A Comparison of Strategies for Source-Free Domain Adaptation
Data sharing restrictions are common in NLP, especially in the clinical domain, but there is limited research on adapting models to new domains without access to the original training data, a setting known as source-free domain adaptation. We take algorithms that traditionally assume access to the source-domain training data—active learning, self-training, and data augmentation—and adapt them for source free domain adaptation. Then we systematically compare these different strategies across multiple tasks and domains. We find that active learning yields consistent gains across all SemEval 2021 Task 10 tasks and domains, but though the shared task saw successful self-trained and data augmented models, our systematic comparison finds these strategies to be unreliable for source-free domain adaptation.
Code (0)
등록된 구현이 없습니다.
Tasks
Active LearningData AugmentationDomain AdaptationSource-Free Domain AdaptationSimilar Papers 제목 키워드 기반
A Comparison of Strategies for Source-Free Domain Adaptation
Data sharing restrictions are common in NLP, especially in the clinical domain, but there is limited research on adapting models to new domains without access to the original training data, a setting known as source-free…
Active LearningData AugmentationDomain AdaptationSource-Free Domain AdaptationSource-Free Online Domain Adaptive Semantic Segmentation of Satellite Images under Image Degradation
Online adaptation to distribution shifts in satellite image segmentation stands as a crucial yet underexplored problem. In this paper, we address source-free and online domain adaptation, i.e., test-time adaptation (TTA)…
Domain AdaptationImage SegmentationOnline Domain AdaptationSemantic Segmentation+1Source-Free Domain Adaptation for RGB-D Semantic Segmentation with Vision Transformers
With the increasing availability of depth sensors, multimodal frameworks that combine color information with depth data are gaining interest. However, ground truth data for semantic segmentation is burdensome to provide,…
Domain AdaptationSegmentationSemantic SegmentationSource-Free Domain Adaptation+1Transcending Domains through Text-to-Image Diffusion: A Source-Free Approach to Domain Adaptation
Domain Adaptation (DA) is a method for enhancing a model's performance on a target domain with inadequate annotated data by applying the information the model has acquired from a related source domain with sufficient lab…
Domain AdaptationSource-Free Domain AdaptationSimplifying Source-Free Domain Adaptation for Object Detection: Effective Self-Training Strategies and Performance Insights
This paper focuses on source-free domain adaptation for object detection in computer vision. This task is challenging and of great practical interest, due to the cost of obtaining annotated data sets for every new domain…
Domain Adaptationobject-detectionObject DetectionPseudo Label+2