Scaling Unsupervised Domain Adaptation through Optimal Collaborator Selection and Lazy Discriminator Synchronization
Breakthroughs in unsupervised domain adaptation (uDA) have opened up the possibility of adapting models from a label-rich source domain to unlabeled target domains. Prior uDA works have primarily focused on improving adaptation accuracy between the given source and target domains, and considerably less attention has been paid to the challenges that arise when uDA is deployed in practical settings. This paper puts forth a novel and complementary perspective, and investigates the algorithmic challenges that arise when uDA is deployed in a distributed ML system with multiple target domains. We propose two algorithms: i) a Collaborator Selection algorithm which selects an optimal collaborator for each target domain, and makes uDA systems more accurate and flexible; ii) a distributed training strategy that allows adversarial uDA algorithms to train in a privacy-preserving manner. We provide theoretical justifications and empirical results to show that our solution significantly boosts the performance of uDA in practical settings.
Code (0)
등록된 구현이 없습니다.
Tasks
Domain AdaptationPrivacy PreservingUnsupervised Domain AdaptationSimilar Papers 제목 키워드 기반
SAILOR: Scaling Anchors via Insights into Latent Object Representation
LiDAR 3D object detection models are inevitably biased towards their training dataset. The detector clearly exhibits this bias when employed on a target dataset, particularly towards object sizes. However, object sizes v…
3D Object DetectionDomain AdaptationObjectobject-detection+2Memory Consistent Unsupervised Off-the-Shelf Model Adaptation for Source-Relaxed Medical Image Segmentation
Unsupervised domain adaptation (UDA) has been a vital protocol for migrating information learned from a labeled source domain to facilitate the implementation in an unlabeled heterogeneous target domain. Although UDA is …
Brain Tumor SegmentationDomain AdaptationImage SegmentationMedical Image Segmentation+5Hierarchical Optimal Transport for Unsupervised Domain Adaptation
In this paper, we propose a novel approach for unsupervised domain adaptation, that relates notions of optimal transport, learning probability measures and unsupervised learning. The proposed approach, HOT-DA, is based o…
Domain AdaptationUnsupervised Domain AdaptationUnsupervised domain adaptation with imputation
Motivated by practical applications, we consider unsupervised domain adaptation for classification problems, in the presence of missing data in the target domain. More precisely, we focus on the case where there is a dom…
ClassificationDomain AdaptationImputationUnsupervised Domain AdaptationA Unified Framework for Unsupervised Domain Adaptation based on Instance Weighting
Despite the progress made in domain adaptation, solving Unsupervised Domain Adaptation (UDA) problems with a general method under complex conditions caused by label shifts between domains remains a formidable task. In th…
Domain AdaptationPartial Domain AdaptationUniversal Domain AdaptationUnsupervised Domain Adaptation