DLOW: Domain Flow for Adaptation and Generalization

Abstract

In this work, we present a domain flow generation(DLOW) model to bridge two different domains by generating a continuous sequence of intermediate domains flowing from one domain to the other. The benefits of our DLOW model are two-fold. First, it is able to transfer source images into different styles in the intermediate domains. The transferred images smoothly bridge the gap between source and target domains, thus easing the domain adaptation task. Second, when multiple target domains are provided for training, our DLOW model is also able to generate new styles of images that are unseen in the training data. We implement our DLOW model based on CycleGAN. A domainness variable is introduced to guide the model to generate the desired intermediate domain images. In the inference phase, a flow of various styles of images can be obtained by varying the domainness variable. We demonstrate the effectiveness of our model for both cross-domain semantic segmentation and the style generalization tasks on benchmark datasets. Our implementation is available at https://github.com/ETHRuiGong/DLOW.

arXiv commentAccepted to CVPR 2019 (oral)

References in corpus (10)

• Toward Multimodal Image-to-Image Translation
• Learning to Discover Cross-Domain Relations with Generative Adversarial Networks
• FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptation
• Domain Generalization via Invariant Feature Representation
• Augmented CycleGAN: Learning Many-to-Many Mappings from Unpaired Data
• Maximum Classifier Discrepancy for Unsupervised Domain Adaptation
• Domain Stylization: A Strong, Simple Baseline for Synthetic to Real Image Domain Adaptation
• Image to Image Translation for Domain Adaptation
• Penalizing Top Performers: Conservative Loss for Semantic Segmentation Adaptation
• A Unified Framework for Generalizable Style Transfer: Style and Content Separation