Semi-supervised Domain Adaptation via Sample-to-Sample Self-Distillation
Semi-supervised domain adaptation (SSDA) is to adapt a learner to a new domain with only a small set of labeled samples when a large labeled dataset is given on a source domain. In this paper, we propose a pair-based SSDA method that adapts a model to the target domain using self-distillation with sample pairs. Each sample pair is composed of a teacher sample from a labeled dataset (i.e., source or labeled target) and its student sample from an unlabeled dataset (i.e., unlabeled target). Our method generates an assistant feature by transferring an intermediate style between the teacher and the student, and then train the model by minimizing the output discrepancy between the student and the assistant. During training, the assistants gradually bridge the discrepancy between the two domains, thus allowing the student to easily learn from the teacher. Experimental evaluation on standard benchmarks shows that our method effectively minimizes both the inter-domain and intra-domain discrepancies, thus achieving significant improvements over recent methods.
Code (1)
Tasks
Domain AdaptationSemi-supervised Domain AdaptationSimilar Papers 제목 키워드 기반
Towards Realizing the Value of Labeled Target Samples: a Two-Stage Approach for Semi-Supervised Domain Adaptation
Semi-Supervised Domain Adaptation (SSDA) is a recently emerging research topic that extends from the widely-investigated Unsupervised Domain Adaptation (UDA) by further having a few target samples labeled, i.e., the mode…
Domain AdaptationSemi-supervised Domain AdaptationUnsupervised Domain AdaptationCluster-Guided Semi-Supervised Domain Adaptation for Imbalanced Medical Image Classification
Semi-supervised domain adaptation is a technique to build a classifier for a target domain by modifying a classifier in another (source) domain using many unlabeled samples and a small number of labeled samples from the …
ClusteringDomain Adaptationimage-classificationImage Classification+3Cross-Domain Adaptive Clustering for Semi-Supervised Domain Adaptation
In semi-supervised domain adaptation, a few labeled samples per class in the target domain guide features of the remaining target samples to aggregate around them. However, the trained model cannot produce a highly discr…
ClusteringDomain AdaptationSemi-supervised Domain AdaptationSource Domain Subset Sampling for Semi-Supervised Domain Adaptation in Semantic Segmentation
In this paper, we introduce source domain subset sampling (SDSS) as a new perspective of semi-supervised domain adaptation. We propose domain adaptation by sampling and exploiting only a meaningful subset from source dat…
Domain AdaptationSemantic SegmentationSemi-supervised Domain AdaptationAdversarial Semi-Supervised Domain Adaptation for Semantic Segmentation: A New Role for Labeled Target Samples
Adversarial learning baselines for domain adaptation (DA) approaches in the context of semantic segmentation are under explored in semi-supervised framework. These baselines involve solely the available labeled target sa…
Domain AdaptationSemantic SegmentationSemi-supervised Domain Adaptation