Research map / Vision-language and multimodal / Cross-modal learning
Intra-class Distribution-guided Generative Hashing with Neighbor Refinement for Cross-modal Retrieval
Hao Sun, Yadong Huo, Qibing Qin, Wenfeng Zhang, Lei Huang
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 DAG sample generation (ablation) | IDGH baseline · XMediaNet I->T (16 bits) | mAP: 0.1662 -> 0.3928 | Improved |
| add NDR neighbor refinement on top of DAG (ablation) | IDGH · XMediaNet I->T (16 bits) | mAP: 0.3928 -> 0.4046 | Improved |
| add NDR neighbor refinement on top of DAG (ablation) | IDGH · NUS-WIDE I->T (128 bits) | mAP: 0.7470 -> 0.7565 | Improved |
| add NDR neighbor refinement on top of DAG (ablation) | IDGH · MIRFLICKR-25K I->T (16 bits) | mAP: 0.8434 -> 0.8392 | Hurt |
| add IDGH to contrastive loss | Contrastive loss · MIRFLICKR-25K I->T (16 bits) | mAP: 0.7414 -> 0.7581 | Improved |
| add IDGH to triplet loss | Triplet loss · MIRFLICKR-25K I->T (16 bits) | mAP: 0.8233 -> 0.8392 | Improved |
| add IDGH to multi-similarity loss | Multi-similarity loss · MIRFLICKR-25K I->T (16 bits) | mAP: 0.7791 -> 0.7991 | Improved |
| add IDGH to proxy-NCA loss | Proxy-NCA loss · MIRFLICKR-25K I->T (16 bits) | mAP: 0.7644 -> 0.8022 | Improved |
| use IDGH generation instead of Mixup | IDGH · MIRFLICKR-25K T->I (128 bits) | mAP: 0.8340 -> 0.8411 | Improved |
| use IDGH generation instead of HashGAN | IDGH · MIRFLICKR-25K I->T (16 bits) | mAP: 0.8309 -> 0.8392 | Improved |
| increase number of synthetic samples M beyond 10 (ablation) | IDGH · IAPR TC-12 (128 bits) | mAP | Hurt |
| increase number of neighbor classes K (ablation) | IDGH · IAPR TC-12 (128 bits) | mAP | Improved |
Closest papers by meaning
- Distribution-Consistency-Guided Multi-modal Hashing (AAAI 2025 · similarity 0.86)
- Robust Self-Paced Hashing for Cross-Modal Retrieval with Noisy Labels (AAAI 2025 · similarity 0.86)
- Dual Self-Paced Cross-Modal Hashing (AAAI 2024 · similarity 0.85)
- PromptHash:Affinity-Prompted Collaborative Cross-Modal Learning for Adaptive Hashing Retrieval (CVPR 2025 · similarity 0.85)
- Lightweight Contrastive Distilled Hashing for Online Cross-modal Retrieval (AAAI 2025 · similarity 0.85)
- Deep Evidential Hashing for Trustworthy Cross-Modal Retrieval (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.
