Research map / Label-efficient and robust learning / Domain adaptation and generalization
Generative Adversarial Networks for Video-to-Video Domain Adaptation
Jiawei Chen, Yuexiang Li, Kai Ma, Yefeng Zheng
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 |
|---|---|---|---|
| translate CVC-Clinic training videos to ETIS-Larib with VideoGAN | ResUNet-50 transfer-learning pipeline · ETIS-Larib | Dice (%): +5.12% | Improved |
| use UNIT-translated training videos | ResUNet-50 transfer-learning pipeline · ETIS-Larib | Dice (%): -44.96% | Hurt |
| use DRIT-translated training videos | ResUNet-50 transfer-learning pipeline · ETIS-Larib | Dice (%): -31.50% | Hurt |
| use CycleGAN-translated training videos | ResUNet-50 transfer-learning pipeline · ETIS-Larib | Dice (%): -2.26% | Hurt |
| add VideoGAN-translated ETIS-Larib videos for augmentation | ResUNet-50 segmentation pipeline · CVC-Clinic-2018 | Dice (%): +4.28% | Improved |
| add UNIT-translated videos for augmentation | ResUNet-50 segmentation pipeline · CVC-Clinic-2018 | Dice (%) | Hurt |
| add DRIT-translated videos for augmentation | ResUNet-50 segmentation pipeline · CVC-Clinic-2018 | Dice (%) | Hurt |
| add CycleGAN-translated videos for augmentation | ResUNet-50 segmentation pipeline · CVC-Clinic-2018 | Dice (%): +1.92% | Improved |
| add X-shape generator to CycleGAN (ablation) | VideoGAN · ETIS-Larib transfer learning | Dice (%): +4.99% | Improved |
| add X-shape generator to CycleGAN (ablation) | VideoGAN · CVC-Clinic-2018 data augmentation | Dice (%): +1.13% | Improved |
| add color histogram loss (ablation) | CycleGAN + X-G · ETIS-Larib transfer learning | Dice (%): +1.56% | Improved |
| add color histogram loss (ablation) | CycleGAN + X-G · CVC-Clinic-2018 data augmentation | Dice (%): +0.64% | Improved |
Closest papers by meaning
- Can Adversarial Networks Make Uninformative Colonoscopy Video Frames Clinically Informative? (Student Abstract) (AAAI 2023 · similarity 0.86)
- Augmenting Colonoscopy Using Extended and Directional CycleGAN for Lossy Image Translation (CVPR 2020 · similarity 0.85)
- Transferring GANs: generating images from limited data (ECCV 2018 · similarity 0.85)
- AugGAN: Cross Domain Adaptation with GAN-based Data Augmentation (ECCV 2018 · similarity 0.85)
- Generalized One-shot Domain Adaptation of Generative Adversarial Networks (NeurIPS 2022 · similarity 0.85)
- An Embedding-Unleashing Video Polyp Segmentation Framework via Region Linking and Scale Alignment (AAAI 2024 · similarity 0.83)
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.
