Uncertainty-Guided Mixup for Semi-Supervised Domain Adaptation without Source Data

07/14/2021
by   Ning Ma, et al.
0

Present domain adaptation methods usually perform explicit representation alignment by simultaneously accessing the source data and target data. However, the source data are not always available due to the privacy preserving consideration or bandwidth limitation. Source-free domain adaptation aims to solve the above problem by performing domain adaptation without accessing the source data. The adaptation paradigm is receiving more and more attention in recent years, and multiple works have been proposed for unsupervised source-free domain adaptation. However, without utilizing any supervised signal and source data at the adaptation stage, the optimization of the target model is unstable and fragile. To alleviate the problem, we focus on semi-supervised domain adaptation under source-free setting. More specifically, we propose uncertainty-guided Mixup to reduce the representation's intra-domain discrepancy and perform inter-domain alignment without directly accessing the source data. Finally, we conduct extensive semi-supervised domain adaptation experiments on various datasets. Our method outperforms the recent semi-supervised baselines and the unsupervised variant also achieves competitive performance. The experiment codes will be released in the future.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
07/14/2021

Semi-Supervised Hypothesis Transfer for Source-Free Domain Adaptation

Domain Adaptation has been widely used to deal with the distribution shi...
research
07/18/2020

Attract, Perturb, and Explore: Learning a Feature Alignment Network for Semi-supervised Domain Adaptation

Although unsupervised domain adaptation methods have been widely adopted...
research
07/12/2018

Learning-based Regularization for Cardiac Strain Analysis with Ability for Domain Adaptation

Reliable motion estimation and strain analysis using 3D+time echocardiog...
research
02/13/2023

In Search for a Generalizable Method for Source Free Domain Adaptation

Source-free domain adaptation (SFDA) is compelling because it allows ada...
research
01/19/2021

Source-free Domain Adaptation via Distributional Alignment by Matching Batch Normalization Statistics

In this paper, we propose a novel domain adaptation method for the sourc...
research
07/15/2022

Feed-Forward Source-Free Latent Domain Adaptation via Cross-Attention

We study the highly practical but comparatively under-studied problem of...
research
08/13/2020

Alleviating Human-level Shift : A Robust Domain Adaptation Method for Multi-person Pose Estimation

Human pose estimation has been widely studied with much focus on supervi...

Please sign up or login with your details

Forgot password? Click here to reset