Deep Hierarchical Parsing for Semantic Segmentation

被引:0
|
作者
Sharma, Abhishek [1 ]
Tuzel, Oncel [2 ]
Jacobs, David W. [1 ]
机构
[1] Univ Maryland, Dept Comp Sci, College Pk, MD 20742 USA
[2] MERL, Cambridge, MA USA
关键词
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
This paper proposes a learning-based approach to scene parsing inspired by the deep Recursive Context Propagation Network (RCPN). RCPN is a deep feed-forward neural network that utilizes the contextual information from the entire image, through bottom-up followed by top-down context propagation via random binary parse trees. This improves the feature representation of every super-pixel in the image for better classification into semantic categories. We analyze RCPN and propose two novel contributions to further improve the model. We first analyze the learning of RCPN parameters and discover the presence of bypass error paths in the computation graph of RCPN that can hinder contextual propagation. We propose to tackle this problem by including the classification loss of the internal nodes of the random parse trees in the original RCPN loss function. Secondly, we use an MRF on the parse tree nodes to model the hierarchical dependency present in the output. Both modifications provide performance boosts over the original RCPN and the new system achieves state-of-the-art performance on Stanford Background, SIFT-Flow and Daimler urban datasets.
引用
收藏
页码:530 / 538
页数:9
相关论文
共 50 条
  • [41] Deep Video Dehazing With Semantic Segmentation
    Ren, Wenqi
    Zhang, Jingang
    Xu, Xiangyu
    Ma, Lin
    Cao, Xiaochun
    Meng, Gaofeng
    Liu, Wei
    IEEE TRANSACTIONS ON IMAGE PROCESSING, 2019, 28 (04) : 1895 - 1908
  • [42] Deep Structured Features for Semantic Segmentation
    Tschannen, Michael
    Cavigelli, Lukas
    Mentzer, Fabian
    Wiatowski, Thomas
    Benini, Luca
    2017 25TH EUROPEAN SIGNAL PROCESSING CONFERENCE (EUSIPCO), 2017, : 61 - 65
  • [43] Semantic Segmentation: A Zoology of Deep Architectures
    Artola, Aitor
    IMAGE PROCESSING ON LINE, 2023, 13 : 167 - 182
  • [44] Deep Semantic Segmentation of Angiogenesis Images
    Ibragimov, Alisher
    Senotrusova, Sofya
    Markova, Kseniia
    Karpulevich, Evgeny
    Ivanov, Andrei
    Tyshchuk, Elizaveta
    Grebenkina, Polina
    Stepanova, Olga
    Sirotskaya, Anastasia
    Kovaleva, Anastasiia
    Oshkolova, Arina
    Zementova, Maria
    Konstantinova, Viktoriya
    Kogan, Igor
    Selkov, Sergey
    Sokolov, Dmitry
    INTERNATIONAL JOURNAL OF MOLECULAR SCIENCES, 2023, 24 (02)
  • [45] Deep Context Modeling for Semantic Segmentation
    Kien Nguyen
    Fookes, Clinton
    Sridharan, Sridha
    2017 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV 2017), 2017, : 56 - 63
  • [46] Learning deep representations for semantic image parsing: a comprehensive overview
    Huang, Lili
    Peng, Jiefeng
    Zhang, Ruimao
    Li, Guanbin
    Lin, Liang
    FRONTIERS OF COMPUTER SCIENCE, 2018, 12 (05) : 840 - 857
  • [47] Learning deep representations for semantic image parsing: a comprehensive overview
    Lili Huang
    Jiefeng Peng
    Ruimao Zhang
    Guanbin Li
    Liang Lin
    Frontiers of Computer Science, 2018, 12 : 840 - 857
  • [48] Simple Negation Scope Resolution through Deep Parsing: A Semantic Solution to a Semantic Problem
    Packard, Woodley
    Bender, Emily M.
    Read, Jonathon
    Oepen, Stephan
    Dridan, Rebecca
    PROCEEDINGS OF THE 52ND ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, VOL 1, 2014, : 69 - 78
  • [49] Hierarchical semantic segmentation of image scene with object labeling
    Qing Li
    Aihua Liang
    Hongzhe Liu
    EURASIP Journal on Image and Video Processing, 2018
  • [50] Indoor Scene Parsing with Instance Segmentation, Semantic Labeling and Support Relationship Inference
    Zhuo, Wei
    Salzmann, Mathieu
    He, Xuming
    Liu, Miaomiao
    30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017), 2017, : 6269 - 6275