Semi-Supervised Transfer Boosting (SS-TrBoosting)

TL;DR

This paper introduces SS-TrBoosting, a semi-supervised transfer boosting framework that enhances domain adaptation models by ensemble learning, boosting, and source data generation, effectively improving performance across various adaptation settings.

Contribution

It proposes a novel fine-tuning framework that combines boosting and ensemble learning for semi-supervised domain adaptation, including a source data generation method for source-free adaptation.

Findings

SS-TrBoosting improves performance of existing UDA, SSDA, and SFDA models.

The method effectively extends to source-free domain adaptation scenarios.

Experiments demonstrate significant accuracy gains across multiple datasets.

Abstract

Semi-supervised domain adaptation (SSDA) aims at training a high-performance model for a target domain using few labeled target data, many unlabeled target data, and plenty of auxiliary data from a source domain. Previous works in SSDA mainly focused on learning transferable representations across domains. However, it is difficult to find a feature space where the source and target domains share the same conditional probability distribution. Additionally, there is no flexible and effective strategy extending existing unsupervised domain adaptation (UDA) approaches to SSDA settings. In order to solve the above two challenges, we propose a novel fine-tuning framework, semi-supervised transfer boosting (SS-TrBoosting). Given a well-trained deep learning-based UDA or SSDA model, we use it as the initial model, generate additional base learners by boosting, and then use all of them as an ensemble. More specifically, half of the base learners are generated by supervised domain adaptation, and half by semi-supervised learning. Furthermore, for more efficient data transmission and better data privacy protection, we propose a source data generation approach to extend SS-TrBoosting to semi-supervised source-free domain adaptation (SS-SFDA). Extensive experiments showed that SS-TrBoosting can be applied to a variety of existing UDA, SSDA and SFDA approaches to further improve their performance.