Convolutional Neural Networks for Semantic Segmentation: A Recent Survey

Abstract

Image segmentation is one of the most researched problems in computer vision. Various algorithms and techniques in artificial intelligence and machine learning were used and experimented with. Recently deep learning models have improved state-of-the-art performance on most of the well-known semantic segmentation datasets. In this work, we present a comprehensive study of 9 of the most recent models and methods in semantic segmentation. We experiment with these models on different datasets and draw our conclusions.