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
  • [1] Deep Hierarchical Semantic Segmentation
    Li, Liulei
    Zhou, Tianfei
    Wang, Wenguan
    Li, Jianwu
    Yang, Yi
    2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022), 2022, : 1236 - 1247
  • [2] Semantic Image Segmentation via Deep Parsing Network
    Liu, Ziwei
    Li, Xiaoxiao
    Luo, Ping
    Loy, Chen Change
    Tang, Xiaoou
    2015 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2015, : 1377 - 1385
  • [3] CaveSeg: Deep Semantic Segmentation and Scene Parsing for Autonomous Underwater Cave Exploration
    Abdullah, Adnan (adnanabdullah@ufl.edu), 1600, Institute of Electrical and Electronics Engineers Inc.
  • [4] CaveSeg: Deep Semantic Segmentation and Scene Parsing for Autonomous Underwater Cave Exploration
    Abdullah, Adnan
    Barua, Titon
    Tibbetts, Reagan
    Chen, Zijie
    Islam, Md Jahidul
    Rekleitis, Ioannis
    2024 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION, ICRA 2024, 2024, : 3781 - 3788
  • [5] Deep Hierarchical Learning for 3D Semantic Segmentation
    Li, Chongshou
    Liu, Yuheng
    Li, Xinke
    Zhang, Yuning
    Li, Tianrui
    Yuan, Junsong
    INTERNATIONAL JOURNAL OF COMPUTER VISION, 2025,
  • [6] Semantic Parsing Using Hierarchical Concept Base
    Gao, Yi
    Hong, Caifu
    Wu, Xihong
    INTELLIGENCE SCIENCE AND BIG DATA ENGINEERING: BIG DATA AND MACHINE LEARNING TECHNIQUES, ISCIDE 2015, PT II, 2015, 9243 : 567 - 575
  • [7] Iterative Utterance Segmentation for Neural Semantic Parsing
    Guo, Yinuo
    Lin, Zeqi
    Lou, Jian-Guang
    Zhang, Dongmei
    THIRTY-FIFTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THIRTY-THIRD CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE AND THE ELEVENTH SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2021, 35 : 12937 - 12945
  • [8] Active learning for deep semantic parsing
    Duong, Long
    Afshar, Hadi
    Estival, Dominique
    Pink, Glen
    Cohen, Philip
    Johnson, Mark
    PROCEEDINGS OF THE 56TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, VOL 2, 2018, : 43 - 48
  • [9] Deep Semantic Parsing with Upper Ontologies
    Laukaitis, Algirdas
    Ostasius, Egidijus
    Plikynas, Darius
    APPLIED SCIENCES-BASEL, 2021, 11 (20):
  • [10] A Hierarchical Loss for Semantic Segmentation
    Muller, Bruce
    Smith, William
    VISAPP: PROCEEDINGS OF THE 15TH INTERNATIONAL JOINT CONFERENCE ON COMPUTER VISION, IMAGING AND COMPUTER GRAPHICS THEORY AND APPLICATIONS, VOL 4: VISAPP, 2020, : 260 - 267