Generation, augmentation, and alignment: A pseudo-source domain based method for source-free domain adaptation

by   Yuntao Du, et al.

Conventional unsupervised domain adaptation (UDA) methods need to access both labeled source samples and unlabeled target samples simultaneously to train the model. While in some scenarios, the source samples are not available for the target domain due to data privacy and safety. To overcome this challenge, recently, source-free domain adaptation (SFDA) has attracted the attention of researchers, where both a trained source model and unlabeled target samples are given. Existing SFDA methods either adopt a pseudo-label based strategy or generate more samples. However, these methods do not explicitly reduce the distribution shift across domains, which is the key to a good adaptation. Although there are no source samples available, fortunately, we find that some target samples are very similar to the source domain and can be used to approximate the source domain. This approximated domain is denoted as the pseudo-source domain. In this paper, inspired by this observation, we propose a novel method based on the pseudo-source domain. The proposed method firstly generates and augments the pseudo-source domain, and then employs distribution alignment with four novel losses based on pseudo-label based strategy. Among them, a domain adversarial loss is introduced between the pseudo-source domain the remaining target domain to reduce the distribution shift. The results on three real-world datasets verify the effectiveness of the proposed method.


page 1

page 2

page 3

page 4


Domain-Augmented Domain Adaptation

Unsupervised domain adaptation (UDA) enables knowledge transfer from the...

Source-Free Domain Adaptive Fundus Image Segmentation with Denoised Pseudo-Labeling

Domain adaptation typically requires to access source domain data to uti...

Boosting Unsupervised Domain Adaptation with Soft Pseudo-label and Curriculum Learning

By leveraging data from a fully labeled source domain, unsupervised doma...

Improving Pseudo Labels With Intra-Class Similarity for Unsupervised Domain Adaptation

Unsupervised domain adaptation (UDA) transfers knowledge from a label-ri...

Your Classifier can Secretly Suffice Multi-Source Domain Adaptation

Multi-Source Domain Adaptation (MSDA) deals with the transfer of task kn...

Reconciling a Centroid-Hypothesis Conflict in Source-Free Domain Adaptation

Source-free domain adaptation (SFDA) aims to transfer knowledge learned ...

Multi-Source Domain Adaptation for Object Detection

To reduce annotation labor associated with object detection, an increasi...

Please sign up or login with your details

Forgot password? Click here to reset