Semantic Segmentation and Depth Estimation Based on Residual Attention Mechanism

被引:3
|
作者
Ji, Naihua [1 ]
Dong, Huiqian [1 ]
Meng, Fanyun [1 ]
Pang, Liping [2 ]
机构
[1] Qingdao Univ Technol, Sch Informat & Control Engn, Qingdao 266033, Peoples R China
[2] Dalian Univ Technol, Sch Math Sci, Dalian 116024, Peoples R China
关键词
Semantic segmentation; depth estimation; residual attention; gradient balance;
D O I
10.3390/s23177466
中图分类号
O65 [分析化学];
学科分类号
070302 ; 081704 ;
摘要
Semantic segmentation and depth estimation are crucial components in the field of autonomous driving for scene understanding. Jointly learning these tasks can lead to a better understanding of scenarios. However, using task-specific networks to extract global features from task-shared networks can be inadequate. To address this issue, we propose a multi-task residual attention network (MTRAN) that consists of a global shared network and two attention networks dedicated to semantic segmentation and depth estimation. The convolutional block attention module is used to highlight the global feature map, and residual connections are added to prevent network degradation problems. To ensure manageable task loss and prevent specific tasks from dominating the training process, we introduce a random-weighted strategy into the impartial multi-task learning method. We conduct experiments to demonstrate the effectiveness of the proposed method.
引用
收藏
页数:15
相关论文
共 50 条
  • [31] Attention Mechanism for Improving Facial Landmark Semantic Segmentation
    Kim, Hyungjoon
    Kim, Hyeonwoo
    Cho, Seongkuk
    Hwang, Eenjun
    ADVANCES IN ARTIFICIAL INTELLIGENCE AND APPLIED COGNITIVE COMPUTING, 2021, : 817 - 824
  • [32] Semantic Segmentation With Attention Mechanism for Remote Sensing Images
    Zhao, Qi
    Liu, Jiahui
    Li, Yuewen
    Zhang, Hong
    IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2022, 60
  • [33] DBCAN: DFormer-Based Cross-Attention Network for RGB Depth Semantic Segmentation
    Wu, Aihua
    Fu, Liuxu
    APPLIED SCIENCES-BASEL, 2024, 14 (18):
  • [34] Semantic Segmentation Based on Depth Background Blur
    Li, Hao
    Liu, Changjiang
    Basu, Anup
    APPLIED SCIENCES-BASEL, 2022, 12 (03):
  • [35] Concatenated Residual Attention UNet for Semantic Segmentation of Urban Green Space
    Men, Guoqiang
    He, Guojin
    Wang, Guizhou
    FORESTS, 2021, 12 (11):
  • [36] Joint Semantic Segmentation and Depth Estimation with Deep Convolutional Networks
    Mousavian, Arsalan
    Pirsiavash, Hamed
    Kosecka, Jana
    PROCEEDINGS OF 2016 FOURTH INTERNATIONAL CONFERENCE ON 3D VISION (3DV), 2016, : 611 - 619
  • [37] Semantic Segmentation Network Based on Integral Attention
    Xiong, Siqi
    PROCEEDINGS OF 2024 INTERNATIONAL CONFERENCE ON COMPUTER AND MULTIMEDIA TECHNOLOGY, ICCMT 2024, 2024, : 285 - 288
  • [38] An Attention based Method for Video Semantic Segmentation
    Huang, Yuan
    Huang, Qian
    Huang, Shuai
    Li, Yanping
    TWELFTH INTERNATIONAL CONFERENCE ON DIGITAL IMAGE PROCESSING (ICDIP 2020), 2020, 11519
  • [39] HEIGHT ESTIMATION BASED ON SEMANTIC SEGMENTATION
    Guo, Yuxuan
    Wang, Zhe
    IGARSS 2023 - 2023 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM, 2023, : 766 - 769
  • [40] UNSUPERVISED MONOCULAR DEPTH ESTIMATION BASED ON DUAL ATTENTION MECHANISM AND DEPTH-AWARE LOSS
    Ye, Xinchen
    Zhang, Mingliang
    Xu, Rui
    Zhong, Wei
    Fan, Xin
    Liu, Zhu
    Zhang, Jiaao
    2019 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO (ICME), 2019, : 169 - 174