Source Data-Absent Unsupervised Domain Adaptation Through Hypothesis Transfer and Labeling Transfer

By Jian Liang, Dapeng Hu, Yunbo Wang, Ran He, Jiashi Feng. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020

358 citations recorded by the source corpus.

Unsupervised domain adaptation (UDA) aims to transfer knowledge from a related but different well-labeled source domain to a new unlabeled target domain. Most existing UDA methods require access to the source data, and thus are not applicable when the data are confidential and not shareable due to privacy concerns. This paper aims to tackle a realistic setting with only a classification model available trained over, instead of accessing to, the source data. To effectively utilize the source model for adaptation, we propose a novel approach called Source HypOthesis Transfer (SHOT), which learns the feature extraction module for the target domain by fitting the target data features to the frozen source classification module (representing classification hypothesis). Specifically, SHOT exploits both information maximization and self-supervised learning for the feature extraction module learning to ensure the target features are implicitly aligned with the features of unseen source data via the same hypothesis. Furthermore, we propose a new labeling transfer strategy, which separates the target data into two splits based on the confidence of predictions (labeling information), and then employ semi-supervised learning to improve the accuracy of less-confident predictions in the target domain. We denote labeling transfer as SHOT++ if the predictions are obtained by SHOT. Extensive experiments on both digit classification and object recognition tasks show that SHOT and SHOT++ achieve results surpassing or comparable to the state-of-the-arts, demonstrating the effectiveness of our approaches for various visual domain adaptation problems. Code will be available at https://github.com/tim-learn/SHOT-plus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/fbd860a737810264b7e33adc0cf4f6c8ad726893

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Federated Adversarial Debiasing for Fair and Transferable Representations (2021, methodology): “[24] (SHOT) considered the domain adaptation only using the source-domain model which surprisingly outperformed most traditional UDA with source supervisions.”
A Comprehensive Survey on Test-Time Adaptation Under Distribution Shifts (2023, neutral): “centroid-based SHOT [7], [98], BMD [122] pseudo- neighbor-based NRC [123], SSNLL [124] labeling complementary labels LD [125], ATP [126] optimization-based ASL [127], KUDA [128]”