Cargando…
Adversarial and Random Transformations for Robust Domain Adaptation and Generalization
Data augmentation has been widely used to improve generalization in training deep neural networks. Recent works show that using worst-case transformations or adversarial augmentation strategies can significantly improve accuracy and robustness. However, due to the non-differentiable properties of im...
Autores principales: | , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2023
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10256093/ https://www.ncbi.nlm.nih.gov/pubmed/37300000 http://dx.doi.org/10.3390/s23115273 |
_version_ | 1785057030900285440 |
---|---|
author | Xiao, Liang Xu, Jiaolong Zhao, Dawei Shang, Erke Zhu, Qi Dai, Bin |
author_facet | Xiao, Liang Xu, Jiaolong Zhao, Dawei Shang, Erke Zhu, Qi Dai, Bin |
author_sort | Xiao, Liang |
collection | PubMed |
description | Data augmentation has been widely used to improve generalization in training deep neural networks. Recent works show that using worst-case transformations or adversarial augmentation strategies can significantly improve accuracy and robustness. However, due to the non-differentiable properties of image transformations, searching algorithms such as reinforcement learning or evolution strategy have to be applied, which are not computationally practical for large-scale problems. In this work, we show that by simply applying consistency training with random data augmentation, state-of-the-art results on domain adaptation (DA) and generalization (DG) can be obtained. To further improve the accuracy and robustness with adversarial examples, we propose a differentiable adversarial data augmentation method based on spatial transformer networks (STNs). The combined adversarial and random-transformation-based method outperforms the state-of-the-art on multiple DA and DG benchmark datasets. Furthermore, the proposed method shows desirable robustness to corruption, which is also validated on commonly used datasets. |
format | Online Article Text |
id | pubmed-10256093 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2023 |
publisher | MDPI |
record_format | MEDLINE/PubMed |
spelling | pubmed-102560932023-06-10 Adversarial and Random Transformations for Robust Domain Adaptation and Generalization Xiao, Liang Xu, Jiaolong Zhao, Dawei Shang, Erke Zhu, Qi Dai, Bin Sensors (Basel) Article Data augmentation has been widely used to improve generalization in training deep neural networks. Recent works show that using worst-case transformations or adversarial augmentation strategies can significantly improve accuracy and robustness. However, due to the non-differentiable properties of image transformations, searching algorithms such as reinforcement learning or evolution strategy have to be applied, which are not computationally practical for large-scale problems. In this work, we show that by simply applying consistency training with random data augmentation, state-of-the-art results on domain adaptation (DA) and generalization (DG) can be obtained. To further improve the accuracy and robustness with adversarial examples, we propose a differentiable adversarial data augmentation method based on spatial transformer networks (STNs). The combined adversarial and random-transformation-based method outperforms the state-of-the-art on multiple DA and DG benchmark datasets. Furthermore, the proposed method shows desirable robustness to corruption, which is also validated on commonly used datasets. MDPI 2023-06-01 /pmc/articles/PMC10256093/ /pubmed/37300000 http://dx.doi.org/10.3390/s23115273 Text en © 2023 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). |
spellingShingle | Article Xiao, Liang Xu, Jiaolong Zhao, Dawei Shang, Erke Zhu, Qi Dai, Bin Adversarial and Random Transformations for Robust Domain Adaptation and Generalization |
title | Adversarial and Random Transformations for Robust Domain Adaptation and Generalization |
title_full | Adversarial and Random Transformations for Robust Domain Adaptation and Generalization |
title_fullStr | Adversarial and Random Transformations for Robust Domain Adaptation and Generalization |
title_full_unstemmed | Adversarial and Random Transformations for Robust Domain Adaptation and Generalization |
title_short | Adversarial and Random Transformations for Robust Domain Adaptation and Generalization |
title_sort | adversarial and random transformations for robust domain adaptation and generalization |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10256093/ https://www.ncbi.nlm.nih.gov/pubmed/37300000 http://dx.doi.org/10.3390/s23115273 |
work_keys_str_mv | AT xiaoliang adversarialandrandomtransformationsforrobustdomainadaptationandgeneralization AT xujiaolong adversarialandrandomtransformationsforrobustdomainadaptationandgeneralization AT zhaodawei adversarialandrandomtransformationsforrobustdomainadaptationandgeneralization AT shangerke adversarialandrandomtransformationsforrobustdomainadaptationandgeneralization AT zhuqi adversarialandrandomtransformationsforrobustdomainadaptationandgeneralization AT daibin adversarialandrandomtransformationsforrobustdomainadaptationandgeneralization |