Litcius/Paper detail

DCL: Dipolar Confidence Learning for Source-Free Unsupervised Domain Adaptation

Qing Tian, Heyang Sun, Shun Peng, Yuhui Zheng, Jun Wan, Zhen Lei

2023IEEE Transactions on Circuits and Systems for Video Technology13 citationsDOI

Abstract

Source-free unsupervised domain adaptation (SFUDA) aims to conduct prediction on the target domain by leveraging knowledge from the well-trained source model. Due to the absence of source data in the SFUDA setting, the existing methods mainly build the target classifier by fine-tuning the source model incorporated with empirical adaptation losses. Although these methods have achieved somewhat promising results, nearly all of them typically suffer from the closed-fitting dilemma that their models are dominantly affected by these easy-to-distinguish instances than those hard-to-distinguish ones, resulting from the absence of the labeled source data. To address aforementioned issues, we propose the Dipolar Confidence Learning (DCL) for SFUDA. Specifically, we conduct positive confidence learning on the samples with standard outputs to avoid overfitting of the model to these samples. In contrast, we perform negative confidence learning for the samples with abnormal outputs to optimize the complementary label, which forces the network to pay more attention to these confusing samples. Furthermore, to achieve more generalized domain alignment, both the confidence-based fuzzy mixup and rotation-based self-supervised learning are respectively constructed to boost the representation ability of the target model. Finally, extensive experiments are conducted to demonstrate the effectiveness and performance superiority of the proposed method.

Topics & Concepts

OverfittingComputer scienceArtificial intelligenceMachine learningClassifier (UML)Domain adaptationUnsupervised learningPattern recognition (psychology)Data miningArtificial neural networkDomain Adaptation and Few-Shot LearningMultimodal Machine Learning ApplicationsMachine Learning and ELM
DCL: Dipolar Confidence Learning for Source-Free Unsupervised Domain Adaptation | Litcius