Research map / Label-efficient and robust learning / Noisy labels
Learning with Admissibility: Robust Fuzzy Hashing for Cross-Modal Retrieval with Noisy Labels
Xincheng Sun, Ruitao Pu, Guangsi Shi, Zhenwen Ren, Peng Hu, Yuan Sun
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 |
|---|---|---|---|
| add warm-up stage (ablation) | RFCMH · XMedia noise 0.6 | summed mAP: 355.7 -> 359.3 | Improved |
| add warm-up stage (ablation) | RFCMH · INRIA-Websearch noise 0.6 | summed mAP: 187.1 -> 201.0 | Improved |
| add L_FAR (fuzzy admissibility supervision) (ablation) | RFCMH · INRIA-Websearch noise 0.6 | summed mAP: 168.0 -> 201.0 | Improved |
| add L_FAR (ablation) | RFCMH · XMediaNet noise 0.6 | summed mAP: 184.1 -> 196.8 | Improved |
| add DGSA (ablation) | RFCMH · XMediaNet noise 0.6 | summed mAP: 37.9 -> 196.8 | Improved |
| add DGSA (ablation) | RFCMH · XMedia noise 0.6 | summed mAP: 195.4 -> 359.3 | Improved |
| add necessity measure in FAR (ablation) | RFCMH · XMediaNet noise 0.6 | summed mAP: 194.8 -> 196.8 | Improved |
| add necessity measure in FAR (ablation) | RFCMH · XMedia noise 0.6 | summed mAP: 355.7 -> 359.3 | No clear effect |
| add FAR under clean labels (ablation) | RFCMH · INRIA-Websearch I2T, 128 bits, clean | mAP: 49.5 -> 55.8 | Improved |
| add DGSA under clean labels (ablation) | RFCMH · XMediaNet I2T, 16 bits, clean | mAP: 0.9 -> 43.7 | Improved |
| increase alpha beyond about 0.1 (ablation) | RFCMH · INRIA-Websearch 128 bits | mAP | Hurt |
| use sample selection (hard separation) baseline instead of fuzzy supervision | NRCH · XMediaNet (200 classes), noise 0.6 | I2T mAP at 128 bits: 54.2 (RFCMH) vs 19.7 (NRCH) | Hurt |
Closest papers by meaning
- Ambiguity-Tolerant Cross-Modal Hashing with Partial Labels (AAAI 2026 · similarity 0.92)
- Robust Self-Paced Hashing for Cross-Modal Retrieval with Noisy Labels (AAAI 2025 · similarity 0.92)
- Distribution-Consistency-Guided Multi-modal Hashing (AAAI 2025 · similarity 0.90)
- Dual Self-Paced Cross-Modal Hashing (AAAI 2024 · similarity 0.90)
- Exploiting Descriptive Completeness Prior for Cross Modal Hashing with Incomplete Labels (NeurIPS 2024 · similarity 0.90)
- Deep Evidential Hashing for Trustworthy Cross-Modal Retrieval (AAAI 2025 · similarity 0.88)
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.
