Pred&Guide: Labeled Target Class Prediction for Guiding Semi-Supervised Domain Adaptation

TL;DR

Pred&Guide is a novel semi-supervised domain adaptation framework that uses label prediction consistency to improve classification accuracy on target data, achieving state-of-the-art results.

Contribution

It introduces a three-stage method leveraging label prediction inconsistency to guide domain adaptation in semi-supervised settings.

Findings

Achieves state-of-the-art results on Office-Home and DomainNet datasets.

Effectively utilizes few labeled target examples to improve adaptation.

Outperforms existing methods in semi-supervised domain adaptation tasks.

Abstract

Semi-supervised domain adaptation aims to classify data belonging to a target domain by utilizing a related label-rich source domain and very few labeled examples of the target domain. Here, we propose a novel framework, Pred&Guide, which leverages the inconsistency between the predicted and the actual class labels of the few labeled target examples to effectively guide the domain adaptation in a semi-supervised setting. Pred&Guide consists of three stages, as follows (1) First, in order to treat all the target samples equally, we perform unsupervised domain adaptation coupled with self-training; (2) Second is the label prediction stage, where the current model is used to predict the labels of the few labeled target examples, and (3) Finally, the correctness of the label predictions are used to effectively weigh source examples class-wise to better guide the domain adaptation process. Extensive experiments show that the proposed Pred&Guide framework achieves state-of-the-art results for two large-scale benchmark datasets, namely Office-Home and DomainNet.