Dual Contrastive Learning for Unsupervised Image-to-Image Translation
arXiv:2104.07689
Abstract
Unsupervised image-to-image translation tasks aim to find a mapping between a source domain X and a target domain Y from unpaired training data. Contrastive learning for Unpaired image-to-image Translation (CUT) yields state-of-the-art results in modeling unsupervised image-to-image translation by maximizing mutual information between input and output patches using only one encoder for both domains. In this paper, we propose a novel method based on contrastive learning and a dual learning setting (exploiting two encoders) to infer an efficient mapping between unpaired data. Additionally, while CUT suffers from mode collapse, a variant of our method efficiently addresses this issue. We further demonstrate the advantage of our approach through extensive ablation studies demonstrating superior performance comparing to recent approaches in multiple challenging image translation tasks. Lastly, we demonstrate that the gap between unsupervised methods and supervised methods can be efficiently closed.
arXiv commentAccepted to NTIRE, CVPRW 2021. Code is available at https://github.com/JunlinHan/DCLGAN
References in corpus (5)
- GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
- Instance Normalization: The Missing Ingredient for Fast Stylization
- Data-Efficient Image Recognition with Contrastive Predictive Coding
- Learning to Discover Cross-Domain Relations with Generative Adversarial Networks
- DRIT++: Diverse Image-to-Image Translation via Disentangled Representations