Research map / Image generation / Editing and style transfer
Cousin Network Guided Sketch Recognition via Latent Attribute Warehouse
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 |
|---|---|---|---|
| add cousin-network guidance (feature MSE + adversarial + classification) to ResNet-18 (ablation) | ResNet-18 sketch classifier · TU-Berlin 72/class | rank-1 accuracy: 74.46 -> 78.71 | Helped |
| add latent sketch-to-image attribute warehouse (ablation) | CNG-SCN · TU-Berlin 72/class | rank-1 accuracy: 78.71 -> 80.10 | Helped |
| add warehouse at low training data (16 per class) (ablation) | CNG-SCN · TU-Berlin 16/class | rank-1 accuracy: 64.88 -> 66.43 | Helped |
| naively mix natural images with sketches in training instead of sketches only (ablation) | ResNet-18 · TU-Berlin 72/class | rank-1 accuracy: 74.46 -> 74.11 | Hurt |
Closest papers by meaning
- SketchNet: Sketch Classification With Web Images (CVPR 2016 · similarity 0.91)
- SketchGAN: Joint Sketch Completion and Recognition With Generative Adversarial Network (CVPR 2019 · similarity 0.90)
- SketchMate: Deep Hashing for Million-Scale Human Sketch Retrieval (CVPR 2018 · similarity 0.88)
- Enhance Sketch Recognition’s Explainability via Semantic Component-Level Parsing (AAAI 2024 · similarity 0.85)
- Sketch Down the FLOPs: Towards Efficient Networks for Human Sketch (CVPR 2025 · similarity 0.85)
- ARNet: Self-Supervised FG-SBIR with Unified Sample Feature Alignment and Multi-Scale Token Recycling (AAAI 2025 · similarity 0.84)
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.