Research map / Label-efficient and robust learning / Recognition and long-tail
Learning With Incomplete Labels
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 outlier detection to ICVL (ablation) | ICVL · Enron | F1: 0.2373 -> 0.2805 | Helped |
| add outlier detection to ICVL (ablation) | ICVL · Bookmarks | F1: 0.2251 -> 0.2323 | Helped |
| add outlier detection to ICVL (ablation) | ICVL · Birds | F1: 0.2845 -> 0.3462 | Helped |
| add outlier detection to FastTag (ablation) | FastTag · Enron | F1: 0.2313 -> 0.2487 | Helped |
| add outlier detection to FastTag (ablation) | FastTag · Bookmarks | F1: 0.2084 -> 0.2214 | Helped |
| add outlier detection to FastTag (ablation) | FastTag · Birds | F1: 0.2704 -> 0.2980 | Helped |
| add local label correlations on top of global dependency (ICVL vs FastTag) (ablation) | FastTag · Enron | F1: 0.2313 -> 0.2373 | Mixed |
| add local label correlations (ICVL vs FastTag) (ablation) | FastTag · Birds | F1: 0.2704 -> 0.2845 | Helped |
| add local label correlations (ICVL vs FastTag) (ablation) | FastTag · Bookmarks | F1: 0.2084 -> 0.2251 | Helped |
| ICVL-OD vs best competing model on Birds | ICVL-OD · Birds | F1: 0.2980 -> 0.3462 | Helped |
| replace LeastSquare with ICVL-OD | LeastSquare · Enron | F1: 0.2263 -> 0.2805 | Helped |
| increase ratio of observed labels from small to full | ICVL-OD · Enron/Birds | F1 | Helped |
Closest papers by meaning
- Learning with Partial-Label and Unlabeled Data: A Uniform Treatment for Supervision Redundancy and Insufficiency (ICML 2024 · similarity 0.85)
- A Two-Stage Information Extraction Network for Incomplete Multi-View Multi-Label Classification (AAAI 2024 · similarity 0.84)
- Multi-Instance Multi-Label Classification from Crowdsourced Labels (AAAI 2025 · similarity 0.84)
- Incomplete Multi-View Multi-Label Classification via Diffusion-Guided Redundancy Removal (AAAI 2025 · similarity 0.84)
- Incomplete Multi-View Multi-label Learning via Disentangled Representation and Label Semantic Embedding (CVPR 2025 · similarity 0.84)
- Partial Label Learning with a Partner (AAAI 2024 · similarity 0.83)
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.