Research map / Learning theory and algorithms / Clustering
Deep Multi-View Enhancement Hashing for Image Retrieval
Chenggang Clarence Yan, Biao Gong, Yuxuan Wei, Yue Gao
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 the view-relation matrix E with all four views (ablation) | D-MVE-Hash (+R) · CIFAR-10 (64 bits) | mAP: 0.7588 -> 0.8401 | Improved |
| add view-relation matrix E to views 2,3,4 (ablation) | D-MVE-Hash (+R) · CIFAR-10 (64 bits) | mAP: 0.8352 -> 0.8401 | Improved |
| add only view1 without E (ablation) | D-MVE-Hash (+R) · CIFAR-10 (64 bits) | mAP: 0.7588 -> 0.7513 | Hurt |
| add only view4 without E (ablation) | D-MVE-Hash (+R) · CIFAR-10 (64 bits) | mAP: 0.7588 -> 0.7854 | Improved |
| add E to partial views 1,2,3 (ablation) | D-MVE-Hash (+R) · CIFAR-10 (64 bits) | mAP: 0.7699 -> 0.8275 | Improved |
| add multi-view enhancement and E (training cost) (ablation) | D-MVE-Hash (+R) · CIFAR-10 training time | hours: 0.954 -> 1.711 | Hurt |
| use replication fusion instead of probability view pooling | D-MVE-Hash · CIFAR-10 (64 bits) | mAP: 0.7712 -> 0.8401 | Improved |
| use replication fusion instead of view-code fusion | D-MVE-Hash · NUS-WIDE (16 bits) | mAP: 0.6906 -> 0.7883 | Improved |
| add multi-view enhancement to MV-Hash (D-MVE-Hash +R) | MV-Hash · CIFAR-10 (64 bits) | mAP: 0.5370 -> 0.8401 | Improved |
| use D-MVE-Hash instead of DCH | DCH · CIFAR-10 (64 bits) | mAP: 0.7936 -> 0.8401 | Improved |
| use D-MVE-Hash (+R) instead of AGAH | AGAH · NUS-WIDE (64 bits) | mAP: 0.7096 -> 0.8073 | Improved |
Closest papers by meaning
- Deep Supervised Hashing for Fast Image Retrieval (CVPR 2016 · similarity 0.91)
- Deep Hashing Network for Efficient Similarity Retrieval (AAAI 2016 · similarity 0.90)
- Deep Incremental Hashing Network for Efficient Image Retrieval (CVPR 2019 · similarity 0.90)
- Accelerate Learning of Deep Hashing With Gradient Attention (ICCV 2019 · similarity 0.90)
- Deep Graph Online Hashing for Multi-Label Image Retrieval (AAAI 2025 · similarity 0.88)
- Pairwise-Label-Based Deep Incremental Hashing with Simultaneous Code Expansion (AAAI 2024 · similarity 0.87)
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.
