Research map / Label-efficient and robust learning / Semi-supervised learning
Deep Hashing with Active Pairwise Supervision
Ziwei Wang, Quan Zheng, Jiwen Lu, Jie Zhou
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| increase labeled-sample ratio from 1% to 30% (ablation) | DH-APS · CIFAR-10 (32-bit) | MAP (%): 32.6 -> 63.5 | Improved |
| increase labeled ratio from 50% to 100% (ablation) | DH-APS · CIFAR-10 (32-bit) | MAP (%): 64.7 -> 66.1 | No clear effect |
| add active sample selection at 1% labels vs 0% (ablation) | DH-APS · CIFAR-10 (32-bit) | MAP (%): 18.1 -> 32.6 | Improved |
| use all three acquisition terms (uncertainty, representativeness, diversity) (ablation) | DH-APS · CIFAR-10 (32-bit, 1% labeled) | MAP (%): 25.5 -> 32.6 | Improved |
| add uncertainty term to acquisition function (ablation) | DH-APS · CIFAR-10 (32-bit) | MAP (%) | Improved |
| add representativeness term (ablation) | DH-APS · CIFAR-10 (32-bit) | MAP (%) | Improved |
| add diversity term (ablation) | DH-APS · CIFAR-10 (32-bit) | MAP (%) | Improved |
| use DH-APS as the sampler for labeled instances in PTS3H | PTS3H · CIFAR-10 (32-bit) | MAP (%): 83.5 -> 86.7 | Improved |
| use DH-APS as the sampler for labeled instances in PTS3H | PTS3H · ImageNet-100 (32-bit) | MAP (%): 68.0 -> 70.3 | Improved |
| use DH-APS with 1% labels instead of unsupervised GraphBit | hashing · CIFAR-10 (32-bit) | MAP (%): 27.0 -> 32.6 | Improved |
Closest papers by meaning
- Deep Supervised Discrete Hashing (NeurIPS 2017 · similarity 0.90)
- Unsupervised Deep Hashing with Similarity-Adaptive and Discrete Optimization (TPAMI 2018 · similarity 0.89)
- Supervised Deep Hashing for Hierarchical Labeled Data (AAAI 2018 · similarity 0.89)
- SADIH: Semantic-Aware DIscrete Hashing (AAAI 2019 · similarity 0.88)
- Pairwise-Label-Based Deep Incremental Hashing with Simultaneous Code Expansion (AAAI 2024 · similarity 0.88)
- Generalized Debiased Semi-Supervised Hashing for Large-Scale Image Retrieval (AAAI 2025 · 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.
