MPFANet: Semantic Segmentation Using Multiple Path Feature Aggregation

被引:0
|
作者
Jeon, Wang-Su [1 ]
Rhee, Sang-Yong [2 ]
机构
[1] Kyungnam Univ, Dept IT Convergence Engn, Chang Won, South Korea
[2] Kyungnam Univ, Dept Comp Engn, Chang Won, South Korea
基金
新加坡国家研究基金会;
关键词
MPFA; Semantic segmentation; Feature aggregation; CNN; Inverted residual block; Local context;
D O I
10.5391/IJFIS.2021.21.4.401
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
Image segmentation is the process of simplifying the analysis of the meaning or the front to say the process of dividing the image into a set of multiple pixels. The multiple path feature aggregation (MPFA) method proposed in this paper aims to extract various information of an object, and uses conventional pyramid pooling or the extraction of various sized features. This information can be combined with different regional features to obtain the overall feature information. We split four paths to extract numerous local features, and the results showed that the mean intersection over union (mIOU) is 81.6% for the validation data from the PASCAL VOC 2012 dataset, and a better performance than the existing DeepLab model was demonstrated.
引用
收藏
页码:401 / 408
页数:8
相关论文
共 50 条
  • [1] Meta-RangeSeg: LiDAR Sequence Semantic Segmentation Using Multiple Feature Aggregation
    Wang, Song
    Zhu, Jianke
    Zhang, Ruixiang
    [J]. IEEE ROBOTICS AND AUTOMATION LETTERS, 2022, 7 (04) : 9739 - 9746
  • [2] Localized Feature Aggregation Module for Semantic Segmentation
    Furukawa, Ryouichi
    Hotta, Kazuhiro
    [J]. 2021 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN, AND CYBERNETICS (SMC), 2021, : 1745 - 1750
  • [3] FANet: Feature Aggregation Network for Semantic Segmentation
    Singha, Tanmay
    Duc-Son Pham
    Krishna, Aneesh
    [J]. 2020 DIGITAL IMAGE COMPUTING: TECHNIQUES AND APPLICATIONS (DICTA), 2020,
  • [4] Semantic Segmentation Method Based on Multiscale Feature Alignment and Aggregation
    Xu Zhaozhong
    Peng Li
    Dai Feifei
    [J]. LASER & OPTOELECTRONICS PROGRESS, 2023, 60 (02)
  • [5] MPFANet: a multipath feature aggregation network for steel surface defect detection
    Li, Zhongyang
    Tai, Yichun
    Huang, Zhenzhen
    Peng, Tao
    Zhang, Zhijiang
    [J]. MEASUREMENT SCIENCE AND TECHNOLOGY, 2024, 35 (04)
  • [6] DFANet: Deep Feature Aggregation for Real-Time Semantic Segmentation
    Li, Hanchao
    Xiong, Pengfei
    Fan, Haoqiang
    Sun, Jian
    [J]. 2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019), 2019, : 9514 - 9523
  • [7] Enhancing feature fusion with spatial aggregation and channel fusion for semantic segmentation
    Hu, Jie
    Kong, Huifang
    Fan, Lei
    Zhou, Jun
    [J]. IET COMPUTER VISION, 2021, 15 (06) : 418 - 427
  • [8] FinSeg: Finger Parts Semantic Segmentation using Multi-scale Feature Maps Aggregation of FCN
    Saleh, Adel
    Rashwan, Hatem A.
    Abdel-Nasser, Mohamed
    Singh, Vivek K.
    Abdulwahab, Saddam
    Sarker, Md Mostafa Kamal
    Garcia, Miguel Angel
    Puig, Domenec
    [J]. PROCEEDINGS OF THE 14TH INTERNATIONAL JOINT CONFERENCE ON COMPUTER VISION, IMAGING AND COMPUTER GRAPHICS THEORY AND APPLICATIONS (VISAPP), VOL 5, 2019, : 77 - 84
  • [9] Dual-Neighborhood Feature Aggregation Network for Point Cloud Semantic Segmentation
    Chen, Minghong
    Zhang, Guanghui
    Shi, Wenjun
    Zhu, Dongchen
    Zhang, Xiaolin
    Li, Jiamao
    [J]. 2022 IEEE 34TH INTERNATIONAL CONFERENCE ON TOOLS WITH ARTIFICIAL INTELLIGENCE, ICTAI, 2022, : 76 - 81
  • [10] Research on Efficient Feature Generation and Spatial Aggregation for Remote Sensing Semantic Segmentation
    Li, Ruoyang
    Xiong, Shuping
    Che, Yinchao
    Shi, Lei
    Ma, Xinming
    Xi, Lei
    [J]. ALGORITHMS, 2024, 17 (04)