Research map / Label-efficient and robust learning / Recognition and long-tail
Revisiting Pseudo-Label for Single-Positive Multi-Label 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 |
|---|---|---|---|
| Use MIME pseudo-label generation (mutual-information label enhancement) instead of prior SPMLL methods | SPMLL on four MLIC datasets · VOC, COCO, NUS, CUB | mAP: MIME best on all four; e.g. COCO 72.920 vs 70.758 for EM-APL | Helped |
| Use MIME instead of prior SPMLL methods | SPMLL on five MLL datasets · Image, Scene, Yeast, Rcv1subset1, Mediamill | Average precision: Best on Image, Scene, Yeast, Rcv1subset1; on Mediamill AN (0.690) is within noise of MIME (0.694) | Mixed |
| Sensitivity to tradeoff beta, label-specific dim k, and threshold tau (ablation) | MIME · COCO and NUS | mAP: largest gap about 1.9% (beta) and 1.2% (k) | No clear effect |
| Pseudo-label enhancement iterations in MIME (ablation) | MIME pseudo-labels · Image and Scene | mislabeled ratio of pseudo-labels: mislabeled ratio steadily decreases and converges over epochs | Helped |
Closest papers by meaning
- Can Class-Priors Help Single-Positive Multi-Label Learning? (NeurIPS 2025 · similarity 0.91)
- Semi-supervised Multi-label Learning with Balanced Binary Angular Margin Loss (NeurIPS 2024 · similarity 0.87)
- Correlation-Induced Label Prior for Semi-Supervised Multi-Label Learning (ICML 2024 · similarity 0.87)
- Reduction-based Pseudo-label Generation for Instance-dependent Partial Label Learning (NeurIPS 2025 · similarity 0.87)
- Addressing Multi-Label Learning with Partial Labels: From Sample Selection to Label Selection (AAAI 2025 · similarity 0.86)
- 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.