Robust Unsupervised Domain Adaptation by Retaining Confident Entropy via Edge Concatenation
The generalization capability of unsupervised domain adaptation can mitigate the need for extensive pixel-level annotations to train semantic segmentation networks by training models on synthetic data as a source with computer-generated annotations. Entropy-based adversarial networks are proposed to improve source domain prediction; however, they disregard significant external information, such as edges, which have the potential to identify and distinguish various objects within an image accurately. To address this issue, we introduce a novel approach to domain adaptation, leveraging the synergy of internal and external information within entropy-based adversarial networks. In this approach, we enrich the discriminator network with edge-predicted probability values within this innovative framework to enhance the clarity of class boundaries. Furthermore, we devised a probability-sharing network that integrates diverse information for more effective segmentation. Incorporating object edges addresses a pivotal aspect of unsupervised domain adaptation that has frequently been neglected in the past -- the precise delineation of object boundaries. Conventional unsupervised domain adaptation methods usually center around aligning feature distributions and may not explicitly model object boundaries. Our approach effectively bridges this gap by offering clear guidance on object boundaries, thereby elevating the quality of domain adaptation. Our approach undergoes rigorous evaluation on the established unsupervised domain adaptation benchmarks, specifically in adapting SYNTHIA $\rightarrow$ Cityscapes and SYNTHIA $\rightarrow$ Mapillary. Experimental results show that the proposed model attains better performance than state-of-the-art methods. The superior performance across different unsupervised domain adaptation scenarios highlights the versatility and robustness of the proposed method.
Code (0)
등록된 구현이 없습니다.
Tasks
Domain AdaptationObjectSemantic SegmentationUnsupervised Domain AdaptationSimilar Papers 제목 키워드 기반
Energy-constrained Self-training for Unsupervised Domain Adaptation
Unsupervised domain adaptation (UDA) aims to transfer the knowledge on a labeled source domain distribution to perform well on an unlabeled target domain. Recently, the deep self-training involves an iterative process of…
Domain Adaptationimage-classificationImage ClassificationSemantic Segmentation+1Unsupervised Domain Adaptive Object Detection using Forward-Backward Cyclic Adaptation
We present a novel approach to perform the unsupervised domain adaptation for object detection through forward-backward cyclic (FBC) training. Recent adversarial training based domain adaptation methods have shown their …
Domain Adaptationimage-classificationImage Classificationobject-detection+2Domain Adaptation on Semantic Segmentation for Aerial Images
Semantic segmentation has achieved significant advances in recent years. While deep neural networks perform semantic segmentation well, their success rely on pixel level supervision which is expensive and time-consuming.…
Domain AdaptationImage SegmentationSegmentationSemantic Segmentation+1Constraining Pseudo-label in Self-training Unsupervised Domain Adaptation with Energy-based Model
Deep learning is usually data starved, and the unsupervised domain adaptation (UDA) is developed to introduce the knowledge in the labeled source domain to the unlabeled target domain. Recently, deep self-training presen…
Domain Adaptationimage-classificationImage ClassificationPseudo Label+2ESL: Entropy-guided Self-supervised Learning for Domain Adaptation in Semantic Segmentation
While fully-supervised deep learning yields good models for urban scene semantic segmentation, these models struggle to generalize to new environments with different lighting or weather conditions for instance. In additi…
Domain AdaptationSelf-Supervised LearningSemantic SegmentationUnsupervised Domain Adaptation