arXiv Analytics

Sign in

arXiv:1810.04377 [cs.CV]AbstractReferencesReviewsResources

Learning Deep Representations for Semantic Image Parsing: a Comprehensive Overview

Lili Huang, Jiefeng Peng, Ruimao Zhang, Guanbin Li, Liang Lin

Published 2018-10-10Version 1

Semantic image parsing, which refers to the process of decomposing images into semantic regions and constructing the structure representation of the input, has recently aroused widespread interest in the field of computer vision. The recent application of deep representation learning has driven this field into a new stage of development. In this paper, we summarize three aspects of the progress of research on semantic image parsing, i.e., category-level semantic segmentation, instance-level semantic segmentation, and beyond segmentation. Specifically, we first review the general frameworks for each task and introduce the relevant variants. The advantages and limitations of each method are also discussed. Moreover, we present a comprehensive comparison of different benchmark datasets and evaluation metrics. Finally, we explore the future trends and challenges of semantic image parsing.

Related articles: Most relevant | Search more
arXiv:1706.02493 [cs.CV] (Published 2017-06-08)
Learning Deep Representations for Scene Labeling with Guided Supervision
arXiv:1712.00250 [cs.CV] (Published 2017-12-01)
Learning Deep Representations for Word Spotting Under Weak Supervision
arXiv:1510.01553 [cs.CV] (Published 2015-10-06)
Learning Deep Representations of Appearance and Motion for Anomalous Event Detection