Towards Realizing the Value of Labeled Target Samples: a Two-Stage Approach for Semi-Supervised Domain Adaptation

04/21/2023
by   mengqun Jin, et al.
0

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 model is trained with labeled source samples, unlabeled target samples as well as a few labeled target samples. Compared with UDA, the key to SSDA lies how to most effectively utilize the few labeled target samples. Existing SSDA approaches simply merge the few precious labeled target samples into vast labeled source samples or further align them, which dilutes the value of labeled target samples and thus still obtains a biased model. To remedy this, in this paper, we propose to decouple SSDA as an UDA problem and a semi-supervised learning problem where we first learn an UDA model using labeled source and unlabeled target samples and then adapt the learned UDA model in a semi-supervised way using labeled and unlabeled target samples. By utilizing the labeled source samples and target samples separately, the bias problem can be well mitigated. We further propose a consistency learning based mean teacher model to effectively adapt the learned UDA model using labeled and unlabeled target samples. Experiments show our approach outperforms existing methods.

READ FULL TEXT
research
06/30/2021

CLDA: Contrastive Learning for Semi-Supervised Domain Adaptation

Unsupervised Domain Adaptation (UDA) aims to align the labeled source di...
research
11/29/2021

Semi-supervised Domain Adaptation via Sample-to-Sample Self-Distillation

Semi-supervised domain adaptation (SSDA) is to adapt a learner to a new ...
research
04/19/2021

Semi-Supervised Domain Adaptation with Prototypical Alignment and Consistency Learning

Domain adaptation enhances generalizability of a model across domains wi...
research
02/05/2023

Semi-Supervised Domain Adaptation with Source Label Adaptation

Semi-Supervised Domain Adaptation (SSDA) involves learning to classify u...
research
06/01/2021

Semi-supervised Models are Strong Unsupervised Domain Adaptation Learners

Unsupervised domain adaptation (UDA) and semi-supervised learning (SSL) ...
research
04/09/2018

G-Distillation: Reducing Overconfident Errors on Novel Samples

Counter to the intuition that unfamiliarity should lead to lack of confi...
research
03/05/2017

A Theory of Output-Side Unsupervised Domain Adaptation

When learning a mapping from an input space to an output space, the assu...

Please sign up or login with your details

Forgot password? Click here to reset