A Novel Unsupervised Domain Adaption Method for Depth-Guided Semantic Segmentation Using Coarse-to-Fine Alignment
Domain adaptation methods in machine learning deal with the domain shift issue by aligning source and target data representation. This paper proposes a novel domain adaptation method for semantic segmentation that exploits the Fourier transform on chromatic space to improve the quality of style transfer, and generates pseudo-labels for self-training by combining the results from different teachers obtained at different rounds of self-training. Our method also applies class-level adversarial learning to achieve a more fine-grained alignment between the two domains, and a late fusion with a depth-estimation model to improve its segmentation outputs. Experiments show that our method yields superior performance in terms of accuracy compared to other existing state-of-the-art methods.
Code (0)
등록된 구현이 없습니다.
Tasks
Depth EstimationDomain AdaptationSegmentationSemantic SegmentationStyle TransferUnsupervised Domain AdaptationSimilar Papers 제목 키워드 기반
Spatial Attention Pyramid Network for Unsupervised Domain Adaptation
Unsupervised domain adaptation is critical in various computer vision tasks, such as object detection, instance segmentation, and semantic segmentation, which aims to alleviate performance degradation caused by domain-sh…
Domain AdaptationInstance Segmentationobject-detectionObject Detection+3AdaDepth: Unsupervised Content Congruent Adaptation for Depth Estimation
Supervised deep learning methods have shown promising results for the task of monocular depth estimation; but acquiring ground truth is costly, and prone to noise as well as inaccuracies. While synthetic datasets have be…
Depth EstimationDomain AdaptationMonocular Depth EstimationUnsupervised Domain AdaptationLearning Invariant Representation for Unsupervised Image Restoration
Recently, cross domain transfer has been applied for unsupervised image restoration tasks. However, directly applying existing frameworks would lead to domain-shift problems in translated images due to lack of effective …
Domain AdaptationImage RestorationA Domain Agnostic Normalization Layer for Unsupervised Adversarial Domain Adaptation
We propose a normalization layer for unsupervised domain adaption in semantic scene segmentation. Normalization layers are known to improve convergence and generalization and are part of many state-of-the-art fully-convo…
Domain AdaptationScene SegmentationOn the Robustness of Domain Adaption to Adversarial Attacks
State-of-the-art deep neural networks (DNNs) have been proved to have excellent performance on unsupervised domain adaption (UDA). However, recent work shows that DNNs perform poorly when being attacked by adversarial sa…
Adversarial AttackDomain AdaptationPseudo LabelUnsupervised Domain Adaptation