Image classification and training with severe data loss

Dillon Marquard; Kyle Wright; Roummel Marcia

doi:10.1117/12.2633172

3 October 2022 Image classification and training with severe data loss

Dillon Marquard, Kyle Wright, Roummel Marcia

Proceedings Volume 12227, Applications of Machine Learning 2022; 122270T (2022) https://doi.org/10.1117/12.2633172
Event: SPIE Optical Engineering + Applications, 2022, San Diego, California, United States

Conference Poster

Abstract

Image classification forms an important class of problems in machine learning and is widely used in many realworld applications, such as medicine, ecology, astronomy, and defense. Convolutional neural networks (CNNs) are machine learning techniques designed for inputs with grid structures, e.g., images, whose features are spatially correlated. As such, CNNs have been demonstrated to be highly effective approaches for many image classification problems and have consistently outperformed other approaches in many image classification and object detection competitions. A particular challenge involved in using machine learning for classifying images is measurement data loss in the form of missing pixels, which occurs in settings where scene occlusions are present or where the photodetectors in the imaging system are partially damaged. In such cases, the performance of CNN models tends to deteriorate or becomes unreliable even when the perturbations to the input image are small. In this work, we investigate techniques for improving the performance of CNN models for image classification with missing data. In particular, we explore training on a variety of data alterations that mimic data loss for producing more robust classifiers. By optimizing the categorical cross-entropy loss function, we demonstrate through numerical experiments on the MNIST dataset that training with these synthetic alterations can enhance the classification accuracy of our CNN models.

Citation Download Citation

Dillon Marquard, Kyle Wright, and Roummel Marcia "Image classification and training with severe data loss", Proc. SPIE 12227, Applications of Machine Learning 2022, 122270T (3 October 2022); https://doi.org/10.1117/12.2633172

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available