An Abstraction of Semantic Segmentation Algorithms

Semantic segmentation is a process of classifying each pixel in the image. Due to its advantages, semantic segmentation is used in many tasks like cancer detection, robot-assisted surgery, satellite images, self-driving car, etc. in this process, accuracy and efficiency are the two crucial goals for this purpose, 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 saving the costs. The diversity of the implemented approaches for semantic segmentation makes it difficult for researchers to achieve a comprehensive view. Due to this, in this paper, an abstract framework for semantic segmentation is offered. This framework consists of 4 blocks that cover the majority of the methods that have been proposed for semantic segmentation. In this paper, we also attempt to compare different approaches and consider the importance of each part in semantic segmentation. Although our proposed framework considers most of the previous methods, maybe a few papers need new blocks.