Exploring context with deep structured models for semantic segmentation

• Main Authors: van den Hengel, Anton, Lin, Guosheng, Shen, Chunhua, Reid, Ian
• 其他作者: School of Computer Science and Engineering
• 格式: Article
• 語言: English
• 出版: 2019
• 主題: Convolutional Neural Networks; DRNTU::Engineering::Computer science and engineering; Semantic Segmentation
• 在線閱讀: https://hdl.handle.net/10356/106417; http://hdl.handle.net/10220/47945; http://dx.doi.org/10.1109/TPAMI.2017.2708714

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...