Survey of recent progress in semantic image segmentation with CNNs

• Published in: Science China. Information sciences Vol. 61; no. 5; p. 051101
• Main Authors: Geng, Qichuan, Zhou, Zhong, Cao, Xiaochun
• Format: Journal Article
• Language: English
• Published: Beijing Science China Press 01.05.2018; Springer Nature B.V
• Subjects: Artificial neural networks; Classification; Computer Science; Computer vision; Datasets; Face recognition; Image classification; Image segmentation; Information Systems and Communication Service; Neural networks; Object recognition; Review; Science; Semantic segmentation; Semantics; Statistical methods; Pascal VOC 2012 challenge; CNN; semantic image segmentation; multi-granularity features; construction of contextual relationships
• ISSN: 1674-733X; 1869-1919
• DOI: 10.1007/s11432-017-9189-6

In recent years, convolutional neural networks (CNNs) are leading the way in many computer vision tasks, such as image classification, object detection, and face recognition. In order to produce more refined semantic image segmentation, we survey the powerful CNNs and novel elaborate layers, structures and strategies, especially including those that have achieved the state-of-the-art results on the Pascal VOC 2012 semantic segmentation challenge. Moreover, we discuss their different working stages and various mechanisms to utilize the structural and contextual information in the image and feature spaces. Finally, combining some popular underlying referential methods in homologous problems, we propose several possible directions and approaches to incorporate existing effective methods as components to enhance CNNs for the segmentation of specific semantic objects.