Research map / Label-efficient and robust learning / Recognition and long-tail
Codebook-Centric Deep Hashing: End-to-End Joint Learning of Semantic Hash Centers and Neural Hash Function
Shuo Yin, Zhiyuan Yin, Yuqing Hou, Rui Liu, Yong Chen, Dell Zhang
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 dynamic center reassignment (CRH-U to CRH-M) (ablation) | CRH · Stanford Cars / NABirds / MS COCO | mAP: NABirds 64-bit 74.51 -> 75.94 | Improved |
| add multi-head codebook (CRH-M to CRH) (ablation) | CRH · Stanford Cars / NABirds / MS COCO | mAP: NABirds 64-bit 75.94 -> 77.71 | Improved |
| add reassignment to CSQ, MDS, OrthoHash (ablation) | CSQ/MDS/OrthoHash · Stanford Cars / NABirds / MS COCO | mAP: CSQ Cars 16-bit 79.13 -> 85.25 | Improved |
| use greedy instead of Hungarian reassignment (ablation) | CRH · Stanford Cars / NABirds / MS COCO | mAP: NABirds 16-bit 73.45 -> 74.09 | Improved |
| disable center updates (interval infinity) (ablation) | CRH · MS COCO / Stanford Cars / NABirds | mAP | Hurt |
| larger codebook (M=2C vs M=C) (ablation) | CRH · Stanford Cars / NABirds / MS COCO | mAP | Improved |
| head dimension too small causing collisions (ablation) | CRH · Stanford Cars / NABirds / MS COCO | mAP | Hurt |
| CRH vs best baselines | CRH · MS COCO 64-bit | mAP@5K: 87.07 -> 87.44 vs OrthoHash | Mixed |
| vary random initialization/seed (ablation) | CRH · all three datasets | mAP: e.g. 87.46 ± 0.11 vs 87.35 ± 0.03 | No clear effect |
Closest papers by meaning
- Unsupervised Deep Hashing with Similarity-Adaptive and Discrete Optimization (TPAMI 2018 · similarity 0.89)
- Deep Hashing With Minimal-Distance-Separated Hash Centers (CVPR 2023 · similarity 0.89)
- Supervised Learning of Semantics-Preserving Hash via Deep Convolutional Neural Networks (TPAMI 2017 · similarity 0.89)
- One Loss for All: Deep Hashing with a Single Cosine Similarity based Learning Objective (NeurIPS 2021 · similarity 0.89)
- Pairwise-Label-Based Deep Incremental Hashing with Simultaneous Code Expansion (AAAI 2024 · similarity 0.88)
- KALAHash: Knowledge-Anchored Low-Resource Adaptation for Deep 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.
