Research map / Graph learning / Graph algorithms and clustering
Asymmetric Discrete Graph 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 |
|---|---|---|---|
| use asymmetric discrete constraint instead of symmetric (SDGH) (ablation) | ADGH · CIFAR-10, 8 bits | MAP (%): 47.00 -> 51.70 | Helped |
| use asymmetric discrete constraint instead of symmetric (SDGH) (ablation) | ADGH · YouTube, 16 bits | MAP (%): 35.56 -> 39.61 | Helped |
| use asymmetric instead of symmetric discrete constraint with long codes (ablation) | ADGH · CIFAR-10, 16 bits | MAP (%): 55.17 -> 53.16 | Hurt |
| use asymmetric instead of symmetric discrete constraint at 32 bits (ablation) | ADGH · ImageNet subset, 32 bits | MAP (%): 81.40 -> 82.60 | Helped |
| asymmetric anchor affinity matrix and efficient optimisation instead of SDGH (ablation) | ADGH · CIFAR-10, 32 bits | train time (s): 199.44 -> 6.74 | Helped |
| kernelise ADGH (KADGH, 3000 anchors) (ablation) | ADGH · CIFAR-10, 16 bits | MAP (%): 53.16 -> 64.30 | Helped |
| increase anchors from 1000 to 3000 (ablation) | KADGH · CIFAR-10, 16 bits | MAP (%): 60.40 -> 64.30 | Helped |
| use KADGH instead of SDH | kernel hashing · CIFAR-10, 16 bits | MAP (%): 63.40 -> 64.30 | Helped |
| use ADGH instead of FastHash | linear supervised hashing · CIFAR-10, 16 bits | MAP (%): 57.81 -> 53.16 | Hurt |
Closest papers by meaning
- Towards Optimal Discrete Online Hashing with Balanced Similarity (AAAI 2019 · similarity 0.88)
- AMVH: Asymmetric Multi-Valued Hashing (CVPR 2017 · similarity 0.87)
- Large Graph Hashing with Spectral Rotation (AAAI 2017 · similarity 0.87)
- 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 0.84)
- An Asymmetric Augmented Self-Supervised Learning Method for Unsupervised Fine-Grained Image Hashing (CVPR 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.