Learnable Data Augmentation for One-Shot Unsupervised Domain Adaptation
Julio Ivan Davila Carrazco (Istituto Italiano di Tecnologia),* Pietro Morerio (Istituto Italiano di Tecnologia), Alessio Del Bue (Istituto Italiano di Tecnologia (IIT)), Vittorio Murino (Istituto Italiano di Tecnologia)
The 34th British Machine Vision Conference
Abstract
This paper presents a classification framework based on learnable data augmentation to tackle the One-Shot Unsupervised Domain Adaptation (OS-UDA) problem. OS-UDA is the most challenging setting in Domain Adaptation, as only one single unlabeled target sample is assumed to be available for model adaptation. Driven by such single sample, our method LearnAug-UDA learns how to augment source data, making it perceptually similar to the target. As a result, a classifier trained on such augmented data will generalize well for the target domain. To achieve this, we designed an encoder-decoder architecture that exploits a perceptual loss and style transfer strategies to augment the source data. Our method achieves state-of-the-art performance on two well-known Domain Adaptation benchmarks, DomainNet and VisDA. The project code is available at https://github.com/IIT-PAVIS/LearnAug-UDAVideo
Citation
@inproceedings{Carrazco_2023_BMVC,
author = {Julio Ivan Davila Carrazco and Pietro Morerio and Alessio Del Bue and Vittorio Murino},
title = {Learnable Data Augmentation for One-Shot Unsupervised Domain Adaptation},
booktitle = {34th British Machine Vision Conference 2023, {BMVC} 2023, Aberdeen, UK, November 20-24, 2023},
publisher = {BMVA},
year = {2023},
url = {https://papers.bmvc2023.org/0752.pdf}
}
Copyright © 2023
The British Machine Vision Conference is organised by