Deep Floor Plan Recognition Using a Multi-Task Network with Room-Boundary-Guided Attention

被引:66
|
作者
Zeng, Zhiliang [1 ]
Li, Xianzhi [1 ]
Yu, Ying Kin [1 ]
Fu, Chi-Wing [1 ]
机构
[1] Chinese Univ Hong Kong, Hong Kong, Peoples R China
关键词
D O I
10.1109/ICCV.2019.00919
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 presents a new approach to recognize elements in floor plan layouts. Besides walls and rooms, we aim to recognize diverse floor plan elements, such as doors, windows and different types of rooms, in the floor layouts. To this end, we model a hierarchy of floor plan elements and design a deep multi-task neural network with two tasks: one to learn to predict room-boundary elements, and the other to predict rooms with types. More importantly, we formulate the room-boundary-guided attention mechanism in our spatial contextual module to carefully take room-boundary features into account to enhance the room-type predictions. Furthermore, we design a cross-and-within-task weighted loss to balance the multi-label tasks and prepare two new datasets for floor plan recognition. Experimental results demonstrate the superiority and effectiveness of our network over the state-of-the-art methods.
引用
收藏
页码:9095 / 9103
页数:9
相关论文
共 50 条
  • [1] Enhanced Pest Recognition Using Multi-Task Deep Learning with the Discriminative Attention Multi-Network
    Dong, Zhaojie
    Wei, Xinyu
    Wu, Yonglin
    Guo, Jiaming
    Zeng, Zhixiong
    APPLIED SCIENCES-BASEL, 2024, 14 (13):
  • [2] MVANet: Multi-Task Guided Multi-View Attention Network for Chinese Food Recognition
    Liang, Haozan
    Wen, Guihua
    Hu, Yang
    Luo, Mingnan
    Yang, Pei
    Xu, Yingxue
    IEEE Transactions on Multimedia, 2021, 23 : 3551 - 3561
  • [3] MVANet: Multi-Task Guided Multi-View Attention Network for Chinese Food Recognition
    Liang, Haozan
    Wen, Guihua
    Hu, Yang
    Luo, Mingnan
    Yang, Pei
    Xu, Yingxue
    IEEE TRANSACTIONS ON MULTIMEDIA, 2021, 23 : 3551 - 3561
  • [4] Automatic floor plan analysis using a boundary attention-based deep network
    Xu, Zhongguo
    Yang, Cheng
    Alheejawi, Salah
    Jha, Naresh
    Mehadi, Syed
    Mandal, Mrinal
    INTERNATIONAL JOURNAL ON DOCUMENT ANALYSIS AND RECOGNITION, 2024, : 19 - 30
  • [5] Multi-Task and Attention Collaborative Network for Facial Emotion Recognition
    Wang, Xiaohua
    Yu, Cong
    Gu, Yu
    Hu, Min
    Ren, Fuji
    IEEJ TRANSACTIONS ON ELECTRICAL AND ELECTRONIC ENGINEERING, 2021, 16 (04) : 568 - 576
  • [6] Multi-Task Collaborative Attention Network for Pedestrian Attribute Recognition
    Cao, Junliang
    Wei, Hua
    Sun, Yongli
    Zhao, Zhifeng
    Wang, Wei
    Sun, Guangze
    Wang, Gang
    2023 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, IJCNN, 2023,
  • [7] IMPROVING SPEECH RECOGNITION IN REVERBERATION USING A ROOM-AWARE DEEP NEURAL NETWORK AND MULTI-TASK LEARNING
    Giri, Ritwik
    Seltzer, Michael L.
    Droppo, Jasha
    Yu, Dong
    2015 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING (ICASSP), 2015, : 5014 - 5018
  • [8] Vehicle recognition using multi-task cascaded network
    Gong, Hua
    Zhang, Yong
    Liu, Fang
    Xu, Ke
    FIFTH SYMPOSIUM ON NOVEL OPTOELECTRONIC DETECTION TECHNOLOGY AND APPLICATION, 2019, 11023
  • [9] Deep Cascaded Attention Network for Multi-task Brain Tumor Segmentation
    Xu, Hai
    Xie, Hongtao
    Liu, Yizhi
    Cheng, Chuandong
    Niu, Chaoshi
    Zhang, Yongdong
    MEDICAL IMAGE COMPUTING AND COMPUTER ASSISTED INTERVENTION - MICCAI 2019, PT III, 2019, 11766 : 420 - 428
  • [10] Towards Complete and Accurate Iris Segmentation Using Deep Multi-Task Attention Network for Non-Cooperative Iris Recognition
    Wang, Caiyong
    Muhammad, Jawad
    Wang, Yunlong
    He, Zhaofeng
    Sun, Zhenan
    IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY, 2020, 15 (15) : 2944 - 2959