Deep Superpixel Convolutional Network for Image Recognition

被引:8
|
作者
Zeng, Xianfang [1 ]
Wu, Wenxuan [2 ]
Tian, Guangzhong [1 ]
Li, Fuxin [2 ]
Liu, Yong [3 ]
机构
[1] Zhejiang Univ, Inst Cyber Syst & Control, Hangzhou 310027, Peoples R China
[2] Oregon State Univ, CORIS Inst, Corvallis, OR 97331 USA
[3] Zhejiang Univ, State Key Lab Ind Control Technol, Hangzhou 310027, Peoples R China
基金
中国国家自然科学基金;
关键词
Convolution; Three-dimensional displays; Task analysis; Standards; Image recognition; Kernel; Feature extraction; Deep learning; representation learning; image recognition; superpixel;
D O I
10.1109/LSP.2021.3075605
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
Due to the high representational efficiency, superpixel largely reduces the number of image primitives for subsequent processing. However, superpixel is scarcely utilized in recent methods since its irregular shape is intractable for standard convolutional layer. In this paper, we propose an end-to-end trainable superpixel convolutional network, named SPNet, to learn high-level representation on image superpixel primitives. We start by treating irregular superpixel lattices as a 2D point cloud, where the low-level features inside one superpixel are aggregated to one feature vector. We replace the standard convolutional layer with the PointConv layer to handle the irregular and unordered point cloud. Besides, we propose grid based downsampling strategies to output uniform 2D sampling result. The resulting network largely utilizes the efficiency of superpixel and provides a novel view for image recognition task. Experiments on image recognition task show promising results compared with prominent image classification methods. The visualization of class activation mapping shows great accuracy at object localization and boundary segmentation.
引用
收藏
页码:922 / 926
页数:5
相关论文
共 50 条
  • [31] Deep Dilated Convolutional Network for Material Recognition
    Jiang, Xiaoyue
    Du, Junna
    Sun, Baihong
    Feng, Xiaoyi
    2018 EIGHTH INTERNATIONAL CONFERENCE ON IMAGE PROCESSING THEORY, TOOLS AND APPLICATIONS (IPTA), 2018, : 217 - 222
  • [32] Superpixel Region Merging Based on Deep Network for Medical Image Segmentation
    Liu, Hui
    Wang, Haiou
    Wu, Yan
    Xing, Lei
    ACM TRANSACTIONS ON INTELLIGENT SYSTEMS AND TECHNOLOGY, 2020, 11 (04)
  • [33] Convolutional Deep Feedforward Network for Image Classification
    Lau, Mian Mian
    Phang, Jonathan Then Sien
    Lim, King Hann
    2019 7TH INTERNATIONAL CONFERENCE ON SMART COMPUTING & COMMUNICATIONS (ICSCC), 2019, : 99 - 102
  • [34] Deep Convolutional Neural Network for Image Deconvolution
    Xu, Li
    Ren, Jimmy S. J.
    Liu, Ce
    Jia, Jiaya
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 27 (NIPS 2014), 2014, 27
  • [35] Deep Superpixel-Based Network For Blind Image Quality Assessment
    Yang, Guangyi
    Zhan, Yang
    Wang, Yuxuan
    Research Square, 2021,
  • [36] Robustness of Deep Convolutional Neural Networks for Image Recognition
    Ulicny, Matej
    Lundstrom, Jens
    Byttner, Stefan
    INTELLIGENT COMPUTING SYSTEMS, 2016, 597 : 16 - 30
  • [37] Hyperspectral Image Classification Based on Superpixel Pooling Convolutional Neural Network with Transfer Learning
    Xie, Fuding
    Gao, Quanshan
    Jin, Cui
    Zhao, Fengxia
    REMOTE SENSING, 2021, 13 (05) : 1 - 17
  • [38] Land cover classification for polarimetric SAR image using convolutional neural network and superpixel
    Ma Y.
    Li Y.
    Zhu L.
    Progress In Electromagnetics Research B, 2019, 83 (2019): : 111 - 128
  • [39] Superpixel-Based Graph Convolutional Network for UAV Forest Fire Image Segmentation
    Mu, Yunjie
    Ou, Liyuan
    Chen, Wenjing
    Liu, Tao
    Gao, Demin
    DRONES, 2024, 8 (04)
  • [40] Image Semantic Segmentation Based on Convolutional Neural Network Feature and Improved Superpixel Matching
    Guo Chengcheng
    Yu Fengqin
    Chen Ying
    LASER & OPTOELECTRONICS PROGRESS, 2018, 55 (08)