Impact of Colour on Robustness of Deep Neural Networks

Kanjar De, Marius Pedersen; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops, 2021, pp. 21-30

Convolutional neural networks have become the most widely used tool for computer vision applications like image classification, segmentation, object localization etc. Recent studies have shown that the quality of images has a significant impact on the performance of these deep neural networks and the accuracy of the computer vision tasks gets significantly influenced by the image quality due to the shift in the distribution of the images on which the networks are trained on. Although, the effects of perturbations like image noise, image blur, image contrast, compression artifacts, etc. on the performance of deep neural networks on image classification have been studied, the effects of colour and quality of colour in digital images have been a mostly unexplored direction. One of the biggest challenges is that there is no particular dataset dedicated to colour distortions and colour aspects of images in image classification. The main aim of this paper is to study the impact of colour distortions on the performance of image classification of deep neural networks. Experiments performed using multiple state-of--of-the--the-art deep convolutional neural architectures on a proposed colour distorted dataset are presented in this paper and the impact of colour on image classification task is demonstrated.