Research map / Architectures and efficiency / Neural architecture search
Improved Hamming Distance Search Using Variable Length Substrings
Check 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 variable-length hashkeys instead of MIH's fixed-length hashkeys | Thresholded Hamming search · ANN 1B | average speedup over MIH: 30, 875, 784, 785 | Helped |
| Use variable-length hashkeys instead of MIH's fixed-length hashkeys | Thresholded Hamming search · 1 Million 128 | average speedup over MIH: 13, 818, 1359, 1064 | Helped |
| Use variable-length hashkeys instead of MIH's fixed-length hashkeys | Thresholded Hamming search · 1 Million 512 | average speedup over MIH: 18, 86, 98, 103 | Helped |
| Use variable-length hashkeys rather than fixed-length hashkeys | Thresholded Hamming search · Flickr 1 Million 512, Hamming thresholds between 100 and 150 | retrieval set size | Hurt |
| Use variable-length hashkeys rather than fixed-length hashkeys | Thresholded Hamming search · Across evaluated datasets and thresholds | minimum recall rate | Helped |
Closest papers by meaning
- Deep Cauchy Hashing for Hamming Space Retrieval (CVPR 2018 · similarity 0.88)
- Efficient end-to-end learning for quantizable representations (ICML 2018 · similarity 0.87)
- Deep Supervised Hashing for Fast Image Retrieval (CVPR 2016 · similarity 0.86)
- Deep Unsupervised Image Hashing by Maximizing Bit Entropy (AAAI 2021 · similarity 0.85)
- Learning Attribute-Aware Hash Codes for Fine-Grained Image Retrieval via Query Optimization (ICML 2025 · similarity 0.85)
- Pairwise-Label-Based Deep Incremental Hashing with Simultaneous Code Expansion (AAAI 2024 · 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.