Consensus Feature Network for Scene Parsing

被引:1
|
作者
Wu, Tianyi [1 ,2 ]
Tang, Sheng [3 ,4 ]
Zhang, Rui [3 ,4 ]
Guo, Guodong [1 ,2 ]
机构
[1] Inst Deep Learning, Baidu Res, Beijing 100085, Peoples R China
[2] Natl Engn Lab Deep Learning Technol & Applicat, Beijing 100085, Peoples R China
[3] Chinese Acad Sci, Insititue Comp Technol, Key Lab Intelligent Informat Proc, Beijing 100190, Peoples R China
[4] Univ Chinese Acad Sci, Beijing 100049, Peoples R China
基金
中国国家自然科学基金;
关键词
Transforms; Semantics; Convolution; Feature extraction; Training; Network architecture; Information and communication technology; Scene Parsing; Instance Consensus Transform; Category Consensus Transform; SEGMENTATION; IMAGES;
D O I
10.1109/TMM.2021.3094333
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Scene parsing is challenging as it aims to assign one of the semantic categories to each pixel in scene images. Thus, pixel-level features are desired for scene parsing. However, classification networks are dominated by the discriminative portion, so directly applying classification networks to scene parsing will result in inconsistent parsing predictions within one instance and among instances of the same category. To address this problem, we propose two transform units to learn pixel-level consensus features. One is an Instance Consensus Transform (ICT) unit to learn the instance-level consensus features by aggregating features within the same instance. The other is a Category Consensus Transform (CCT) unit to pursue category-level consensus features through keeping the consensus of features among instances of the same category in scene images. The proposed ICT and CCT units are lightweight, data-driven and end-to-end trainable. The features learned by the two units are more coherent in both instance-level and category-level. Furthermore, we present the Consensus Feature Network (CFNet) based on the proposed ICT and CCT units, and demonstrate the effectiveness of each component in our method by performing extensive ablation experiments. Finally, our proposed CFNet achieves competitive performance on four datasets, including Cityscapes, Pascal Context, CamVid, and COCO Stuff.
引用
收藏
页码:3208 / 3217
页数:10
相关论文
共 50 条
  • [41] 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
  • [42] Multiscale Context-Aware Feature Fusion Network for Land-Cover Classification of Urban Scene Imagery
    Siddique, Abubakar
    Li, Zhengzhou
    Azeem, Abdullah
    Zhang, Yuting
    Xu, Bitong
    IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2023, 16 : 8475 - 8491
  • [43] A Confounder-Free Fusion Network for Aerial Image Scene Feature Representation
    Xiong, Wei
    Xiong, Zhenyu
    Cui, Yaqi
    IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2022, 15 : 5440 - 5454
  • [44] SMALL COMPONENTS PARSING VIA MULTI-FEATURE FUSION NETWORK
    Leng, Zhiying
    Lu, Yang
    Liang, Xiaohui
    2020 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO (ICME), 2020,
  • [45] Edge-Aware Guidance Fusion Network for RGB-Thermal Scene Parsing
    Zhou, Wujie
    Dong, Shaohua
    Xu, Caie
    Qian, Yaguan
    THIRTY-SIXTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTY-FOURTH CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE / THE TWELVETH SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2022, : 3571 - 3579
  • [46] An Automatic Glioma Segmentation System Using a Multilevel Attention Pyramid Scene Parsing Network
    Zhang, Zhenyu
    Gao, Shouwei
    Huang, Zheng
    CURRENT MEDICAL IMAGING, 2021, 17 (06) : 751 - 761
  • [47] Nonparametric scene parsing in the images of buildings
    Talebi, Mehdi
    Vafaei, Abbas
    Monadjemi, S. Amirhassan
    COMPUTERS & ELECTRICAL ENGINEERING, 2018, 70 : 777 - 788
  • [48] GEBNet: Graph-Enhancement Branch Network for RGB-T Scene Parsing
    Dong, Shaohua
    Zhou, Wujie
    Qian, Xiaohong
    Yu, Lu
    IEEE SIGNAL PROCESSING LETTERS, 2022, 29 : 2273 - 2277
  • [49] Hierarchical Scene Parsing by Weakly Supervised Learning with Image Descriptions
    Zhang, Ruimao
    Lin, Liang
    Wang, Guangrun
    Wang, Meng
    Zuo, Wangmeng
    IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2019, 41 (03) : 596 - 610
  • [50] Text Enhancement Network for Cross-Domain Scene Text Detection
    Deng, Jinhong
    Luo, Xiulian
    Zheng, Jiawen
    Dang, Wanli
    Li, Wen
    IEEE SIGNAL PROCESSING LETTERS, 2022, 29 : 2203 - 2207