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] Semantic Segmentation of Remote Sensing Image Based on Regional Self-Attention Mechanism
    Zhao, Danpei
    Wang, Chenxu
    Gao, Yue
    Shi, Zhenwei
    Xie, Fengying
    IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2022, 19
  • [32] Modeling and Optimization of Semantic Segmentation for Track Bed Foreign Object Based on Attention Mechanism
    Song, Haoran
    Wang, Shengchun
    Gu, Zichen
    Dai, Peng
    Du, Xinyu
    Cheng, Yu
    IEEE ACCESS, 2021, 9 : 86646 - 86656
  • [33] An Unmanned Aerial Vehicle Detection Algorithm Based on Semantic Segmentation and Visual Attention Mechanism
    Zhang, Jiaohao
    Zhang, Qiang
    Shi, Chunlei
    PROCEEDINGS OF 2018 THE 2ND INTERNATIONAL CONFERENCE ON COMPUTER SCIENCE AND ARTIFICIAL INTELLIGENCE (CSAI 2018) / 2018 THE 10TH INTERNATIONAL CONFERENCE ON INFORMATION AND MULTIMEDIA TECHNOLOGY (ICIMT 2018), 2018, : 309 - 313
  • [34] Semantic segmentation model of cotton roots in-situ image based on attention mechanism
    Kang, Jia
    Liu, Liantao
    Zhang, Fucheng
    Shen, Chen
    Wang, Nan
    Shao, Limin
    COMPUTERS AND ELECTRONICS IN AGRICULTURE, 2021, 189
  • [35] Lidar Point Semantic Segmentation Using Dual Attention Mechanism
    Wang, Haosen
    Zhou, Yuan
    Chen, Tiankai
    Qian, Feng
    Ma, Yue
    Wang, Shifeng
    Lu, Bo
    JOURNAL OF RUSSIAN LASER RESEARCH, 2023, 44 (02) : 224 - 234
  • [36] Weed Semantic Segmentation Network Combining Hybrid Attention Mechanism
    Li, Bo
    Ding, Yanhong
    Xue, Yuming
    2024 5TH INTERNATIONAL CONFERENCE ON COMPUTER ENGINEERING AND APPLICATION, ICCEA 2024, 2024, : 620 - 624
  • [37] Lidar Point Semantic Segmentation Using Dual Attention Mechanism
    Haosen Wang
    Yuan Zhou
    Tiankai Chen
    Feng Qian
    Yue Ma
    Shifeng Wang
    Bo Lu
    Journal of Russian Laser Research, 2023, 44 : 224 - 234
  • [38] The strong substructure and feature attention mechanism for image semantic segmentation
    Zhang, Yuhang
    Ren, Hongshuai
    Yang, Wensi
    Wang, Yang
    Ye, Kejiang
    Xu, Cheng-Zhong
    CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE, 2022, 34 (12)
  • [39] CAENet: Efficient Multi-task Learning for Joint Semantic Segmentation and Depth Estimation
    Wang, Luxi
    Li, Yingming
    MACHINE LEARNING AND KNOWLEDGE DISCOVERY IN DATABASES: RESEARCH TRACK, ECML PKDD 2023, PT V, 2023, 14173 : 408 - 425
  • [40] Depth Estimation Method of Light Field Based on Attention Mechanism of Neighborhood Pixel
    Xi, Lin
    Yang, Guo
    Zhao Yongqiang
    Yao Naifu
    ACTA OPTICA SINICA, 2023, 43 (21)