Abstract:Semantic segmentation is a process of classifying each pixel in the image. Due to its advantages, sematic segmentation is used in many tasks such as cancer detection, robot-assisted surgery, satellite image analysis, self-driving car control, etc. In this process, accuracy and efficiency are the two crucial goals for this purpose, and there are several state of the art neural networks. In each method, by employing different techniques, new solutions have been presented for increasing efficiency, accuracy, and reducing the costs. The diversity of the implemented approaches for semantic segmentation makes it difficult for researches to achieve a comprehensive view of the field. To offer a comprehensive view, in this paper, an abstraction model for the task of semantic segmentation is offered. The proposed framework consists of four general blocks that cover the majority of majority of methods that have been proposed for semantic segmentation. We also compare different approaches and consider the importance of each part in the overall performance of a method.