Semi-Supervised Domain Adaptation with Representation Learning for Semantic Segmentation across Time
Deep learning generates state-of-the-art semantic segmentation provided that a large number of images together with pixel-wise annotations are available. To alleviate the expensive data collection process, we propose a semi-supervised domain adaptation method for the specific case of images with similar semantic content but different pixel distributions. A network trained with supervision on a past dataset is finetuned on the new dataset to conserve its features maps. The domain adaptation becomes a simple regression between feature maps and does not require annotations on the new dataset. This method reaches performances similar to classic transfer learning on the PASCAL VOC dataset with synthetic transformations.
Code (0)
등록된 구현이 없습니다.
Tasks
Domain AdaptationregressionRepresentation LearningSemantic SegmentationSemi-supervised Domain AdaptationTransfer LearningSimilar Papers 제목 키워드 기반
SemiDAViL: Semi-supervised Domain Adaptation with Vision-Language Guidance for Semantic Segmentation
Domain Adaptation (DA) and Semi-supervised Learning (SSL) converge in Semi-supervised Domain Adaptation (SSDA), where the objective is to transfer knowledge from a source domain to a target domain using a combination…
Domain AdaptationRepresentation LearningSegmentationSemantic Segmentation+1AGLP: A Graph Learning Perspective for Semi-supervised Domain Adaptation
In semi-supervised domain adaptation (SSDA), the model aims to leverage partially labeled target domain data along with a large amount of labeled source domain data to enhance its generalization capability for the target…
Domain AdaptationGraph LearningSemi-supervised Domain AdaptationSemi-supervised Domain Adaptation for Semantic Segmentation
Deep learning approaches for semantic segmentation rely primarily on supervised learning approaches and require substantial efforts in producing pixel-level annotations. Further, such approaches may perform poorly when a…
Data AugmentationDomain AdaptationSegmentationSemantic Segmentation+2Uncertainty-Guided Mixup for Semi-Supervised Domain Adaptation without Source Data
Present domain adaptation methods usually perform explicit representation alignment by simultaneously accessing the source data and target data. However, the source data are not always available due to the privacy preser…
Domain AdaptationPrivacy PreservingSemi-supervised Domain AdaptationSource-Free Domain AdaptationDomain Adaptation for Semantic Segmentation via Patch-Wise Contrastive Learning
We introduce a novel approach to unsupervised and semi-supervised domain adaptation for semantic segmentation. Unlike many earlier methods that rely on adversarial learning for feature alignment, we leverage contrastive …
Contrastive LearningDomain AdaptationSegmentationSemantic Segmentation+1