Research map / Vision-language and multimodal / Cross-modal learning
Online Cross-Modal Hashing with Expanding Label Space
Wentao Fan, Chao Zhang, Chunlin Chen, Huaxiong Li
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 cross-chunk anchor-code replay (sample-level similarity) (ablation) | OH-ELS · MIRFlickr-25K and NUS-WIDE | mAP | Improved |
| add classifier consistency regularizer (ablation) | OH-ELS · MIRFlickr-25K and NUS-WIDE | mAP | Improved |
| add both knowledge-transfer terms to base model (ablation) | OH-ELS · MIRFlickr-25K and NUS-WIDE | mAP | Improved |
| increase lambda (similarity preservation weight) (ablation) | OH-ELS · MIRFlickr-25K and NUS-WIDE | mAP | Hurt |
| vary alpha (consistency regularization weight) (ablation) | OH-ELS · MIRFlickr-25K and NUS-WIDE | mAP | No clear effect |
| use OH-ELS instead of DOCH (discrete, fixed label space) for class-incremental retrieval | online cross-modal hashing · MIRFlickr-25K I2T 32 bits | avg mAP: 0.7301 -> 0.8361 | Improved |
| use OH-ELS instead of DOCH | online cross-modal hashing · MIRFlickr-25K 16 bits | training time round 7 (s): 3.09 -> 1.97 | Improved |
Closest papers by meaning
- Lightweight Contrastive Distilled Hashing for Online Cross-modal Retrieval (AAAI 2025 · similarity 0.90)
- Semi-Supervised Online Cross-Modal Hashing (AAAI 2025 · similarity 0.90)
- Robust Self-Paced Hashing for Cross-Modal Retrieval with Noisy Labels (AAAI 2025 · similarity 0.89)
- Dual Self-Paced Cross-Modal Hashing (AAAI 2024 · similarity 0.89)
- Asymmetric Cross-Modal Hashing Based on Formal Concept Analysis (AAAI 2025 · similarity 0.89)
- Distribution-Consistency-Guided Multi-modal Hashing (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.
