Strategies for Robust Image Classification
This work addresses robustness issues in image classification for AI applications, but appears incremental as it focuses on evaluating and improving existing methods.
The paper tackles the problem of image classification models being negatively affected by digitally altered images, and presents training techniques that enhance model robustness and generalization against such alterations.
In this work we evaluate the impact of digitally altered images on the performance of artificial neural networks. We explore factors that negatively affect the ability of an image classification model to produce consistent and accurate results. A model's ability to classify is negatively influenced by alterations to images as a result of digital abnormalities or changes in the physical environment. The focus of this paper is to discover and replicate scenarios that modify the appearance of an image and evaluate them on state-of-the-art machine learning models. Our contributions present various training techniques that enhance a model's ability to generalize and improve robustness against these alterations.