A Fiber Image Classification Strategy Based on Key Module Localization

Abstract
Traditional image classification approach divides the fiber image into several non overlapping patches during the embedding stage. However, for fine-grained image data, this rough method makes the model lack the ability to model locally within each patch. In addition, the overall proportion of fiber features is always small and densely distributed, and irrelevant interference noise occupies the vast majority of the image. Therefore, this paper proposes a strategy to address the above issues. Firstly, ResNeXt-50 is used to obtain prior information such as inductive bias and translation invariance. Then, by introducing a lightweight Coordinate Attention, focus is achieved on the inside of the fibers rather than background information. Finally, this information is used as input to the Grad-CAM module to accurately identify the fiber interior regions of interest. The proposed approach has significant advantages over multiple strong baseline models on the test data provided by the National Fiber Quality Testing Center, as it can effectively learn fiber skeleton features and achieve finer grained modeling.
Description

CCS Concepts: Computing methodologies → Image processing; Shape analysis; Neural networks

        
@inproceedings{
10.2312:pg.20241323
, booktitle = {
Pacific Graphics Conference Papers and Posters
}, editor = {
Chen, Renjie
and
Ritschel, Tobias
and
Whiting, Emily
}, title = {{
A Fiber Image Classification Strategy Based on Key Module Localization
}}, author = {
Ji, Ya Tu
and
Xue, Xiang
and
Dai, L. J.
and
Yao, M. M.
and
Li, X. M.
and
Liu, Yang
and
Xu, H. T.
and
Ren, Q. D. E. J.
and
Shi, B.
and
Wu, N. E.
and
Lu, M.
and
Xu, X. X.
and
Wang, L.
}, year = {
2024
}, publisher = {
The Eurographics Association
}, ISBN = {
978-3-03868-250-9
}, DOI = {
10.2312/pg.20241323
} }
Citation