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
  • [31] Lightweight and Efficient Multimodal Prompt Injection Network for Scene Parsing of Remote Sensing Scene Images
    Li, Yangzhen
    Zhou, Wujie
    Meng, Jiajun
    Yan, Weiqing
    IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2024, 62
  • [32] Hierarchical Parsing Net: Semantic Scene Parsing From Global Scene to Objects
    Shi, Hengcan
    Li, Hongliang
    Meng, Fanman
    Wu, Qingbo
    Xu, Linfeng
    Ngan, King Ngi
    IEEE TRANSACTIONS ON MULTIMEDIA, 2018, 20 (10) : 2670 - 2682
  • [33] AttaNet: Attention-Augmented Network for Fast and Accurate Scene Parsing
    Song, Qi
    Mei, Kangfu
    Huang, Rui
    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 : 2567 - 2575
  • [34] MoE-SPNet: A mixture-of-experts scene parsing network
    Fu, Huan
    Gong, Mingming
    Wang, Chaohui
    Tao, Dacheng
    PATTERN RECOGNITION, 2018, 84 : 226 - 236
  • [35] PSANet: Point-wise Spatial Attention Network for Scene Parsing
    Zhao, Hengshuang
    Zhang, Yi
    Liu, Shu
    Shi, Jianping
    Loy, Chen Change
    Lin, Dahua
    Jia, Jiaya
    COMPUTER VISION - ECCV 2018, PT IX, 2018, 11213 : 270 - 286
  • [36] Learning to transfer focus of graph neural network for scene graph parsing
    Jiang, Junjie
    He, Zaixing
    Zhang, Shuyou
    Zhao, Xinyue
    Tan, Jianrong
    PATTERN RECOGNITION, 2021, 112
  • [37] A Real-Time Scene Parsing Network for Autonomous Maritime Transportation
    Zhou, Rundong
    Gao, Yulong
    Wang, Yang
    Xie, Xingxiang
    Zhao, Xiongwei
    IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, 2023, 72
  • [38] ECNet: An Efficient and Context-Aware Network for Street Scene Parsing
    Jiang, Bin
    Tu, Wenxuan
    Yang, Chao
    Xiao, Yi
    2018 9TH INTERNATIONAL CONFERENCE ON PARALLEL ARCHITECTURES, ALGORITHMS AND PROGRAMMING (PAAP 2018), 2018, : 202 - 210
  • [39] Depth-embedded instance segmentation network for urban scene parsing
    Wang, Zhifan
    Xin, Tong
    Wang, Shidong
    Zhang, Haofeng
    JOURNAL OF INTELLIGENT & FUZZY SYSTEMS, 2022, 42 (03) : 1269 - 1279
  • [40] A Real-Time Scene Parsing Network for Autonomous Maritime Transportation
    Zhou, Rundong
    Gao, Yulong
    Wang, Yang
    Xie, Xingxiang
    Zhao, Xiongwei
    IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, 2023, 72