Research map / Label-efficient and robust learning / Recognition and long-tail
Online Hashing with Efficient Updating of Binary Codes
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 |
|---|---|---|---|
| Process queries and database codes asymmetrically, using a separate query projection (ablation) | OHWEU · MS-COCO and NUS-WIDE | mAP | Helped |
| Increase the aggressiveness parameter C initially, then continue increasing it beyond the performance threshold (ablation) | OHWEU · MS-COCO and NUS-WIDE | mAP | Mixed |
| Use fixed hash functions and update projection functions rather than recomputing codes from the whole database | OHWEU · MS-COCO and NUS-WIDE | training time | Helped |
| Use OHWEU instead of other online hashing methods | Online hashing methods · MS-COCO, 32–128 bits | mAP | Helped |
| Use OHWEU instead of other online hashing methods | Online hashing methods · NUS-WIDE, 64–128 bits | mAP | Helped |
| Use OHWEU instead of MIH or BSODH | Online hashing methods · NUS-WIDE, 32 bits | mAP | No clear effect |
Closest papers by meaning
- Fast Online Hashing with Multi-Label Projection (AAAI 2023 · similarity 0.92)
- Pairwise-Label-Based Deep Incremental Hashing with Simultaneous Code Expansion (AAAI 2024 · similarity 0.85)
- Deep Graph Online Hashing for Multi-Label Image Retrieval (AAAI 2025 · similarity 0.85)
- Generalized Debiased Semi-Supervised Hashing for Large-Scale Image Retrieval (AAAI 2025 · similarity 0.84)
- Characteristics Matching Based Hash Codes Generation for Efficient Fine-grained Image Retrieval (CVPR 2024 · similarity 0.84)
- Learning Attribute-Aware Hash Codes for Fine-Grained Image Retrieval via Query Optimization (ICML 2025 · similarity 0.84)
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.