Publication Type

Journal Article

Version

acceptedVersion

Publication Date

3-2022

Abstract

This paper focuses on the domain generalization task where domain knowledge is unavailable, and even worse, only samples from a single domain can be utilized during training. Our motivation originates from the recent progresses in deep neural network (DNN) testing, which has shown that maximizing neuron coverage of DNN can help to explore possible defects of DNN (i.e.,misclassification). More specifically, by treating the DNN as a program and each neuron as a functional point of the code, during the network training we aim to improve the generalization capability by maximizing the neuron coverage of DNN with the gradient similarity regularization between the original and augmented samples. As such, the decision behavior of the DNN is optimized, avoiding the arbitrary neurons that are deleterious for the unseen samples, and leading to the trained DNN that can be better generalized to out-of-distribution samples. Extensive studies on various domain generalization tasks based on both single and multiple domain(s) setting demonstrate the effectiveness of our proposed approach compared with state-of-the-art baseline methods. We also analyze our method by conducting visualization based on network dissection. The results further provide useful evidence on the rationality and effectiveness of our approach.

Keywords

Out-of-distribution, neuron coverage, gradient similarity

Discipline

Artificial Intelligence and Robotics

Publication

IEEE Transactions on Pattern Analysis and Machine Intelligence

First Page

1

Last Page

12

ISSN

0162-8828

Identifier

10.1109/TPAMI.2022.3157441

Publisher

Institute of Electrical and Electronics Engineers

Additional URL

https://doi.org/10.1109/TPAMI.2022.3157441

Share

COinS