Research map / Label-efficient and robust learning / Recognition and long-tail
Dual Set Multi-Label Learning
Chong Liu, Peng Zhao, Sheng-Jun Huang, Yuan Jiang, Zhi-Hua Zhou
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 DSML (boosting with model reuse and distribution adjusting) instead of independent decomposition | RBF-network base classifiers · Calligrapher-Font | Accuracy_all: .4836 -> .5672 | Improved |
| add distribution adjusting (B=1.05 vs 1.00) (ablation) | DSML · Calligrapher-Font | Accuracy_all: .5656 -> .5672 | No clear effect |
| add distribution adjusting (B=1.05 vs 1.00) (ablation) | DSML · Brand-Type | Accuracy_all: .4905 -> .4949 | Improved |
| add distribution adjusting (B=1.05 vs 1.00) (ablation) | DSML · Frequency-Gender | Accuracy_all: .8131 -> .8220 | Improved |
| increase B beyond 1.05-1.10 (ablation) | DSML · all datasets | Accuracy_all | No clear effect |
| add model-reuse mechanism (ablation) | DSML · Calligrapher-Font, Brand-Type, Frequency-Gender | accuracy | Improved |
| use DSML instead of Label Stacking on first label set | DSML · Brand-Type | Accuracy_a: .5968 -> .5723 | Hurt |
| use DSML instead of ML-RBF on second label set | DSML · Frequency-Gender | Accuracy_b: .9661 -> .9547 | Hurt |
Closest papers by meaning
- Dual Relation Semi-Supervised Multi-Label Learning (AAAI 2020 · similarity 0.88)
- Multi-Label Learning From Single Positive Labels (CVPR 2021 · similarity 0.87)
- DualCoOp++: Fast and Effective Adaptation to Multi-Label Recognition With Limited Annotations (TPAMI 2023 · similarity 0.87)
- Multi-Label Open Set Recognition (NeurIPS 2024 · similarity 0.86)
- Double-Layer Hybrid-Label Identification Feature Selection for Multi-View Multi-Label Learning (AAAI 2024 · similarity 0.85)
- Addressing Multi-Label Learning with Partial Labels: From Sample Selection to Label Selection (AAAI 2025 · similarity 0.85)
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.
