Research map / Label-efficient and robust learning / Recognition and long-tail
Deep Supervised Discrete Hashing
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 |
|---|---|---|---|
| Use DSDH instead of DTSH | CIFAR-10, first experimental setting, 48 bits · CIFAR-10, first experimental setting, 48 bits | MAP: 0.774 -> 0.820 | Helped |
| Use DSDH instead of DTSH | NUS-WIDE, first experimental setting, 48 bits · NUS-WIDE, first experimental setting, 48 bits | MAP: 0.824 -> 0.829 | Helped |
| Use DSDH instead of DTSH | CIFAR-10, second experimental setting, 48 bits · CIFAR-10, second experimental setting, 48 bits | MAP: 0.926 -> 0.939 | Helped |
| Use DSDH instead of DTSH | NUS-WIDE, second experimental setting, 48 bits · NUS-WIDE, second experimental setting, 48 bits | MAP: 0.799 -> 0.821 | Helped |
| Add classification information to pairwise-label hashing (ablation) | DSDH-A on CIFAR-10 · CIFAR-10 | precision within Hamming radius 2 | Helped |
| Add classification information in a two-stream design (ablation) | DSDH-A on CIFAR-10 · CIFAR-10 | precision within Hamming radius 2 | Helped |
| Add classification information in a two-stream design (ablation) | DSDH-A on CIFAR-10 · CIFAR-10 | precision-recall | Helped |
| Use a single stream so classification information directly shapes the hash codes (ablation) | DSDH-B on CIFAR-10 · CIFAR-10 | image retrieval performance | Helped |
| Keep the hash codes discrete during optimization instead of directly applying the sign function (ablation) | DSDH-C on CIFAR-10 · CIFAR-10 | image retrieval performance | Helped |
Closest papers by meaning
- Deep Supervised Hashing for Fast Image Retrieval (CVPR 2016 · similarity 0.92)
- On Trivial Solution and High Correlation Problems in Deep Supervised Hashing (AAAI 2018 · similarity 0.92)
- Deep Hashing Network for Efficient Similarity Retrieval (AAAI 2016 · similarity 0.91)
- Deep Graph Online Hashing for Multi-Label Image Retrieval (AAAI 2025 · similarity 0.89)
- Pairwise-Label-Based Deep Incremental Hashing with Simultaneous Code Expansion (AAAI 2024 · similarity 0.88)
- Generalized Debiased Semi-Supervised Hashing for Large-Scale Image Retrieval (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.