Review the state-of-the-art technologies of semantic segmentation based on deep learning

• Published in: Neurocomputing (Amsterdam) Vol. 493; pp. 626 - 646
• Main Authors: Mo, Yujian, Wu, Yan, Yang, Xinneng, Liu, Feilin, Liao, Yujun
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 07.07.2022
• Subjects: Convolutional neural networks; Deep learning; Domain adaptation; Multi-modal fusion; Real-time; Semantic segmentation; Weakly-supervised; Deep learning; Semantic segmentation; Multi-modal fusion; Real-time; Domain adaptation; Weakly-supervised; Convolutional neural networks

The goal of semantic segmentation is to segment the input image according to semantic information and predict the semantic category of each pixel from a given label set. With the gradual intellectualization of modern life, more and more applications need to infer relevant semantic information from i...