Research map / Learning theory and algorithms / Prediction and decision losses
An ensemble diversity approach to supervised binary 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 |
|---|---|---|---|
| Train each hash function on a different training set (ablation) | Independent Laplacian Hashing (ILHt) · CIFAR and Infinite MNIST | precision | Helped |
| Combine different training sets with random initialization and random feature subsets (ablation) | ILHt · CIFAR | precision | No clear effect |
| Use a random subset of features per hash function instead of all features (ablation) | ILHf · CIFAR | precision | Mixed |
| Use all features rather than a feature subset when other diversity mechanisms are present (ablation) | ILHitf · CIFAR | precision | Helped |
| Use disjoint or independently resampled training sets instead of bootstrap samples (ablation) | ILHt · CIFAR and Infinite MNIST | precision | Helped |
| Add hash functions trained on independently sampled data (ablation) | ILHt · CIFAR and Infinite MNIST | precision | Helped |
| Add more bits beyond the initial set (ablation) | KSHcut · CIFAR and Infinite MNIST | precision | No clear effect |
| Add more bits beyond the initial set (ablation) | Thresholded PCA (tPCA) · CIFAR and Infinite MNIST | precision | Hurt |
| Initialize KSHcut with ILHt codes rather than all-ones codes (ablation) | KSHcut · CIFAR and Infinite MNIST | precision | Helped |
Closest papers by meaning
- Optimizing affinity-based binary hashing using auxiliary coordinates (NeurIPS 2016 · similarity 0.91)
- On Trivial Solution and High Correlation Problems in Deep Supervised Hashing (AAAI 2018 · similarity 0.89)
- Deep Supervised Discrete Hashing (NeurIPS 2017 · similarity 0.88)
- Deep Supervised Hashing for Fast Image Retrieval (CVPR 2016 · similarity 0.88)
- One Loss for Quantization: Deep Hashing With Discrete Wasserstein Distributional Matching (CVPR 2022 · similarity 0.87)
- Effective Comparative Prototype Hashing for Unsupervised Domain Adaptation (AAAI 2024 · 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.