Traffic Scene Semantic Segmentation Algorithm with Knowledge Distillation of Multi-level Features Guided by Boundary Perception

被引：0
作者：
Xie, Xinlin [1 ,2 ]
Duan, Zeyun [1 ,2 ]
Luo, Chenyan [1 ,2 ]
Xie, Gang [1 ,2 ]
机构：
[1] School of Electronic Information Engineering, Taiyuan University of Science and Technology, Taiyuan
[2] Shanxi Key Laboratory of Advanced Control and Equipment Intelligence, Taiyuan University of Science and Technology, Taiyuan
来源：
Moshi Shibie yu Rengong Zhineng/Pattern Recognition and Artificial Intelligence | 2024年 / 37卷 / 09期
基金：
中国国家自然科学基金;
关键词：
Attention Mechanism; Deep Learning; Knowledge Distillation; Semantic Segmentation; Traffic Scene;
D O I：
10.16451/j.cnki.issn1003-6059.202409002
中图分类号：
学科分类号：
摘要：
To solve the problems of object detail information loss and large model parameters in traffic scenes, a traffic scene semantic segmentation algorithm with knowledge distillation of multi-level features guided by boundary perception is proposed. The proposed algorithm can smooth the object segmentation boundaries with fewer parameters. First, the adaptive fusing multi-level feature module is constructed to integrate the multi-level features of deep semantic information and shallow spatial information. The object boundary information and object subject information are highlighted selectively. Second, an interactive attention fusion module is proposed to model the long-range dependencies in spatial and channel dimensions, enhancing the information interaction capabilities between different dimensions. Finally, a boundary loss function based on candidate boundaries is proposed to construct a boundary knowledge distillation network based on detail awareness and transfer boundary information from complex teacher networks. Experiments on the traffic scene datasets Cityscapes and CamVid demonstrate that the proposed algorithm achieves a lightweight model while gaining positive segmentation performance, maintaining significant advantages in dealing with small and slender objects. © 2024 Science Press. All rights reserved.
引用
收藏
页码：770 / 785
页数：15
相关论文
共 34 条
  • [1] PAN H H, HONG Y D, SUN W C, Et al., Deep Dual-Resolution Networks for Real-Time and Accurate Semantic Segmentation of Traffic Scenes, IEEE Transactions on Intelligent Transportation Systems, 24, 3, pp. 3448-3460, (2023)
  • [2] HU X G, JING L Y, SEHAR U., Joint Pyramid Attention Network for Real-Time Semantic Segmentation of Urban Scenes, Applied Intelligence, 52, 1, pp. 580-594, (2022)
  • [3] JIANG B, TU W X, YANG C, Et al., Semantic Segmentation Method for Complex Traffic Scene Based on DenseNet, Pattern Recognition and Artificial Intelligence, 32, 5, pp. 472-480, (2019)
  • [4] XIAO X Y, ZHAO Y Q, ZHANG F, Et al., BASeg: Boundary Aware Semantic Segmentation for Autonomous Driving, Neural Networks, 157, pp. 460-470, (2023)
  • [5] GAO G W, XU G A, LI J C., FBSNet: A Fast Bilateral Symmetrical Network for Real-Time Semantic Segmentation, IEEE Transactions on Multimedia, 25, pp. 3273-3283, (2023)
  • [6] ZHANG A Q, KANG Y X, WU Z Y, Et al., Semantic Segmentation Network of Pathological Images of Liver Tissue Based on the Multi-scale Feature and Attention Mechanism, Pattern Recognition and Artificial Intelligence, 34, 4, pp. 375-384, (2021)
  • [7] FU J, LIU J, TIAN H J, Et al., Dual Attention Network for Scene Segmentation, Proc of the IEEE / CVF Conference on Computer Vision and Pattern Recognition, pp. 3141-3149, (2019)
  • [8] DAI Y M, GIESEKE F, OEHMCKE S, Et al., Attentional Feature Fusion, Proc of the IEEE Winter Conference on Applications of Computer Vision, pp. 3559-3568, (2021)
  • [9] ZHOU Z, ZHOU Y, WANG D L, Et al., Self-Attention Feature Fusion Network for Semantic Segmentation, Neurocomputing, 453, pp. 50-59, (2021)
  • [10] YANG C G, ZHOU H L, AN Z L, Et al., Cross-Image Relational Knowledge Distillation for Semantic Segmentation, Proc of the IEEE/ CVF Conference on Computer Vision and Pattern Recognition, pp. 12309-12318, (2022)
1234