Towards Accurate and Robust Classification in Continuously Transitioning Industrial Sprays with Mixup

TL;DR

This paper demonstrates that Mixup data augmentation effectively improves the accuracy and robustness of deep neural network classifiers in industrial spray applications with limited and ambiguous data, addressing overfitting and class transition challenges.

Contribution

It introduces the use of Mixup for industrial spray classification, showing its effectiveness in handling data scarcity and continuous class transitions.

Findings

Mixup mitigates overfitting on small datasets.

Convex interpolation aligns with continuous class transitions.

Mixup enables accurate classification with few hundred samples.

Abstract

Image classification with deep neural networks has seen a surge of technological breakthroughs with promising applications in areas such as face recognition, medical imaging, and autonomous driving. In engineering problems, however, such as high-speed imaging of engine fuel injector sprays or body paint sprays, deep neural networks face a fundamental challenge related to the availability of adequate and diverse data. Typically, only thousands or sometimes even hundreds of samples are available for training. In addition, the transition between different spray classes is a continuum and requires a high level of domain expertise to label the images accurately. In this work, we used Mixup as an approach to systematically deal with the data scarcity and ambiguous class boundaries found in industrial spray applications. We show that data augmentation can mitigate the over-fitting problem of large neural networks on small data sets, to a certain level, but cannot fundamentally resolve the issue. We discuss how a convex linear interpolation of different classes naturally aligns with the continuous transition between different classes in our application. Our experiments demonstrate Mixup as a simple yet effective method to train an accurate and robust deep neural network classifier with only a few hundred samples.