Recent advances in convolutional neural networks and vision transformers have brought about a revolution in the area of computer vision. Studies have shown that the performance of deep learning-based models is sensitive to image quality. The human visual system is trained to infer semantic information from poor quality images, but deep learning algorithms may find it challenging to perform this task. In this paper, we study the effect of image quality and color parameters on deep learning models trained for the task of semantic segmentation. One of the major challenges in benchmarking robust deep learning-based computer vision models is lack of challenging data covering different quality and colour parameters. In this paper, we have generated data using the subset of the standard benchmark semantic segmentation dataset (ADE20K) with the goal of studying the effect of different quality and colour parameters for the semantic segmentation task. To the best of our knowledge, this is one of the first attempts to benchmark semantic segmentation algorithms under different colour and quality parameters, and this study will motivate further research in this direction.
Recent advances in convolutional neural networks and vision transformers have brought about a revolution in the area of computer vision. Studies have shown that the performance of deep learning-based models is sensitive to image quality. The human visual system is trained to infer semantic information from poor quality images, but deep learning algorithms may find it challenging to perform this task. In this paper, we study the effect of image quality and color parameters on deep learning models trained for the task of semantic segmentation. One of the major challenges in benchmarking robust deep learning-based computer vision models is lack of challenging data covering different quality and colour parameters. In this paper, we have generated data using the subset of the standard benchmark semantic segmentation dataset (ADE20K) with the goal of studying the effect of different quality and colour parameters for the semantic segmentation task. To the best of our knowledge, this is one of the first attempts to benchmark semantic segmentation algorithms under different colour and quality parameters, and this study will motivate further research in this direction.
Our central goal was to create automatic methods for semantic segmentation of human figures in images of fine art paintings. This is a difficult problem because the visual properties and statistics of artwork differ markedly from the natural photographs widely used in research in automatic segmentation. We used a deep neural network to transfer artistic style from paintings across several centuries to modern natural photographs in order to create a large data set of surrogate art images. We then used this data set to train a separate deep network for semantic image segmentation of genuine art images. Such data augmentation led to great improvement in the segmentation of difficult genuine artworks, revealed both qualitatively and quantitatively. Our unique technique of creating surrogate artworks should find wide use in many tasks in the growing field of computational analysis of fine art.
Safe and comfortable travel on the train is only possible on tracks that are in the correct geometric position. For this reason, track tamping machines are used worldwide that carry out this important track maintenance task. Turnout-ta.mping refers to a complex procedure for the improvement and stabilization of the track situation in turnouts, which is carried out usually by experienced operators. This application paper describes the current state of development of a 3D laser line scanner-based sensor system for a new turnout-tamping assistance system, which is able to support and relieve the operator in complex tamping areas. A central task in this context is digital image processing, which carries out so-called semantic segmentation (based on deep learning algorithms) on the basis of 3D scanner data in order to detect essential and critical rail areas fully automatically.