Research map / Label-efficient and robust learning / Recognition and long-tail
Learning Multifunctional Binary Codes for Both Category and Attribute Oriented Retrieval Tasks
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 |
|---|---|---|---|
| Jointly encode category and attribute similarity in one hash model | DPH · ImageNet-150K category retrieval | mAP: 0.343 vs 0.344 (128-bit); 0.353 vs 0.369 (256-bit) | Mixed |
| Jointly encode category and attribute similarity in one hash model | DPH · CFW-60K category retrieval | mAP: 0.241 vs 0.235 (128-bit); 0.274 vs 0.279 (256-bit) | Mixed |
| Use DPH binary codes for attribute-oriented retrieval | DPH · ImageNet-150K | mAP: 0.868 vs 0.903 | Hurt |
| Use DPH binary codes for attribute-oriented retrieval | DPH · CFW-60K | mAP: 0.804 vs 0.771 | Helped |
| Add Attribute-only training data (ablation) | DPH · ImageNet-150K | mean F1-score: 0.753 -> 0.856 | Helped |
| Add Attribute-only training data (ablation) | DPH · CFW-60K | mean F1-score: 0.817 -> 0.867 | Helped |
| Add Category-only training data (ablation) | DPH · ImageNet-150K | mAP: 0.248 -> 0.336 | Helped |
| Add Category-only training data (ablation) | DPH · CFW-60K | mAP: 0.095 -> 0.233 | Helped |
| Train with Both, Attribute-only, and Category-only data (ablation) | DPH · ImageNet-150K | mAP: 0.248 -> 0.343 | Helped |
| Train with Both, Attribute-only, and Category-only data (ablation) | DPH · CFW-60K | mAP: 0.095 -> 0.241 | Helped |
| Train with Both, Attribute-only, and Category-only data (ablation) | DPH · ImageNet-150K | mean F1-score: 0.753 -> 0.879 | Helped |
| Train with Both, Attribute-only, and Category-only data (ablation) | DPH · CFW-60K | mean F1-score: 0.817 -> 0.877 | Helped |
Closest papers by meaning
- Deep Supervised Hashing for Fast Image Retrieval (CVPR 2016 · similarity 0.92)
- Learning Attribute-Aware Hash Codes for Fine-Grained Image Retrieval via Query Optimization (ICML 2025 · similarity 0.91)
- Pairwise-Label-Based Deep Incremental Hashing with Simultaneous Code Expansion (AAAI 2024 · similarity 0.88)
- Deep Graph Online Hashing for Multi-Label Image Retrieval (AAAI 2025 · similarity 0.87)
- Characteristics Matching Based Hash Codes Generation for Efficient Fine-grained Image Retrieval (CVPR 2024 · similarity 0.87)
- 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.