | Helped |
| Combine DARP with classifier re-training | ReMixMatch + cRT · CIFAR-10, γ=γ_l=γ_u=100 | bACC: 81.4\ms{0.41} -> 83.5\ms{0.07} | Helped |
| Use DARP rather than the compared distribution-matching procedures | ReMixMatch · CIFAR-10, γ_l=100, γ_u=1 | bACC: 85.0 -> 89.7 | Helped |
Closest papers by meaning
- DASO: Distribution-Aware Semantics-Oriented Pseudo-Label for Imbalanced Semi-Supervised Learning (CVPR 2022 · similarity 0.92)
- Class-Imbalanced Semi-Supervised Learning with Adaptive Thresholding (ICML 2022 · similarity 0.91)
- CDMAD: Class-Distribution-Mismatch-Aware Debiasing for Class-Imbalanced Semi-Supervised Learning (CVPR 2024 · similarity 0.90)
- Semi-supervised Multi-label Learning with Balanced Binary Angular Margin Loss (NeurIPS 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)
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.