Research map / Label-efficient and robust learning / Recognition and long-tail
Deep Cauchy Hashing for Hamming Space Retrieval
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 DCH instead of HashNet | AlexNet deep hashing · NUS-WIDE | MAP@H≤2: 7.3% | Helped |
| use DCH instead of HashNet | AlexNet deep hashing · MS-COCO | MAP@H≤2: 10.4% | Helped |
| use DCH instead of HashNet | AlexNet deep hashing · CIFAR-10 | MAP@H≤2: 9.9% | Helped |
| add the Cauchy quantization loss (ablation) | DCH · NUS-WIDE | MAP@H≤2: 2.3% | Helped |
| add the Cauchy quantization loss (ablation) | DCH · MS-COCO | MAP@H≤2: 2.3% | Helped |
| add the Cauchy quantization loss (ablation) | DCH · CIFAR-10 | MAP@H≤2: 1.9% | Helped |
| use Cauchy rather than sigmoid cross-entropy (ablation) | DCH · NUS-WIDE | MAP@H≤2: 6.3% | Helped |
| use Cauchy rather than sigmoid cross-entropy (ablation) | DCH · MS-COCO | MAP@H≤2: 9.4% | Helped |
| use Cauchy rather than sigmoid cross-entropy (ablation) | DCH · CIFAR-10 | MAP@H≤2: 8.3% | Helped |
| use normalized Euclidean distance instead of Euclidean distance (ablation) | DCH · NUS-WIDE | MAP@H≤2: 2.4% | Helped |
| use normalized Euclidean distance instead of Euclidean distance (ablation) | DCH · MS-COCO | MAP@H≤2: 3.4% | Helped |
| use normalized Euclidean distance instead of Euclidean distance (ablation) | DCH · CIFAR-10 | MAP@H≤2: 4.4% | Helped |
Closest papers by meaning
- Deep Supervised Hashing for Fast Image Retrieval (CVPR 2016 · similarity 0.89)
- Transfer Adversarial Hashing for Hamming Space Retrieval (AAAI 2018 · similarity 0.89)
- Improved Hamming Distance Search Using Variable Length Substrings (CVPR 2016 · similarity 0.88)
- Deep Hashing With Minimal-Distance-Separated Hash Centers (CVPR 2023 · similarity 0.88)
- Effective Comparative Prototype Hashing for Unsupervised Domain Adaptation (AAAI 2024 · similarity 0.86)
- Pairwise-Label-Based Deep Incremental Hashing with Simultaneous Code Expansion (AAAI 2024 · similarity 0.86)
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.