VITA: A Multi-Source Vicinal Transfer Augmentation Method for Out-of-Distribution Generalization

Minghui Chen1; Cheng Wen2; Feng Zheng1; Fengxiang He3; Ling Shao4

2022

36th AAAI Conference on Artificial Intelligence / 34th Conference on Innovative Applications of Artificial Intelligence / 12th Symposium on Educational Advances in Artificial Intelligence

2159-5399

2374-3468

THIRTY-SIXTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTY-FOURTH CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE / THE TWELVETH SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE

FEB 22-MAR 01, 2022

null,null,ELECTR NETWORK

2275 E BAYSHORE RD, STE 160, PALO ALTO, CA 94303 USA

ASSOC ADVANCEMENT ARTIFICIAL INTELLIGENCE

Invariance to diverse types of image corruption, such as noise, blurring, or colour shifts, is essential to establish robust models in computer vision. Data augmentation has been the major approach in improving the robustness against common corruptions. However, the samples produced by popular augmentation strategies deviate significantly from the underlying data manifold. As a result, performance is skewed toward certain types of corruption. To address this issue, we propose a multi-source vicinal transfer augmentation (VITA) method for generating diverse on-manifold samples. The proposed VITA consists of two complementary parts: tangent transfer and integration of multi-source vicinal samples. The tangent transfer creates initial augmented samples for improving corruption robustness. The integration employs a generative model to characterize the underlying manifold built by vicinal samples, facilitating the generation of on-manifold samples. Our proposed VITA significantly outperforms the current state-of-the-art augmentation methods, demonstrated in extensive experiments on corruption benchmarks.

第一 ; 通讯

英语

CPCI-S

National Natural Science Foundation of China["61972188","62122035"] ; National Key R&D Program of China[2021ZD0111700]

Computer Science

Computer Science, Artificial Intelligence

WOS:000893636200036

Web of Science

1.Southern University of Science and Technology, China
2.The University of Sydney
3.JD Explore Academy, JD.com Inc
4.National Center for Artificial Intelligence, Saudi Data and Artificial Intelligence Authority, Riyadh, Saudi Arabia

Minghui Chen,Cheng Wen,Feng Zheng,et al. VITA: A Multi-Source Vicinal Transfer Augmentation Method for Out-of-Distribution Generalization[C]. 2275 E BAYSHORE RD, STE 160, PALO ALTO, CA 94303 USA:ASSOC ADVANCEMENT ARTIFICIAL INTELLIGENCE,2022.