English
Related papers

Related papers: CycleMix: Mixing Source Domains for Domain General…

200 papers

Domain generalization (DG) aims to learn predictive models that can generalize to unseen domains. Most existing DG approaches focus on learning domain-invariant representations under the assumption of conditional distribution shift (i.e.,…

Machine Learning · Computer Science 2026-02-03 Jewon Yeom , Kyubyung Chae , Hyunggyu Lim , Yoonna Oh , Dongyoon Yang , Taesup Kim

Unsupervised image-to-image translation methods such as CycleGAN learn to convert images from one domain to another using unpaired training data sets from different domains. Unfortunately, these approaches still require centrally collected…

Computer Vision and Pattern Recognition · Computer Science 2021-06-18 Joonyoung Song , Jong Chul Ye

Domain generalization (DG) aims to improve the generalizability of computer vision models toward distribution shifts. The mainstream DG methods focus on learning domain invariance, however, such methods overlook the potential inherent in…

Computer Vision and Pattern Recognition · Computer Science 2025-04-04 Shaocong Long , Qianyu Zhou , Xiangtai Li , Chenhao Ying , Yunhai Tong , Lizhuang Ma , Yuan Luo , Dacheng Tao

This year alone has seen unprecedented leaps in the area of learning-based image translation, namely CycleGAN, by Zhu et al. But experiments so far have been tailored to merely two domains at a time, and scaling them to more would require…

Computer Vision and Pattern Recognition · Computer Science 2017-12-20 Asha Anoosheh , Eirikur Agustsson , Radu Timofte , Luc Van Gool

Modern deep neural networks suffer from performance degradation when evaluated on testing data under different distributions from training data. Domain generalization aims at tackling this problem by learning transferable knowledge from…

Computer Vision and Pattern Recognition · Computer Science 2021-05-25 Qinwei Xu , Ruipeng Zhang , Ya Zhang , Yanfeng Wang , Qi Tian

Machine learning models fail to perform when facing out-of-distribution (OOD) domains, a challenging task known as domain generalization (DG). In this work, we develop a novel DG training strategy, we call PGrad, to learn a robust gradient…

Machine Learning · Computer Science 2023-05-03 Zhe Wang , Jake Grigsby , Yanjun Qi

There are many computer vision applications including object segmentation, classification, object detection, and reconstruction for which machine learning (ML) shows state-of-the-art performance. Nowadays, we can build ML tools for such…

Computer Vision and Pattern Recognition · Computer Science 2023-08-29 Hamza Riaz , Alan F. Smeaton

We tackle the challenging problem of single-source domain generalization (DG) for medical image segmentation, where we train a network on one domain (e.g., CT) and directly apply it to a different domain (e.g., MR) without adapting the…

Computer Vision and Pattern Recognition · Computer Science 2026-04-29 Franz Thaler , Martin Urschler , Mateusz Kozinski , Matthias AF Gsell , Gernot Plank , Darko Stern

Training a deep learning model with artificially generated data can be an alternative when training data are scarce, yet it suffers from poor generalization performance due to a large domain gap. In this paper, we characterize the domain…

Computer Vision and Pattern Recognition · Computer Science 2023-02-21 Gilhyun Nam , Gyeongjae Choi , Kyungmin Lee

While deep generative models~(DGMs) have demonstrated remarkable success in capturing complex data distributions, they consistently fail to learn constraints that encode domain knowledge and thus require constraint integration. Existing…

Machine Learning · Computer Science 2025-02-13 Ruoyan Li , Dipti Ranjan Sahu , Guy Van den Broeck , Zhe Zeng

The performance of existing underwater object detection methods degrades seriously when facing domain shift caused by complicated underwater environments. Due to the limitation of the number of domains in the dataset, deep detectors easily…

Computer Vision and Pattern Recognition · Computer Science 2023-01-19 Yang Chen , Pinhao Song , Hong Liu , Linhui Dai , Xiaochuan Zhang , Runwei Ding , Shengquan Li

Domain Generalized Semantic Segmentation (DGSS) seeks to utilize source domain data exclusively to enhance the generalization of semantic segmentation across unknown target domains. Prevailing studies predominantly concentrate on feature…

Computer Vision and Pattern Recognition · Computer Science 2024-12-17 Hongwei Niu , Linhuang Xie , Jianghang Lin , Shengchuan Zhang

Domain generalization approaches aim to learn a domain invariant prediction model for unknown target domains from multiple training source domains with different distributions. Significant efforts have recently been committed to broad…

Computer Vision and Pattern Recognition · Computer Science 2021-08-23 Mohammad Mahfujur Rahman , Clinton Fookes , Sridha Sridharan

Data augmentation is one of the most effective techniques for regularizing deep learning models and improving their recognition performance in a variety of tasks and domains. However, this holds for standard in-domain settings, in which the…

Though remarkable progress has been achieved in various vision tasks, deep neural networks still suffer obvious performance degradation when tested in out-of-distribution scenarios. We argue that the feature statistics (mean and standard…

Computer Vision and Pattern Recognition · Computer Science 2022-04-25 Xiaotong Li , Yongxing Dai , Yixiao Ge , Jun Liu , Ying Shan , Ling-Yu Duan

Generative adversarial networks (GANs) have shown great success in applications such as image generation and inpainting. However, they typically require large datasets, which are often not available, especially in the context of prediction…

Machine Learning · Computer Science 2020-01-31 Daniel Stoller , Sebastian Ewert , Simon Dixon

With the increasing utilization of deep learning in outdoor settings, its robustness needs to be enhanced to preserve accuracy in the face of distribution shifts, such as compression artifacts. Data augmentation is a widely used technique…

Computer Vision and Pattern Recognition · Computer Science 2023-10-03 Shohei Enomoto , Monikka Roslianna Busto , Takeharu Eda

Aiming at recognizing images of the same person across distinct camera views, person re-identification (re-ID) has been among active research topics in computer vision. Most existing re-ID works require collection of a large amount of…

Computer Vision and Pattern Recognition · Computer Science 2020-10-20 Ci-Siang Lin , Yuan-Chia Cheng , Yu-Chiang Frank Wang

Medical images are usually collected from multiple domains, leading to domain shifts that impair the performance of medical image segmentation models. Domain Generalization (DG) aims to address this issue by training a robust model with…

Image and Video Processing · Electrical Eng. & Systems 2025-06-13 Xi Chen , Zhiqiang Shen , Peng Cao , Jinzhu Yang , Osmar R. Zaiane

The topic of generalizing machine learning models learned on a collection of source domains to unknown target domains is challenging. While many domain generalization (DG) methods have achieved promising results, they primarily rely on the…

Computer Vision and Pattern Recognition · Computer Science 2022-05-20 Xingchen Zhao , Chang Liu , Anthony Sicilia , Seong Jae Hwang , Yun Fu