Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/142866
Title: Toward achieving robust low-level and high-level scene parsing
Authors: Shuai, Bing
Ding, Henghui
Liu, Ting
Wang, Gang
Jiang, Xudong
Keywords: Engineering::Electrical and electronic engineering
Issue Date: 2018
Source: Shuai, B., Ding, H., Liu, T., Wang, G., & Jiang, X. (2019). Toward achieving robust low-level and high-level scene parsing. IEEE Transactions on Image Processing, 28(3), 1378-1390. doi:10.1109/TIP.2018.2878975
Journal: IEEE Transactions on Image Processing
Abstract: In this paper, we address the challenging task of scene segmentation. We first discuss and compare two widely used approaches to retain detailed spatial information from pretrained CNN - "dilation" and "skip". Then, we demonstrate that the parsing performance of "skip" network can be noticeably improved by modifying the parameterization of skip layers. Furthermore, we introduce a "dense skip" architecture to retain a rich set of low-level information from pre-trained CNN, which is essential to improve the low-level parsing performance. Meanwhile, we propose a convolutional context network (CCN) and place it on top of pre-trained CNNs, which is used to aggregate contexts for high-level feature maps so that robust high-level parsing can be achieved. We name our segmentation network enhanced fully convolutional network (EFCN) based on its significantly enhanced structure over FCN. Extensive experimental studies justify each contribution separately. Without bells and whistles, EFCN achieves state-of-the-arts on segmentation datasets of ADE20K, Pascal Context, SUN-RGBD and Pascal VOC 2012.
URI: https://hdl.handle.net/10356/142866
ISSN: 1057-7149
DOI: 10.1109/TIP.2018.2878975
Rights: © 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. The published version is available at: https://doi.org/10.1109/TIP.2018.2878975
Fulltext Permission: open
Fulltext Availability: With Fulltext
Appears in Collections:EEE Journal Articles

Files in This Item:
File Description SizeFormat 
Toward Achieving Robust Low-Level and High-Level Scene Parsing.pdf2.81 MBAdobe PDFView/Open

Google ScholarTM

Check

Altmetric


Plumx

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.