Research map / Learning theory and algorithms / Combinatorial and search optimization
Greedy Hash: Towards Fast Optimization for Accurate Hash Coding in CNN
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Greedy Hash (sign forward, straight-through backward) vs DSDH | deep supervised hashing · CIFAR-10 (I), 12 bits | MAP: 0.740 -> 0.774 | Helped |
| Greedy Hash vs HashNet at short codes | deep hashing · ImageNet, 16 bits | MAP@1000: 0.506 -> 0.625 | Helped |
| Greedy Hash vs HashNet at long codes | deep hashing · ImageNet, 64 bits | MAP@1000: 0.684 -> 0.688 | No clear effect |
| use exact sign with greedy gradient instead of tanh relaxation or penalty term | AlexNet hashing, 16 bits · CIFAR-10 | MAP during training | Helped |
| binary hash codes instead of unrestricted continuous features for retrieval | AlexNet 16-dim features · CIFAR-10 | MAP | Helped |
| use DPLM with deep CNN features instead of raw features | DPLM · CIFAR-10 (II), 48 bits | MAP: 0.671 -> 0.843 | Helped |
Closest papers by meaning
- Deep Supervised Hashing for Fast Image Retrieval (CVPR 2016 · similarity 0.90)
- Deep Hashing Network for Efficient Similarity Retrieval (AAAI 2016 · similarity 0.90)
- Deep Hashing: A Joint Approach for Image Signature Learning (AAAI 2017 · similarity 0.90)
- From Hashing to CNNs: Training Binary Weight Networks via Hashing (AAAI 2018 · 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 0.87)
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.