Large-Scale Shape Retrieval with Sparse 3D Convolutional Neural Networks

被引：9
|
作者：
Notchenko, Alexandr [1 ,2 ]
Kapushev, Yermek [1 ,2 ]
Burnaev, Evgeny [1 ]
机构：
[1] Skolkovo Innovat Ctr, Skolkovo Inst Sci & Technol, Bldg 3, Moscow 143026, Russia
[2] RAS, Inst Informat Transmiss Problems, Bolshoy Karetny Per 19,Build 1, Moscow 127051, Russia
来源：
ANALYSIS OF IMAGES, SOCIAL NETWORKS AND TEXTS, AIST 2017 | 2018年 / 10716卷
基金：
俄罗斯科学基金会;
关键词：
Deep Learning; Sparse 3D Convolutional Neural Network; Voxel resolution;
D O I：
10.1007/978-3-319-73013-4_23
中图分类号：
TP [自动化技术、计算机技术];
学科分类号：
0812 ;
摘要：
In this paper we present results of performance evaluation of S3DCNN - a Sparse 3D Convolutional Neural Network - on a largescale 3D Shape benchmark ModelNet40, and measure how it is impacted by voxel resolution of input shape. We demonstrate comparable classification and retrieval performance to state-of-the-art models, but with much less computational costs in training and inference phases. We also notice that benefits of higher input resolution can be limited by an ability of a neural network to generalize high level features.
引用
收藏
页码：245 / 254
页数：10
相关论文
共 50 条
  • [41] Accelerating Large-Scale Convolutional Neural Networks with Parallel Graphics Multiprocessors
    Scherer, Dominik
    Schulz, Hannes
    Behnke, Sven
    ARTIFICIAL NEURAL NETWORKS (ICANN 2010), PT III, 2010, 6354 : 82 - 91
  • [42] Large-scale Isolated Gesture Recognition Using Convolutional Neural Networks
    Wang, Pichao
    Li, Wanqing
    Liu, Song
    Gao, Zhimin
    Tang, Chang
    Ogunbona, Philip
    2016 23RD INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR), 2016, : 7 - 12
  • [43] Efficient Inference of Large-Scale and Lightweight Convolutional Neural Networks on FPGA
    Wu, Xiao
    Ma, Yufei
    Wang, Zhongfeng
    2020 IEEE 33RD INTERNATIONAL SYSTEM-ON-CHIP CONFERENCE (SOCC), 2020, : 168 - 173
  • [44] GVCNN: Group-View Convolutional Neural Networks for 3D Shape Recognition
    Feng, Yifan
    Zhang, Zizhao
    Zhao, Xibin
    Ji, Rongrong
    Gao, Yue
    2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2018, : 264 - 272
  • [45] Training deep convolutional neural networks to acquire the best view of a 3D shape
    Zhou, Wen
    Jia, Jinyuan
    MULTIMEDIA TOOLS AND APPLICATIONS, 2020, 79 (1-2) : 581 - 601
  • [46] Directionally Convolutional Networks for 3D Shape Segmentation
    Xu, Haotian
    Dong, Ming
    Zhong, Zichun
    2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2017, : 2717 - 2726
  • [47] Non-rigid 3D Shape Classification based on Convolutional Neural Networks
    Llerena Quenaya, Jan Franco
    Lopez Del Alamo, Cristian Jose
    2017 IEEE LATIN AMERICAN CONFERENCE ON COMPUTATIONAL INTELLIGENCE (LA-CCI), 2017,
  • [48] Balanced principal component for 3D shape recognition using convolutional neural networks
    Luo, Wenjie
    Zhang, Han
    Ni, Peng
    Tian, Xuedong
    IET IMAGE PROCESSING, 2020, 14 (17) : 4468 - 4476
  • [49] Training deep convolutional neural networks to acquire the best view of a 3D shape
    Wen Zhou
    Jinyuan Jia
    Multimedia Tools and Applications, 2020, 79 : 581 - 601
  • [50] 3D Shape Segmentation with Projective Convolutional Networks
    Kalogerakis, Evangelos
    Averkiou, Melinos
    Maji, Subhransu
    Chaudhuri, Siddhartha
    30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017), 2017, : 6630 - 6639
12345