Cross Contrasting Feature Perturbation for Domain Generalization

Chenming Li1; Daoan Zhang1; Wenjian Huang1; Jianguo Zhang1,2

10.48550/arXiv.2307.12502

2023-10-01

IEEE International Conference on Computer Vision 2023

1550-5499

979-8-3503-0719-1

2023 IEEE/CVF International Conference on Computer Vision (ICCV)

1327-1337

2023.10

Paris

10662 LOS VAQUEROS CIRCLE, PO BOX 3014, LOS ALAMITOS, CA 90720-1264 USA

IEEE COMPUTER SOC

Domain generalization (DG) aims to learn a robust model from source domains that generalize well on unseen target domains. Recent studies focus on generating novel domain samples or features to diversify distributions complementary to source domains. Yet, these approaches can hardly deal with the restriction that the samples synthesized from various domains can cause semantic distortion. In this paper, we propose an online one-stage Cross Contrasting Feature Perturbation (CCFP) framework to simulate domain shift by generating perturbed features in the latent space while regularizing the model prediction against domain shift. Different from the previous fixed synthesizing strategy, we design modules with learnable feature perturbations and semantic consistency constraints. In contrast to prior work, our method does not use any generative-based models or domain labels. We conduct extensive experiments on a standard DomainBed benchmark with a strict evaluation protocol for a fair comparison. Comprehensive experiments show that our method outperforms the previous state-of-the-art, and quantitative analyses illustrate that our approach can alleviate the domain shift problem in out-of-distribution (OOD) scenarios. https://github.com/hackmebroo/CCFP

Adaptation models Protocols Statistical analysis Perturbation methods Semantics Transportation Predictive models

第一 ; 通讯

英语

CPCI-S

National Key Research and Development Program of China[2021YFF1200800]

Computer Science ; Imaging Science & Photographic Technology

Computer Science, Artificial Intelligence ; Computer Science, Theory & Methods ; Imaging Science & Photographic Technology

WOS:001159644301054

人工提交

正式出版

1.Research Institute of Trustworthy Autonomous Systems and Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen, China
2.Peng Cheng Laboratory, Shenzhen, China

Chenming Li,Daoan Zhang,Wenjian Huang,et al. Cross Contrasting Feature Perturbation for Domain Generalization[C]. 10662 LOS VAQUEROS CIRCLE, PO BOX 3014, LOS ALAMITOS, CA 90720-1264 USA:IEEE COMPUTER SOC,2023:1327-1337.