Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning
Doodle to Search: Practical Zero-Shot Sketch-Based Image Retrieval
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 |
|---|---|---|---|
| add attention to the triplet baseline (ablation) | ZS-SBIR model · Sketchy-Extended, TUBerlin-Extended, QuickDraw-Extended | mAP: 0.3020 -> 0.3207; 0.0590 -> 0.0729; 0.0354 -> 0.0456 | Helped |
| add domain loss to the attention model (ablation) | ZS-SBIR model · Sketchy-Extended, TUBerlin-Extended, QuickDraw-Extended | mAP: 0.3207 -> 0.3256; 0.0729 -> 0.0845; 0.0456 -> 0.0651 | Helped |
| add semantic loss to the attention model (ablation) | ZS-SBIR model · Sketchy-Extended, TUBerlin-Extended, QuickDraw-Extended | mAP: 0.3207 -> 0.3392; 0.0729 -> 0.1055; 0.0456 -> 0.0693 | Helped |
| add domain loss to the attention + semantic model (ablation) | ZS-SBIR model · Sketchy-Extended, TUBerlin-Extended, QuickDraw-Extended | mAP: 0.3392 -> 0.3691; 0.1055 -> 0.1094; 0.0693 -> 0.0752 | Helped |
| use the full model rather than CVAE | ZS-SBIR model · Sketchy-Extended | mAP: 0.1959 -> 0.3691 | Helped |
| use the full model rather than ZSIH | ZS-SBIR model · TUBerlin-Extended | mAP: 0.2200 -> 0.1094 | Hurt |
| use the full model rather than CVAE | ZS-SBIR model · QuickDraw-Extended | mAP: 0.0030 -> 0.0752 | Helped |
Closest papers by meaning
- CLIP for All Things Zero-Shot Sketch-Based Image Retrieval, Fine-Grained or Not (CVPR 2023 · similarity 0.95)
- Asymmetric Mutual Alignment for Unsupervised Zero-Shot Sketch-Based Image Retrieval (AAAI 2024 · similarity 0.91)
- Sketch Down the FLOPs: Towards Efficient Networks for Human Sketch (CVPR 2025 · similarity 0.91)
- Text-to-Image Diffusion Models are Great Sketch-Photo Matchmakers (CVPR 2024 · similarity 0.89)
- How to Handle Sketch-Abstraction in Sketch-Based Image Retrieval? (CVPR 2024 · similarity 0.89)
- You'll Never Walk Alone: A Sketch and Text Duet for Fine-Grained Image Retrieval (CVPR 2024 · similarity 0.89)
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.