Exploring context with deep structured models for semantic segmentation

• Main Authors: van den Hengel, Anton, Lin, Guosheng, Shen, Chunhua, Reid, Ian
• Other Authors: School of Computer Science and Engineering
• Format: Article
• Language: English
• Published: 2019
• Subjects: Convolutional Neural Networks; DRNTU::Engineering::Computer science and engineering; Semantic Segmentation
• Online Access: https://hdl.handle.net/10356/106417; http://hdl.handle.net/10220/47945; http://dx.doi.org/10.1109/TPAMI.2017.2708714
• Institution: Nanyang Technological University

State-of-the-art semantic image segmentation methods are mostly based on training deep convolutional neural networks (CNNs). In this work, we proffer to improve semantic segmentation with the use of contextual information. In particular, we explore patch-patch context and patch-background context in...