Dual Moving Average Pseudo-Labeling for Source-Free Inductive Domain Adaptation
Hao Yan (Carleton Univeristy),* Yuhong Guo (Carleton University)
The 33rd British Machine Vision Conference
Abstract
Unsupervised domain adaptation reduces the reliance on data annotation in deep learning by adapting knowledge from a source to a target domain. For privacy and effi- ciency concerns, source-free domain adaptation extends unsupervised domain adaptation by adapting a pre-trained source model to an unlabeled target domain without accessing the source data. However, most existing source-free domain adaptation methods to date focus on the transductive setting, where the target training set is also the testing set. In this paper, we address source-free domain adaptation in the more realistic inductive setting, where the target training and testing sets are mutually exclusive. We propose a new semi- supervised fine-tuning method named Dual Moving Average Pseudo-Labeling (DMAPL) for source-free inductive domain adaptation. We first split the unlabeled training set in the target domain into a pseudo-labeled confident subset and an unlabeled less-confident subset according to the prediction confidence scores from the pre-trained source model. Then we propose a soft-label moving-average updating strategy for the unlabeled sub- set based on a moving-average prototypical classifier, which gradually adapts the source model towards the target domain. Experiments show that our proposed method achieves state-of-the-art performance and outperforms previous methods by large margins.Video
Citation
@inproceedings{Yan_2022_BMVC,
author = {Hao Yan and Yuhong Guo},
title = {Dual Moving Average Pseudo-Labeling for Source-Free Inductive Domain Adaptation},
booktitle = {33rd British Machine Vision Conference 2022, {BMVC} 2022, London, UK, November 21-24, 2022},
publisher = {{BMVA} Press},
year = {2022},
url = {https://bmvc2022.mpi-inf.mpg.de/0965.pdf}
}
Copyright © 2022
The British Machine Vision Conference is organised by