Adversarial Diffusion Model for Unsupervised Domain-Adaptive Semantic Segmentation
Semantic segmentation requires labour-intensive labelling tasks to obtain the supervision signals, and because of this issue, it is encouraged that using domain adaptation, which transfers information from the existing labelled source domains to unlabelled or weakly labelled target domains, is essential. However, it is intractable to find a well-generalised representation which can describe two domains due to probabilistic or geometric difference between the two domains. This paper presents a novel method, the Conditional and Inter-coder Connected Latent Diffusion (CICLD) based Semantic Segmentation Model, to advance unsupervised domain adaptation (UDA) for semantic segmentation tasks. Leveraging the strengths of latent diffusion models and adversarial learning, our method effectively bridges the gap between synthetic and real-world imagery. CICLD incorporates a conditioning mechanism to improve contextual understanding during segmentation and an inter-coder connection to preserve fine-grained details and spatial hierarchies. Additionally, adversarial learning aligns latent feature distributions across source, mixed, and target domains, further enhancing generalisation. Extensive experiments are conducted across three benchmark datasets-GTA5, Synthia, and Cityscape-shows that CICLD outperforms state-of-the-art UDA methods. Notably, the proposed method achieves a mean Intersection over Union (mIoU) of 74.4 for the GTA5 to Cityscape UDA setting and 67.2 mIoU for the Synthia to Cityscape UDA setting. This project is publicly available on 'https://github.com/andreYoo/CICLD'.
Code (0)
등록된 구현이 없습니다.
Tasks
Domain AdaptationSegmentationSemantic SegmentationUnsupervised Domain AdaptationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Unsupervised Domain Adaptation via Domain-Adaptive Diffusion
Unsupervised Domain Adaptation (UDA) is quite challenging due to the large distribution discrepancy between the source domain and the target domain. Inspired by diffusion models which have strong capability to gradually …
Domain AdaptationUnsupervised Domain AdaptationSemantic-guided Adversarial Diffusion Model for Self-supervised Shadow Removal
Existing unsupervised methods have addressed the challenges of inconsistent paired data and tedious acquisition of ground-truth labels in shadow removal tasks. However, GAN-based training often faces issues such as mode …
Generative Adversarial NetworkShadow RemovalUnsupervised Adaptive Semantic Segmentation with Local Lipschitz Constraint
Recent advances in unsupervised domain adaptation have seen considerable progress in semantic segmentation. Existing methods either align different domains with adversarial training or involve the self-learning that util…
Domain AdaptationSegmentationSelf-LearningSemantic Segmentation+1Significance-aware Information Bottleneck for Domain Adaptive Semantic Segmentation
For unsupervised domain adaptation problems, the strategy of aligning the two domains in latent feature space through adversarial learning has achieved much progress in image classification, but usually fails in semantic…
Domain Adaptationimage-classificationImage ClassificationSegmentation+2MLAN: Multi-Level Adversarial Network for Domain Adaptive Semantic Segmentation
Recent progresses in domain adaptive semantic segmentation demonstrate the effectiveness of adversarial learning (AL) in unsupervised domain adaptation. However, most adversarial learning based methods align source and t…
Domain AdaptationImage-to-Image TranslationSemantic SegmentationTranslation+1