Single domain generalization via normalised cross-correlation based convolutions

Abstract

Deep learning techniques often perform poorly in the presence of domain shift, where the test data follows a different distribution than the training data. The most practically desirable approach to address this issue is Single Domain Generalization (S-DG), which aims to train robust models using data from a single source. Prior work on S-DG has primarily focused on using data augmentation techniques to generate diverse training data. In this paper, we explore an alternative approach by investigating the robustness of linear operators, such as convolution and dense layers commonly used in deep learning. We propose a novel operator called "XCNorm"that computes the normalized cross-correlation between weights and an input feature patch. This approach is invariant to both affine shifts and changes in energy within a local feature patch and eliminates the need for commonly used non-linear activation functions. We show that deep neural networks composed of this operator are robust to common semantic distribution shifts. Furthermore, our empirical results on single-domain generalization benchmarks demonstrate that our proposed technique performs comparably to the stateof-the-art methods.

RAS ID

70479

Document Type

Conference Proceeding

Date of Publication

1-3-2024

Funding Information

Australian Government / Ford Motor Company

School

School of Science

Grant Number

LP190100165

Copyright

subscription content

Publisher

IEEE

Comments

Chuah, W., Tennakoon, R., Hoseinnezhad, R., Suter, D., & Bab-Hadiashar, A. (2024). Single domain generalization via normalised cross-correlation based convolutions. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (pp. 1741-1750). https://doi.org/10.1109/WACV57701.2024.00177

Share

 
COinS
 

Link to publisher version (DOI)

10.1109/WACV57701.2024.00177