Semantically Consistent Image-to-Image Translation for Unsupervised Domain Adaptation
This work addresses the problem of adapting models from synthetic to real domains for semantic segmentation, which is incremental as it builds on existing image-to-image translation and semi-supervised learning methods.
The paper tackles unsupervised domain adaptation for semantic segmentation from synthetic to real-world images by proposing a semantically consistent image-to-image translation method with consistency regularization, achieving state-of-the-art performance on benchmarks like GTA5 to Cityscapes and SYNTHIA to Cityscapes.
Unsupervised Domain Adaptation (UDA) aims to adapt models trained on a source domain to a new target domain where no labelled data is available. In this work, we investigate the problem of UDA from a synthetic computer-generated domain to a similar but real-world domain for learning semantic segmentation. We propose a semantically consistent image-to-image translation method in combination with a consistency regularisation method for UDA. We overcome previous limitations on transferring synthetic images to real looking images. We leverage pseudo-labels in order to learn a generative image-to-image translation model that receives additional feedback from semantic labels on both domains. Our method outperforms state-of-the-art methods that combine image-to-image translation and semi-supervised learning on relevant domain adaptation benchmarks, i.e., on GTA5 to Cityscapes and SYNTHIA to Cityscapes.