Rethinking the Truly Unsupervised Image-to-Image Translation
Authors:
Preprint
Abstract
Every recent image-to-image translation model uses either image-level (i.e. input-output pairs) or set-level (i.e. domain labels) supervision at minimum. However, even the set-level supervision can be a serious bottleneck for data collection in practice. In this paper, we tackle image-to-image translation in a fully unsupervised setting, i.e., neither paired images nor domain labels. To this end, we propose the truly unsupervised image-to-image translation method (TUNIT) that simultaneously learns to separate image domains via an information-theoretic approach and generate corresponding images using the estimated domain labels. Experimental results on various datasets show that the proposed method successfully separates domains and translates images across those domains. In addition, our model outperforms existing set-level supervised methods under a semi-supervised setting, where a subset of domain labels is provided. The source code is available at https://github.com/clovaai/tunitKeywords
All Related Versions
This publication has 6 references indexed in Scilit:
- Momentum Contrast for Unsupervised Visual Representation Learning2020
- Filter Response Normalization Layer: Eliminating Batch Dependence in the Training of Deep Neural Networks2020
- Exploring Unlabeled Faces for Novel Attribute Discovery2020
- StarGAN v2: Diverse Image Synthesis for Multiple Domains2020
- Semantic Image Synthesis With Spatially-Adaptive Normalization2019
- High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs2018