Search Results for author:
Found 2 papers, 1 papers with code
Multi-cropping Contrastive Learning and Domain Consistency for Unsupervised Image-to-Image Translation
Recently, unsupervised image-to-image translation methods based on contrastive learning have achieved state-of-the-art results in many tasks.
Spectral Normalization and Dual Contrastive Regularization for Image-to-Image Translation
Similarly, we design a style contrastive loss to improve the global texture information of the generated images.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
