Sep 2025
Abstract
Semantic segmentation requires extensive pixel-level annotation, motivating unsupervised domain adaptation (UDA) to transfer knowledge from labelled source domains to unlabelled or weakly labelled target domains. One of the most efficient strategies involves using synthetic datasets generated within controlled virtual environments, such as video games or traffic simulators, which can automatically generate pixel-level annotations. However, even when such datasets are available, learning a well-generalised representation that captures both domains remains challenging, owing to probabilistic and geometric discrepancies between the virtual world and real-world imagery. This work introduces a semantic segmentation method based on latent diffusion models, termed Inter-Coder Connected Latent Diffusion (ICCLD), alongside an unsupervised domain adaptation approach. The model employs an inter-coder connection to enhance contextual understanding and preserve fine details, while adversarial learning aligns latent feature distributions across domains during the latent diffusion process. Experiments on GTA5, Synthia, and Cityscapes demonstrate that ICCLD outperforms state-of-the-art UDA methods, achieving mIoU scores of 74.4 (GTA5→Cityscapes) and 67.2 (Synthia→Cityscapes).
Keywords
Diffusion Models, Domain Adaptation, Adversarial Learning, Semantic Segmentation, Unsupervised Learning
Key Contributions
Introduces an adversarial diffusion-based generator that aligns source & target domains without labels.
Replaces GAN-style adversarial learning with diffusion-driven domain adaptation for more stable optimization.
Achieves strong segmentation performance under domain shift while avoiding mode collapse and training instability.
Demonstrates robustness across synthetic-to-real settings through iterative denoising–alignment cycles.