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
  • [21] Automatic Segmentation of Human Depth Map Based on Semantic Segmentation of FCN and Depth Segmentation
    Yuan, Ruifeng
    Hui, Mei
    Liu, Ming
    Zhao, Yuejin
    Dong, Liquan
    Kong, Lingqin
    Chang, Ming
    Cai, Zhi
    TENTH INTERNATIONAL CONFERENCE ON DIGITAL IMAGE PROCESSING (ICDIP 2018), 2018, 10806
  • [22] Semantic Segmentation of Marine Remote Sensing Based on a Cross Direction Attention Mechanism
    Gao, Hao
    Cao, Lin
    Yu, Dingfeng
    Xiong, Xuejun
    Cao, Maoyong
    IEEE ACCESS, 2020, 8 : 142483 - 142494
  • [23] Semantic segmentation based on double pyramid network with improved global attention mechanism
    Xianfeng Ou
    Hanpu Wang
    Guoyun Zhang
    Wujing Li
    Shuixiang Yu
    Applied Intelligence, 2023, 53 : 18898 - 18909
  • [24] Semantic Segmentation Method of Point Cloud Based on Sparse Convolution and Attention Mechanism
    Zuo Meng
    Liu Yiyang
    Cui Hao
    Bai Hongfei
    LASER & OPTOELECTRONICS PROGRESS, 2023, 60 (20)
  • [25] Semantic Segmentation of Plant Leaves Based on Generative Adversarial Network and Attention Mechanism
    Cao, Liying
    Li, Hongda
    Liu, Xuerui
    Chen, Guifen
    Yu, Helong
    IEEE ACCESS, 2022, 10 : 76310 - 76317
  • [26] Semantic segmentation based on double pyramid network with improved global attention mechanism
    Ou, Xianfeng
    Wang, Hanpu
    Zhang, Guoyun
    Li, Wujing
    Yu, Shuixiang
    APPLIED INTELLIGENCE, 2023, 53 (15) : 18898 - 18909
  • [27] Point cloud semantic segmentation network based on graph convolution and attention mechanism
    Yang, Nan
    Wang, Yong
    Zhang, Lei
    Jiang, Bin
    Engineering Applications of Artificial Intelligence, 2025, 141
  • [28] Multiple-Attention Mechanism Network for Semantic Segmentation
    Wang, Dongli
    Xiang, Shengliang
    Zhou, Yan
    Mu, Jinzhen
    Zhou, Haibin
    Irampaye, Richard
    SENSORS, 2022, 22 (12)
  • [29] Discriminative Feature Network Based on a Hierarchical Attention Mechanism for Semantic Hippocampus Segmentation
    Shi, Jiali
    Zhang, Rong
    Guo, Lijun
    Gao, Linlin
    Ma, Huifang
    Wang, Jianhua
    IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS, 2021, 25 (02) : 504 - 513
  • [30] Image Semantic Segmentation Based on Combination of DeepLabV3+ and Attention Mechanism
    Qiu Yunfei
    Wen Jinyan
    LASER & OPTOELECTRONICS PROGRESS, 2022, 59 (04)