Manifestation of Image Contrast in Deep Networks
This addresses a robustness issue in machine vision for applications where lighting conditions vary, though it is incremental as it builds on existing augmentation techniques.
The study investigated how image contrast affects deep convolutional networks, finding that low-contrast images cause significant accuracy drops in state-of-the-art models, and demonstrated that contrast-augmentation during training can achieve contrast invariance without negative side effects.
Contrast is subject to dramatic changes across the visual field, depending on the source of light and scene configurations. Hence, the human visual system has evolved to be more sensitive to contrast than absolute luminance. This feature is equally desired for machine vision: the ability to recognise patterns even when aspects of them are transformed due to variation in local and global contrast. In this work, we thoroughly investigate the impact of image contrast on prominent deep convolutional networks, both during the training and testing phase. The results of conducted experiments testify to an evident deterioration in the accuracy of all state-of-the-art networks at low-contrast images. We demonstrate that "contrast-augmentation" is a sufficient condition to endow a network with invariance to contrast. This practice shows no negative side effects, quite the contrary, it might allow a model to refrain from other illuminance related over-fittings. This ability can also be achieved by a short fine-tuning procedure, which opens new lines of investigation on mechanisms involved in two networks whose weights are over 99.9% correlated, yet astonishingly produce utterly different outcomes. Our further analysis suggests that the optimisation algorithm is an influential factor, however with a significantly lower effect; and while the choice of an architecture manifests a negligible impact on this phenomenon, the first layers appear to be more critical.