Deep Parametric Continuous Convolutional Neural Networks

被引:2218
|
作者
Wang, Shenlong [1 ,3 ]
Suo, Simon [2 ,3 ]
Ma, Wei-Chiu [3 ]
Pokrovsky, Andrei [3 ]
Urtasun, Raquel [1 ,3 ]
机构
[1] Univ Toronto, Toronto, ON, Canada
[2] Univ Waterloo, Waterloo, ON, Canada
[3] Uber Adv Technol Grp, Pittsburgh, PA 15201 USA
关键词
D O I
10.1109/CVPR.2018.00274
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Standard convolutional neural networks assume a grid structured input is available and exploit discrete convolutions as their fundamental building blocks. This limits their applicability to many real-world applications. In this paper we propose Parametric Continuous Convolution, a new learnable operator that operates over non-grid structured data. The key idea is to exploit parameterized kernel functions that span the full continuous vector space. This generalization allows us to learn over arbitrary data structures as long as their support relationship is computable. Our experiments show significant improvement over the state-of-the-art in point cloud segmentation of indoor and outdoor scenes, and lidar motion estimation of driving scenes.
引用
收藏
页码:2589 / 2597
页数:9
相关论文
共 50 条
  • [1] Parametric Exponential Linear Unit for Deep Convolutional Neural Networks
    Trottier, Ludovic
    Giguere, Philippe
    Chaib-draa, Brahim
    [J]. 2017 16TH IEEE INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND APPLICATIONS (ICMLA), 2017, : 207 - 214
  • [2] Parametric System Identification Using Deep Convolutional Neural Networks
    Genc, Sahika
    [J]. 2017 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2017, : 2112 - 2119
  • [3] Deep Convolutional Neural Networks
    Gonzalez, Rafael C.
    [J]. IEEE SIGNAL PROCESSING MAGAZINE, 2018, 35 (06) : 79 - 87
  • [4] Deep Anchored Convolutional Neural Networks
    Huang, Jiahui
    Dwivedi, Kshitij
    Roig, Gemma
    [J]. 2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS (CVPRW 2019), 2019, : 639 - 647
  • [5] DEEP CONVOLUTIONAL NEURAL NETWORKS FOR LVCSR
    Sainath, Tara N.
    Mohamed, Abdel-rahman
    Kingsbury, Brian
    Ramabhadran, Bhuvana
    [J]. 2013 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2013, : 8614 - 8618
  • [6] Deep Unitary Convolutional Neural Networks
    Chang, Hao-Yuan
    Wang, Kang L.
    [J]. ARTIFICIAL NEURAL NETWORKS AND MACHINE LEARNING - ICANN 2021, PT II, 2021, 12892 : 170 - 181
  • [7] Universality of deep convolutional neural networks
    Zhou, Ding-Xuan
    [J]. APPLIED AND COMPUTATIONAL HARMONIC ANALYSIS, 2020, 48 (02) : 787 - 794
  • [8] A Review on Deep Convolutional Neural Networks
    Aloysius, Neena
    Geetha, M.
    [J]. 2017 INTERNATIONAL CONFERENCE ON COMMUNICATION AND SIGNAL PROCESSING (ICCSP), 2017, : 588 - 592
  • [9] Fusion of Deep Convolutional Neural Networks
    Suchy, Robert
    Ezekiel, Soundararajan
    Cornacchia, Maria
    [J]. 2017 IEEE APPLIED IMAGERY PATTERN RECOGNITION WORKSHOP (AIPR), 2017,
  • [10] Convergence of deep convolutional neural networks
    Xu, Yuesheng
    Zhang, Haizhang
    [J]. NEURAL NETWORKS, 2022, 153 : 553 - 563