• Complex
  • Title
  • Keyword
  • Abstract
  • Scholars
  • Journal
  • ISSN
  • Conference
成果搜索

author:

Xu, Chaoyang (Xu, Chaoyang.) [1] | Wu, Ling (Wu, Ling.) [2] (Scholars:吴伶) | Wang, Shiping (Wang, Shiping.) [3] (Scholars:王石平)

Indexed by:

CPCI-S EI Scopus

Abstract:

Unsupervised dimension reduction has gained widespread attention. Most of previous work performed poorly on image classification due to taking no account of neighborhood relations and spatial localities. In this paper, we propose the 'regularized convolutional auto-encoder', which is a variant of auto-encoder that uses the convolutional operation to extract low-dimensional representations. Each auto-encoder is trained with cluster regularization terms. The contributions of this work are presented as follows: First, we perform different sized filter convolution in parallel and abstract a low-dimensional representation from images cross scales simultaneously. Second, we introduce a cluster regularized rule on auto-encoders to reduce the classification error. Extensive experiments conducted on six publicly available datasets demonstrate that the proposed method significantly reduces the classification error after dimension reduction.

Keyword:

Auto-encoder Convolutional neural network Deep learning Dimension reduction Unsupervised learning

Community:

  • [ 1 ] [Xu, Chaoyang]Putian Univ, Sch Informat Engn, Putian 351100, Peoples R China
  • [ 2 ] [Wu, Ling]Fuzhou Univ, Sch Econ & Management, Fuzhou 350116, Fujian, Peoples R China
  • [ 3 ] [Wu, Ling]Fuzhou Univ, Coll Math & Comp Sci, Fuzhou 350116, Fujian, Peoples R China
  • [ 4 ] [Wang, Shiping]Fuzhou Univ, Coll Math & Comp Sci, Fuzhou 350116, Fujian, Peoples R China

Reprint 's Address:

  • 吴伶

    [Wu, Ling]Fuzhou Univ, Sch Econ & Management, Fuzhou 350116, Fujian, Peoples R China;;[Wu, Ling]Fuzhou Univ, Coll Math & Comp Sci, Fuzhou 350116, Fujian, Peoples R China

Show more details

Related Keywords:

Source :

ADVANCES IN COMPUTER VISION, CVC, VOL 1

ISSN: 2194-5357

Year: 2020

Volume: 943

Page: 99-108

Language: English

Cited Count:

WoS CC Cited Count: 0

SCOPUS Cited Count: 2

ESI Highly Cited Papers on the List: 0 Unfold All

WanFang Cited Count:

Chinese Cited Count:

30 Days PV: 2

Online/Total:97/10009632
Address:FZU Library(No.2 Xuyuan Road, Fuzhou, Fujian, PRC Post Code:350116) Contact Us:0591-22865326
Copyright:FZU Library Technical Support:Beijing Aegean Software Co., Ltd. 闽ICP备05005463号-1