Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning
Zero-Shot Sketch-Based Image Retrieval via Graph Convolution Network
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 learnable (visual+semantic) adjacency matrix instead of fixed semantic one (ablation) | GCN-only SketchGCN · Sketchy-Extended | mAP@200: 0.549 -> 0.556 | Helped |
| use learnable adjacency matrix instead of fixed one (ablation) | GCN-only SketchGCN · TU-Berlin-Extended | mAP@200: 0.517 -> 0.508 | Hurt |
| use learnable adjacency matrix instead of fixed one (ablation) | GCN-only SketchGCN · Sketchy-Extended | mAP: 0.366 -> 0.367 | No clear effect |
| use CVAE instead of MLP as semantic reconstruction network (ablation) | SketchGCN · Sketchy-Extended | mAP@200: 0.555 -> 0.568 | Helped |
| use CVAE instead of MLP as semantic reconstruction network (ablation) | SketchGCN · TU-Berlin-Extended | mAP: 0.300 -> 0.324 | Helped |
| use CVAE instead of MLP as semantic reconstruction network (ablation) | SketchGCN · TU-Berlin-Extended | mAP@200: 0.506 -> 0.528 | Helped |
| add MLP semantic reconstruction network to GCN with fixed A (ablation) | GCN only · TU-Berlin-Extended | mAP@200: 0.517 -> 0.506 | No clear effect |
| add CVAE reconstruction network and learnable A to GCN-only basic model (ablation) | GCN with fixed A · Sketchy-Extended | mAP: 0.366 -> 0.382 | Helped |
| SketchGCN vs best prior method Doodle2Search | ZS-SBIR · Sketchy-Extended | mAP: 0.369 -> 0.382 | Helped |
Closest papers by meaning
- Semantically Tied Paired Cycle Consistency for Zero-Shot Sketch-Based Image Retrieval (CVPR 2019 · similarity 0.93)
- Asymmetric Mutual Alignment for Unsupervised Zero-Shot Sketch-Based Image Retrieval (AAAI 2024 · similarity 0.89)
- ARNet: Self-Supervised FG-SBIR with Unified Sample Feature Alignment and Multi-Scale Token Recycling (AAAI 2025 · similarity 0.88)
- Text-to-Image Diffusion Models are Great Sketch-Photo Matchmakers (CVPR 2024 · similarity 0.87)
- Sketch Down the FLOPs: Towards Efficient Networks for Human Sketch (CVPR 2025 · similarity 0.87)
- How to Handle Sketch-Abstraction in Sketch-Based Image Retrieval? (CVPR 2024 · 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.