On the Benefits of Selectivity in Pseudo-Labeling for Unsupervised Multi-Source-Free Domain Adaptation

02/01/2022
by   Maohao Shen, et al.
0

Due to privacy, storage, and other constraints, there is a growing need for unsupervised domain adaptation techniques in machine learning that do not require access to the data used to train a collection of source models. Existing methods for such multi-source-free domain adaptation typically train a target model using supervised techniques in conjunction with pseudo-labels for the target data, which are produced by the available source models. However, we show that assigning pseudo-labels to only a subset of the target data leads to improved performance. In particular, we develop an information-theoretic bound on the generalization error of the resulting target model that demonstrates an inherent bias-variance trade-off controlled by the subset choice. Guided by this analysis, we develop a method that partitions the target data into pseudo-labeled and unlabeled subsets to balance the trade-off. In addition to exploiting the pseudo-labeled subset, our algorithm further leverages the information in the unlabeled subset via a traditional unsupervised domain adaptation feature alignment procedure. Experiments on multiple benchmark datasets demonstrate the superior performance of the proposed method.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/19/2021

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

Domain adaptation typically requires to access source domain data to uti...
research
12/07/2020

Selective Pseudo-Labeling with Reinforcement Learning for Semi-Supervised Domain Adaptation

Recent domain adaptation methods have demonstrated impressive improvemen...
research
05/06/2019

Unsupervised Domain Adaptation using Graph Transduction Games

Unsupervised domain adaptation (UDA) amounts to assigning class labels t...
research
11/24/2021

Source-free unsupervised domain adaptation for cross-modality abdominal multi-organ segmentation

It is valuable to achieve domain adaptation to transfer the learned know...
research
08/01/2019

Pseudo-Labeling Curriculum for Unsupervised Domain Adaptation

To learn target discriminative representations, using pseudo-labels is a...
research
07/19/2023

Unsupervised Accuracy Estimation of Deep Visual Models using Domain-Adaptive Adversarial Perturbation without Source Samples

Deploying deep visual models can lead to performance drops due to the di...
research
04/04/2023

Algorithm-Dependent Bounds for Representation Learning of Multi-Source Domain Adaptation

We use information-theoretic tools to derive a novel analysis of Multi-s...

Please sign up or login with your details

Forgot password? Click here to reset