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
  • [21] Semantic Parsing for Task Oriented Dialog using Hierarchical Representations
    Gupta, Sonal
    Shah, Rushin
    Mohit, Mrinal
    Kumar, Anuj
    Lewis, Michael
    2018 CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING (EMNLP 2018), 2018, : 2787 - 2792
  • [22] Scene Parsing Using Fully Convolutional Network for Semantic Segmentation
    Ali, Nisar
    Ijaz, Ali Zeeshan
    Ali, Raja Hashim
    Ul Abideen, Zain
    Bais, Abdul
    2023 IEEE CANADIAN CONFERENCE ON ELECTRICAL AND COMPUTER ENGINEERING, CCECE, 2023,
  • [23] Averse Deep Semantic Segmentation
    Cruz, Ricardo
    Costa, Joaquim F. Pinto
    Cardoso, Jaime S.
    2019 41ST ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY (EMBC), 2019, : 44 - 47
  • [24] ClothSeg: semantic segmentation network with feature projection for clothing parsing
    Tang, Guangyu
    Yu, Feng
    Li, Huiyin
    Shi, Yankang
    Liu, Li
    Peng, Tao
    Hu, Xinrong
    Jiang, Minghua
    JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION, 2023, 97
  • [25] High resolution scene parsing network based on semantic segmentation
    Shi Jian-Feng
    Xang Ning
    Wang A-Chuan
    CHINESE JOURNAL OF LIQUID CRYSTALS AND DISPLAYS, 2022, 37 (12) : 1598 - 1606
  • [26] HDPA: HIERARCHICAL DEEP PROBABILITY ANALYSIS FOR SCENE PARSING
    Yuan, Yuan
    Jiang, Zhiyu
    Wang, Qi
    2017 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO (ICME), 2017, : 313 - 318
  • [27] Scene sketch semantic segmentation with hierarchical Transformer
    Yang, Jie
    Ke, Aihua
    Yu, Yaoxiang
    Cai, Bo
    KNOWLEDGE-BASED SYSTEMS, 2023, 280
  • [28] Semantic Instance Labeling Leveraging Hierarchical Segmentation
    Hickson, Steven
    Essa, Irfan
    Christensen, Henrik
    2015 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV), 2015, : 1068 - 1075
  • [29] HCNet: Hierarchical Context Network for Semantic Segmentation
    Chong, Yanwen
    Nie, Congchong
    Tao, Yulong
    Chen, Xiaoshu
    Pan, Shaoming
    IEEE ACCESS, 2020, 8 : 179213 - 179223
  • [30] Semantic Image Segmentation with Contextual Hierarchical Models
    Seyedhosseini, Mojtaba
    Tasdizen, Tolga
    IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2016, 38 (05) : 951 - 964