Research map / Label-efficient and robust learning / Recognition and long-tail
Learning to Sketch With Shortcut Cycle Consistency
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 the full hybrid model with shortcut cycle consistency instead of Pix2seq one-way supervised translation (ablation) | Photo-to-sketch synthesis · ShoeV2 | Recognition acc.@1: 51.50% -> 53.50% | Helped |
| Use the full hybrid model with shortcut cycle consistency instead of Pix2seq one-way supervised translation (ablation) | Photo-to-sketch synthesis · ShoeV2 | Retrieval acc.@1: 4.50% -> 6.00% | Helped |
| Use the full hybrid model with shortcut cycle consistency instead of CycleGAN-S hybrid translation | Photo-to-sketch synthesis · ChairV2 | Retrieval acc.@1: 6.00% -> 8.00% | Helped |
| Add synthetic photo-sketch pretraining for FG-SBIR | FG-SBIR model · ShoeV2 | acc.@1: 30.33% -> 32.43% | Helped |
| Add synthetic photo-sketch pretraining for FG-SBIR | FG-SBIR model · ShoeV2 | acc.@10: 76.28% -> 77.48% | Helped |
| Replace shortcut within-domain reconstruction with conventional full cycle consistency (ablation) | Photo-to-sketch synthesis · QMUL-Shoe-Chair-V2 | photo-to-sketch synthesis quality | Hurt |
| Add adversarial loss to the photo decoder (ablation) | Photo-to-sketch synthesis model · QMUL-Shoe-Chair-V2 | photo-to-sketch synthesis quality | Hurt |
Closest papers by meaning
- Picture That Sketch: Photorealistic Image Generation From Abstract Sketches (CVPR 2023 · similarity 0.92)
- Sketch Me That Shoe (CVPR 2016 · similarity 0.91)
- Sketch Down the FLOPs: Towards Efficient Networks for Human Sketch (CVPR 2025 · similarity 0.90)
- SketchFusion: Learning Universal Sketch Features through Fusing Foundation Models (CVPR 2025 · similarity 0.88)
- It's All About Your Sketch: Democratising Sketch Control in Diffusion Models (CVPR 2024 · similarity 0.88)
- Open Vocabulary Semantic Scene Sketch Understanding (CVPR 2024 · similarity 0.88)
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.