Research map / Image generation / Autoregressive and latent generation
Deep Unsupervised Hashing with Latent Semantic Components
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 DSCH instead of CIB | DSCH · CIFAR-10 | MAP@5000: 11.9% averaged increase | Helped |
| Use DSCH instead of CIB | DSCH · FLICKR25K | MAP@5000: 5.0% averaged increase | Helped |
| Use DSCH instead of CIB | DSCH · NUS-WIDE | MAP@5000: 2.1% averaged increase | Helped |
| Add instance correlation loss L1 (ablation) | Base DSCH loss L0 · FLICKR25K, 16 bits | MAP@5000: 0.735 -> 0.768 | Helped |
| Add instance correlation loss L1 (ablation) | Base DSCH loss L0 · FLICKR25K, 32 bits | MAP@5000: 0.744 -> 0.781 | Helped |
| Add instance correlation loss L1 (ablation) | Base DSCH loss L0 · FLICKR25K, 64 bits | MAP@5000: 0.769 -> 0.797 | Helped |
| Add fine-grained component correlation (ablation) | DSCH with instance correlation · FLICKR25K, 16 bits | MAP@5000: 0.768 -> 0.809 | Helped |
| Add fine-grained component correlation (ablation) | DSCH with instance correlation · FLICKR25K, 32 bits | MAP@5000: 0.781 -> 0.819 | Helped |
| Add fine-grained component correlation (ablation) | DSCH with instance correlation · FLICKR25K, 64 bits | MAP@5000: 0.797 -> 0.822 | Helped |
| Add coarse-grained component correlation (ablation) | DSCH with instance and fine-grained component correlation · FLICKR25K, 16 bits | MAP@5000: 0.809 -> 0.817 | Helped |
| Add coarse-grained component correlation (ablation) | DSCH with instance and fine-grained component correlation · FLICKR25K, 32 bits | MAP@5000: 0.819 -> 0.827 | Helped |
| Add coarse-grained component correlation (ablation) | DSCH with instance and fine-grained component correlation · FLICKR25K, 64 bits | MAP@5000: 0.822 -> 0.828 | Helped |
Closest papers by meaning
- Deep Unsupervised Hashing via External Guidance (ICML 2025 · similarity 0.89)
- Polysemic Semantic Instance Network for Cross-Modal Hashing (AAAI 2026 · similarity 0.88)
- Vision-guided Text Mining for Unsupervised Cross-modal Hashing with Community Similarity Quantization (AAAI 2025 · similarity 0.87)
- Effective Comparative Prototype Hashing for Unsupervised Domain Adaptation (AAAI 2024 · similarity 0.87)
- Learning Attribute-Aware Hash Codes for Fine-Grained Image Retrieval via Query Optimization (ICML 2025 · similarity 0.86)
- Statistical Model-driven Similarity Hashing: Bridging Modalities for Efficient Unsupervised Retrieval (AAAI 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.