Multi-feature contrastive learning for unpaired image-to-image translation
Abstract Unpaired image-to-image translation for the generation field has made much progress recently. However, these methods suffer from mode collapse because of the overfitting of the discriminator. To this end, we propose a straightforward method to construct a contrastive loss using the feature...
Main Authors: | Yao Gou, Min Li, Yu Song, Yujie He, Litao Wang |
---|---|
Format: | Article |
Language: | English |
Published: |
Springer
2022-12-01
|
Series: | Complex & Intelligent Systems |
Subjects: | |
Online Access: | https://doi.org/10.1007/s40747-022-00924-1 |
Similar Items
-
A domain translation network with contrastive constraint for unpaired motion image deblurring
by: Bingxin Zhao, et al.
Published: (2023-08-01) -
Enhanced Unpaired Image-to-Image Translation via Transformation in Saliency Domain
by: Kei Shibasaki, et al.
Published: (2023-01-01) -
Early Detection of Rice Blast Using a Semi-Supervised Contrastive Unpaired Translation Iterative Network Based on UAV Images
by: Shaodan Lin, et al.
Published: (2023-10-01) -
Improving Generative Adversarial Networks for Patch-Based Unpaired Image-to-Image Translation
by: Moritz Bohland, et al.
Published: (2023-01-01) -
UMGAN: Underwater Image Enhancement Network for Unpaired Image-to-Image Translation
by: Boyang Sun, et al.
Published: (2023-02-01)