Controlling semantics of diffusion-augmented data for unsupervised domain adaptation

Abstract

Unsupervised domain adaptation (UDA) offers a compelling solution to bridge the gap between labelled synthetic data and unlabelled real-world data for training semantic segmentation models, given the high costs associated with manual annotation. However, the visual differences between the synthetic and real images pose significant challenges to their practical applications. This work addresses these challenges through synthetic-to-real style transfer leveraging diffusion models. The authors’ proposal incorporates semantic controllers to guide the diffusion process and low-rank adaptations (LoRAs) to ensure that style-transferred images align with real-world aesthetics while preserving semantic layout. Moreover, the authors introduce quality metrics to rank the utility of generated images, enabling the selective use of high-quality images for training. To further enhance reliability, the authors propose a novel loss function that mitigates artefacts from the style transfer process by incorporating only pixels aligned with the original semantic labels. Experimental results demonstrate that the authors’ proposal outperforms selected state-of-the-art methods for image generation and UDA training, achieving optimal performance even with a smaller set of high-quality generated images. The authors’ code and models are available at http://www-vpu.eps.uam.es/ControllingSem4UDA/.