Random Shadows and Highlights: A new data augmentation method for extreme lighting conditions
This addresses the problem of lighting variations in real-world applications for computer vision practitioners, but it is incremental as it builds on existing data augmentation techniques.
The paper tackles robustness to lighting perturbations in vision systems by proposing Random Shadows and Highlights (RSH), a data augmentation method that creates random shadows and highlights on images, resulting in increased robustness and reduced over-fitting.
In this paper, we propose a new data augmentation method, Random Shadows and Highlights (RSH) to acquire robustness against lighting perturbations. Our method creates random shadows and highlights on images, thus challenging the neural network during the learning process such that it acquires immunity against such input corruptions in real world applications. It is a parameter-learning free method which can be integrated into most vision related learning applications effortlessly. With extensive experimentation, we demonstrate that RSH not only increases the robustness of the models against lighting perturbations, but also reduces over-fitting significantly. Thus RSH should be considered essential for all vision related learning systems. Code is available at: https://github.com/OsamaMazhar/Random-Shadows-Highlights.