Research map / Graph learning / Graph self-supervised learning
Linking Sketch Patches by Learning Synonymous Proximity for Graphic Sketch Representation
Sicong Zang, Shikui Tu, Lei Xu
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 |
|---|---|---|---|
| link patches by learned synonymous proximity instead of random affinities (ablation) | SP-gra2seq · DS1 controllable sketch synthesis | Rec (%): 95.50 -> 95.91 | Improved |
| link patches by learned synonymous proximity instead of random affinities (ablation) | SP-gra2seq · DS2 sketch healing, 10% mask | Ret top-1 (%): 18.53 -> 50.42 | Improved |
| link patches by learned synonymous proximity instead of random affinities (ablation) | SP-gra2seq · DS3 sketch healing, 30% mask | Ret top-1 (%): 8.92 -> 5.65 | Hurt |
| add the inter-sketch patch clustering constraint (ablation) | SP-gra2seq · DS1 controllable sketch synthesis | Rec (%): 94.51 -> 95.91 | Improved |
| add the inter-sketch patch clustering constraint (ablation) | SP-gra2seq · DS2 sketch healing, 30% mask | Rec (%): 77.20 -> 82.85 | Improved |
| add the inter-sketch patch clustering constraint (ablation) | SP-gra2seq · DS3 sketch healing, 10% mask | Rec (%): 83.84 -> 83.38 | Hurt |
Closest papers by meaning
- SketchLattice: Latticed Representation for Sketch Manipulation (ICCV 2021 · similarity 0.88)
- Sketching based Representations for Robust Image Classification with Provable Guarantees (NeurIPS 2022 · similarity 0.88)
- SketchFusion: Learning Universal Sketch Features through Fusing Foundation Models (CVPR 2025 · similarity 0.86)
- SketchINR: A First Look into Sketches as Implicit Neural Representations (CVPR 2024 · similarity 0.86)
- Sketch Down the FLOPs: Towards Efficient Networks for Human Sketch (CVPR 2025 · similarity 0.86)
- How to Handle Sketch-Abstraction in Sketch-Based Image Retrieval? (CVPR 2024 · similarity 0.85)
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.
