Research map / Learning theory and algorithms / Prediction and decision losses
K-Nearest Neighbors Hashing
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 |
|---|---|---|---|
| Add KNN-based shrinkage before hashing | KNNH · MNIST (784-D intensity) | mAP (%): 41.18 -> 47.33; 43.82 -> 53.25; 45.37 -> 56.03 | Helped |
| Add KNN-based shrinkage before hashing | KNNH · CIFAR-10 (512-D GIST) | mAP (%): 16.57 -> 17.32; 17.34 -> 18.76; 17.91 -> 19.54 | Helped |
| Add KNN-based shrinkage before hashing | KNNH · CIFAR-10 (VGG-FC7) | mAP (%): 26.82 -> 29.06; 27.38 -> 30.82; 28.73 -> 32.60 | Helped |
| Add KNN-based shrinkage before hashing | KNNH · LabelMe-12-50K (VGG-FC7) | mAP (%): 18.06 -> 20.13; 19.40 -> 23.79; 20.71 -> 26.22 | Helped |
| Add KNN-based shrinkage before hashing | KNNH · MNIST (512-D GIST) | mAP (%): 46.37 -> 53.07; 50.59 -> 61.11; 53.69 -> 65.55 | Helped |
| Add KNN-based shrinkage before hashing | KNNH · Places205 | mAP (%): 5.89 -> 7.60; 9.69 -> 12.17; 13.53 -> 15.92 | Helped |
| Vary the KNN neighborhood size k (ablation) | KNNH · CIFAR-10 and MNIST | mAP | Helped |
| Use KNN shrinkage before the ITQ-style hashing stage | KNNH · MNIST | mAP (%) | Helped |
Closest papers by meaning
- Locality-Sensitive Hashing for f-Divergences: Mutual Information Loss and Beyond (NeurIPS 2019 · similarity 0.88)
- Proximity Preserving Binary Code Using Signed Graph-Cut (AAAI 2020 · similarity 0.88)
- Deep Cauchy Hashing for Hamming Space Retrieval (CVPR 2018 · similarity 0.87)
- Approximate Nearest Neighbor Search through Modern Error-Correcting Codes (ICLR 2023 · similarity 0.87)
- An ensemble diversity approach to supervised binary hashing (NeurIPS 2016 · similarity 0.87)
- Binary Embedding with Additive Homogeneous Kernels (AAAI 2017 · 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.