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
  • [1] HYBRIDNET FOR DEPTH ESTIMATION AND SEMANTIC SEGMENTATION
    Sanchez-Escobedo, Dalila
    Lin, Xiao
    Casas, Josep R.
    Pardas, Montse
    2018 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2018, : 1563 - 1567
  • [2] Semantic Segmentation Leveraging Simultaneous Depth Estimation
    Sun, Wenbo
    Gao, Zhi
    Cui, Jinqiang
    Ramesh, Bharath
    Zhang, Bin
    Li, Ziyao
    SENSORS, 2021, 21 (03) : 1 - 19
  • [3] A Semantic Segmentation Algorithm Based on Improved Attention Mechanism
    Chen, Chunyu
    Wu, Xinsheng
    Chen, An
    2020 INTERNATIONAL SYMPOSIUM ON AUTONOMOUS SYSTEMS (ISAS), 2020, : 244 - 248
  • [4] Depth estimation of supervised monocular images based on semantic segmentation
    Wang, Qi
    Piao, Yan
    JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION, 2023, 90
  • [5] Depth and Pixel-Distance Based Attention for Outdoor Semantic Segmentation
    Woo, Myung-Woo
    Seo, Seung-Woo
    IEEE ACCESS, 2023, 11 : 8824 - 8833
  • [6] Semantic Segmentation of Road Scene Based on the Mechanism of Adversarial Attention
    Jia-Bin, Tan
    Jing-Sheng, Lei
    FOURTEENTH INTERNATIONAL CONFERENCE ON GRAPHICS AND IMAGE PROCESSING, ICGIP 2022, 2022, 12705
  • [7] Semantic Segmentation Algorithm of Night Images Based on Attention Mechanism
    Xie, Xiaona
    Xu, Zhiyong
    Jiang, Tao
    Yuan, JianYing
    Chang, Zhengwei
    Zhang, Linghao
    JOURNAL OF CIRCUITS SYSTEMS AND COMPUTERS, 2023, 32 (15)
  • [8] The Application of Attention Mechanism in Semantic Image Segmentation
    Qin, Qi
    Hu, Xijing
    PROCEEDINGS OF 2020 IEEE 4TH INFORMATION TECHNOLOGY, NETWORKING, ELECTRONIC AND AUTOMATION CONTROL CONFERENCE (ITNEC 2020), 2020, : 1573 - 1580
  • [9] Attention Based Quick Network With Optical Flow Estimation for Semantic Segmentation
    Cai, Jiawen
    Liu, Yarong
    Qin, Pan
    IEEE ACCESS, 2023, 11 : 12402 - 12413
  • [10] Semantic segmentation algorithm based on class feature attention mechanism fusion
    Chen, Na
    Zhang, Rong-fen
    Liu, Yu-hong
    Li, Li
    Zhang, Wen-wen
    CHINESE JOURNAL OF LIQUID CRYSTALS AND DISPLAYS, 2023, 38 (02) : 236 - 244