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

页码：245 / 254

页数：10

共 50 条

[1] Rethinking Loss Design for Large-scale 3D Shape Retrieval
Li, Zhaoqun
Xu, Cheng
Leng, Biao
[J]. PROCEEDINGS OF THE TWENTY-EIGHTH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2019, : 840 - 846
[2] A Large-Scale Shape Benchmark for 3D Object Retrieval: Toyohashi Shape Benchmark
Tatsuma, Atsushi
Koyanagi, Hitoshi
Aono, Masaki
[J]. 2012 ASIA-PACIFIC SIGNAL AND INFORMATION PROCESSING ASSOCIATION ANNUAL SUMMIT AND CONFERENCE (APSIPA ASC), 2012,
[3] Sketch-based 3D Shape Retrieval using Convolutional Neural Networks
Wang, Fang
Kang, Le
Li, Yi
[J]. 2015 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2015, : 1875 - 1883
[4] A novel 3D visualization tool for large-scale neural networks
Alexander Jones
Justin Cardoza
Denver J Liu
Laurence C Jayet Bray
Sergiu M Dascalu
Sushil J Louis
Frederick C Harris
[J]. BMC Neuroscience, 14 (Suppl 1)
[5] A Supervised Video Hashing Method Based on a Deep 3D Convolutional Neural Network for Large-Scale Video Retrieval
Chen, Hanqing
Hu, Chunyan
Lee, Feifei
Lin, Chaowei
Yao, Wei
Chen, Lu
Chen, Qiu
[J]. SENSORS, 2021, 21 (09)
[6] On the Large-Scale Transferability of Convolutional Neural Networks
Zheng, Liang
Zhao, Yali
Wang, Shengjin
Wang, Jingdong
Yang, Yi
Tian, Qi
[J]. TRENDS AND APPLICATIONS IN KNOWLEDGE DISCOVERY AND DATA MINING: PAKDD 2018 WORKSHOPS, 2018, 11154 : 27 - 39
[7] Web3D Learning Framework for 3D Shape Retrieval Based on Hybrid Convolutional Neural Networks
Wen Zhou
Jinyuan Jia
Chengxi Huang
Yongqing Cheng
[J]. Tsinghua Science and Technology, 2020, 25 (01) : 93 - 102
[8] Web3D Learning Framework for 3D Shape Retrieval Based on Hybrid Convolutional Neural Networks
Zhou, Wen
Jia, Jinyuan
Huang, Chengxi
Cheng, Yongqing
[J]. TSINGHUA SCIENCE AND TECHNOLOGY, 2020, 25 (01) : 93 - 102
[9] 3D fully convolutional networks for subcortical segmentation in MRI: A large-scale study
Dolz, Jose
Desrosiers, Christian
Ben Ayed, Ismail
[J]. NEUROIMAGE, 2018, 170 : 456 - 470
[10] Large-scale Isolated Gesture Recognition using Pyramidal 3D Convolutional Networks
Zhu, Guangming
Zhang, Liang
Mei, Lin
Shao, Jie
Song, Juan
Shen, Peiyi
[J]. 2016 23RD INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR), 2016, : 19 - 24

← 1 2 3 4 5 →