Research map / Label-efficient and robust learning / Recognition and long-tail
Deep Hashing: A Joint Approach for Image Signature Learning
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 |
|---|---|---|---|
| jointly learn image features and hashing functions with DeepHash | DeepHash · MNIST, 48 bits | mAP: 0.9817 -> 0.9938 | Helped |
| jointly learn image features and hashing functions with DeepHash | DeepHash · CIFAR10, 48 bits | mAP: 0.581 -> 0.7410 | Helped |
| jointly learn image features and hashing functions with DeepHash | DeepHash · Kaggle-Face, 48 bits | mAP: 0.4132 -> 0.5615 | Helped |
| jointly learn image features and hashing functions with DeepHash | DeepHash · SUN397, 48 bits | mAP: 0.0471 -> 0.1293 | Helped |
| add simultaneous fine-tuning after random initialization (ablation) | DeepHash · MNIST, 12 bits | mAP: 0.9806 -> 0.9918 | Helped |
| add simultaneous fine-tuning after supervised pre-training (ablation) | DeepHash · MNIST, 12 bits | mAP: 0.9673 -> 0.9918 | Helped |
| add simultaneous fine-tuning after random initialization (ablation) | DeepHash · CIFAR10, 12 bits | mAP: 0.5728 -> 0.6874 | Helped |
| add simultaneous fine-tuning after supervised pre-training (ablation) | DeepHash · CIFAR10, 12 bits | mAP: 0.4986 -> 0.6874 | Helped |
| add simultaneous fine-tuning after random initialization (ablation) | DeepHash · Kaggle-Face, 12 bits | mAP: 0.4125 -> 0.5487 | Helped |
| add simultaneous fine-tuning after supervised pre-training (ablation) | DeepHash · Kaggle-Face, 12 bits | mAP: 0.4282 -> 0.5487 | Helped |
| add supervised pre-training and fine-tuning rather than random initialization (ablation) | DeepHash · SUN397, 12 bits | mAP: 0.0211 -> 0.0748 | Helped |
| add simultaneous fine-tuning after supervised pre-training (ablation) | DeepHash · SUN397, 12 bits | mAP: 0.0335 -> 0.0748 | Helped |
Closest papers by meaning
- Deep Supervised Hashing for Fast Image Retrieval (CVPR 2016 · similarity 0.90)
- Deep Hashing Network for Efficient Similarity Retrieval (AAAI 2016 · similarity 0.90)
- Greedy Hash: Towards Fast Optimization for Accurate Hash Coding in CNN (NeurIPS 2018 · similarity 0.90)
- Deep Supervised Discrete Hashing (NeurIPS 2017 · similarity 0.89)
- Pairwise-Label-Based Deep Incremental Hashing with Simultaneous Code Expansion (AAAI 2024 · similarity 0.88)
- Learning Attribute-Aware Hash Codes for Fine-Grained Image Retrieval via Query Optimization (ICML 2025 · similarity 0.86)
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.