Style Adaptation for Domain-adaptive Semantic Segmentation

TL;DR

This paper proposes a simple style transfer approach in the feature space to improve unsupervised domain adaptation for semantic segmentation, significantly boosting performance on synthetic-to-real datasets.

Contribution

It introduces a parameter-free style transfer method that enhances domain adaptation by transferring target style information at multiple feature levels.

Findings

Achieved 76.93 mIoU on GTA->Cityscapes, surpassing previous SOTA by 1.03 points.

Seamlessly integrates with self-training UDA methods without extra parameters.

Demonstrated effectiveness in synthetic-to-real domain adaptation tasks.

Abstract

Unsupervised Domain Adaptation (UDA) refers to the method that utilizes annotated source domain data and unlabeled target domain data to train a model capable of generalizing to the target domain data. Domain discrepancy leads to a significant decrease in the performance of general network models trained on the source domain data when applied to the target domain. We introduce a straightforward approach to mitigate the domain discrepancy, which necessitates no additional parameter calculations and seamlessly integrates with self-training-based UDA methods. Through the transfer of the target domain style to the source domain in the latent feature space, the model is trained to prioritize the target domain style during the decision-making process. We tackle the problem at both the image-level and shallow feature map level by transferring the style information from the target domain to the source domain data. As a result, we obtain a model that exhibits superior performance on the target domain. Our method yields remarkable enhancements in the state-of-the-art performance for synthetic-to-real UDA tasks. For example, our proposed method attains a noteworthy UDA performance of 76.93 mIoU on the GTA->Cityscapes dataset, representing a notable improvement of +1.03 percentage points over the previous state-of-the-art results.