Research map / Image generation / Editing and style transfer
Generative Domain-Migration Hashing for Sketch-to-Image Retrieval
Jingyi Zhang, Fumin Shen, Li Liu, Fan Zhu, Mengyang Yu, Ling Shao, Heng Tao Shen, Luc Van Gool
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 |
|---|---|---|---|
| add unification constraint Lc (ablation) | GDH · Sketchy 128-bit | MAP: 0.727 -> 0.811 | Improved |
| add quantization loss Lq (ablation) | GDH · Sketchy 128-bit | MAP: 0.104 -> 0.811 | Improved |
| add adversarial and cycle-consistent loss Lgan (ablation) | GDH · Sketchy 128-bit | MAP: 0.221 -> 0.811 | Improved |
| add adversarial and cycle-consistent loss Lgan (ablation) | GDH · QMUL-Shoes (128-bit) | acc@1: 0.226 -> 0.357 | Improved |
| add adversarial and cycle-consistent loss Lgan (ablation) | GDH · QMUL-Shoes (128-bit) | acc@10: 0.671 -> 0.843 | Improved |
| add attention layer (ablation) | GDH · Sketchy 128-bit | MAP: 0.798 -> 0.811 | Improved |
| add attention layer (ablation) | GDH · QMUL-Shoes (128-bit) | acc@1: 0.335 -> 0.357 | Improved |
| linear mix-up fusion of two hash code types instead of no fusion (ablation) | GDH · Sketchy 128-bit | MAP: 0.811 -> 0.782 | Hurt |
| concatenation fusion of hash codes (ablation) | GDH · Sketchy 128-bit | MAP: 0.811 -> 0.642 | Hurt |
| Kronecker product fusion of hash codes (ablation) | GDH · Sketchy 128-bit | MAP: 0.811 -> 0.735 | Hurt |
| hash in sketch domain (generate fake sketches) instead of migrating sketches to image domain (ablation) | GDH · Sketchy 128-bit | MAP: 0.811 -> 0.310 | Hurt |
| increase code length from 64 to 128 bits | GDH · Sketchy | MAP: 0.810 -> 0.784 | Hurt |
Closest papers by meaning
- Deep Sketch Hashing: Fast Free-Hand Sketch-Based Image Retrieval (CVPR 2017 · similarity 0.92)
- A Zero-Shot Framework for Sketch based Image Retrieval (ECCV 2018 · similarity 0.89)
- Sketch Me That Shoe (CVPR 2016 · similarity 0.89)
- ARNet: Self-Supervised FG-SBIR with Unified Sample Feature Alignment and Multi-Scale Token Recycling (AAAI 2025 · similarity 0.86)
- How to Handle Sketch-Abstraction in Sketch-Based Image Retrieval? (CVPR 2024 · similarity 0.86)
- Sketch Down the FLOPs: Towards Efficient Networks for Human Sketch (CVPR 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.
