Research map / Detection and segmentation / Open-set and few-shot detection
Memory-Guided Unsupervised Image-to-Image Translation
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 class-aware memory instead of single memory (ablation) | MGUIT · INIT, sunny→night | CIS: 1.094 -> 1.176 | Helped |
| add class-aware memory instead of single memory (ablation) | MGUIT · INIT, sunny→night | LPIPS: 0.310 -> 0.346 | Helped |
| replace feature triplet loss with feature contrastive loss (ablation) | MGUIT with class-aware memory · INIT, sunny→night | CIS: 1.156 -> 1.176 | Helped |
| replace feature triplet loss with feature contrastive loss (ablation) | MGUIT with class-aware memory · INIT, sunny→night | LPIPS: 0.328 -> 0.346 | Helped |
| use class-aware memory with feature contrastive loss rather than single memory with triplet loss (ablation) | MGUIT · INIT, sunny→night | IS: 1.189 -> 1.271 | Helped |
| use class-aware memory with feature contrastive loss rather than single memory with triplet loss (ablation) | MGUIT · INIT, night→sunny | CIS: 1.037 -> 1.115 | Helped |
| use class-aware memory with feature contrastive loss rather than single memory with triplet loss (ablation) | MGUIT · INIT, night→sunny | IS: 1.080 -> 1.130 | Helped |
| use MGUIT for translation in place of DUNIT | INIT dataset · INIT dataset, average | CIS: 1.079 -> 1.112 | Helped |
| use MGUIT for translation in place of DUNIT | INIT dataset · sunny→night/rainy/cloudy, average | LPIPS: 0.287 -> 0.304 | Helped |
| use MGUIT-generated images for domain adaptation instead of DUNIT w/ IC | KITTI→Cityscapes detection · KITTI→Cityscapes | mAP: 54.1 -> 54.6 | Helped |
Closest papers by meaning
- A Style-Aware Discriminator for Controllable Image Translation (CVPR 2022 · similarity 0.90)
- Towards Instance-Level Image-To-Image Translation (CVPR 2019 · similarity 0.90)
- Exemplar Guided Unsupervised Image-to-Image Translation with Semantic Consistency (ICLR 2019 · similarity 0.89)
- Encoding in Style: A StyleGAN Encoder for Image-to-Image Translation (CVPR 2021 · similarity 0.88)
- Unsupervised Image-to-Image Translation With Generative Prior (CVPR 2022 · similarity 0.88)
- Image-To-Image Translation via Group-Wise Deep Whitening-And-Coloring Transformation (CVPR 2019 · similarity 0.87)
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.