Image classification using HTM cortical learning algorithms
Recently the improved bag of features (BoF) model with locality-constrained linear coding (LLC) and spatial pyramid matching (SPM) achieved state-of-the-art performance in image classification. However, only adopting SPM to exploit spatial information is not enough for satisfactory performance. In t...
Saved in:
Main Authors: | , , , , |
---|---|
Other Authors: | |
Format: | Conference or Workshop Item |
Language: | English |
Published: |
2013
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/99526 http://hdl.handle.net/10220/12893 http://ieeexplore.ieee.org.ezlibproxy1.ntu.edu.sg/xpl/login.jsp?tp=&arnumber=6460663&url=http%3A%2F%2Fieeexplore.ieee.org%2Fxpls%2Fabs_all.jsp%3Farnumber%3D6460663 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
id |
sg-ntu-dr.10356-99526 |
---|---|
record_format |
dspace |
spelling |
sg-ntu-dr.10356-995262020-05-28T07:17:56Z Image classification using HTM cortical learning algorithms Zhuo, Wen Cao, Zhiguo Qin, Yueming Yu, Zhenghong Xiao, Yang School of Computer Engineering International Conference on Pattern Recognition (21st : 2012 : Tsukuba, Japan) DRNTU::Engineering::Computer science and engineering Recently the improved bag of features (BoF) model with locality-constrained linear coding (LLC) and spatial pyramid matching (SPM) achieved state-of-the-art performance in image classification. However, only adopting SPM to exploit spatial information is not enough for satisfactory performance. In this paper, we use hierarchical temporal memory (HTM) cortical learning algorithms to extend this LLC & SPM based model. HTM regions consist of HTM cells are constructed to spatial pool the LLC codes. Each cell receives a subset of LLC codes, and adjacent subsets are overlapped so that more spatial information can be captured. Additionally, HTM cortical learning algorithms have two processes: learning phase which make the HTM cell only receive most frequent LLC codes, and inhibition phase which ensure that the output of HTM regions is sparse. The experimental results on Caltech 101 and UIUC-Sport dataset show the improvement on the original LLC & SPM based model. 2013-08-02T04:42:06Z 2019-12-06T20:08:23Z 2013-08-02T04:42:06Z 2019-12-06T20:08:23Z 2012 2012 Conference Paper https://hdl.handle.net/10356/99526 http://hdl.handle.net/10220/12893 http://ieeexplore.ieee.org.ezlibproxy1.ntu.edu.sg/xpl/login.jsp?tp=&arnumber=6460663&url=http%3A%2F%2Fieeexplore.ieee.org%2Fxpls%2Fabs_all.jsp%3Farnumber%3D6460663 en |
institution |
Nanyang Technological University |
building |
NTU Library |
country |
Singapore |
collection |
DR-NTU |
language |
English |
topic |
DRNTU::Engineering::Computer science and engineering |
spellingShingle |
DRNTU::Engineering::Computer science and engineering Zhuo, Wen Cao, Zhiguo Qin, Yueming Yu, Zhenghong Xiao, Yang Image classification using HTM cortical learning algorithms |
description |
Recently the improved bag of features (BoF) model with locality-constrained linear coding (LLC) and spatial pyramid matching (SPM) achieved state-of-the-art performance in image classification. However, only adopting SPM to exploit spatial information is not enough for satisfactory performance. In this paper, we use hierarchical temporal memory (HTM) cortical learning algorithms to extend this LLC & SPM based model. HTM regions consist of HTM cells are constructed to spatial pool the LLC codes. Each cell receives a subset of LLC codes, and adjacent subsets are overlapped so that more spatial information can be captured. Additionally, HTM cortical learning algorithms have two processes: learning phase which make the HTM cell only receive most frequent LLC codes, and inhibition phase which ensure that the output of HTM regions is sparse. The experimental results on Caltech 101 and UIUC-Sport dataset show the improvement on the original LLC & SPM based model. |
author2 |
School of Computer Engineering |
author_facet |
School of Computer Engineering Zhuo, Wen Cao, Zhiguo Qin, Yueming Yu, Zhenghong Xiao, Yang |
format |
Conference or Workshop Item |
author |
Zhuo, Wen Cao, Zhiguo Qin, Yueming Yu, Zhenghong Xiao, Yang |
author_sort |
Zhuo, Wen |
title |
Image classification using HTM cortical learning algorithms |
title_short |
Image classification using HTM cortical learning algorithms |
title_full |
Image classification using HTM cortical learning algorithms |
title_fullStr |
Image classification using HTM cortical learning algorithms |
title_full_unstemmed |
Image classification using HTM cortical learning algorithms |
title_sort |
image classification using htm cortical learning algorithms |
publishDate |
2013 |
url |
https://hdl.handle.net/10356/99526 http://hdl.handle.net/10220/12893 http://ieeexplore.ieee.org.ezlibproxy1.ntu.edu.sg/xpl/login.jsp?tp=&arnumber=6460663&url=http%3A%2F%2Fieeexplore.ieee.org%2Fxpls%2Fabs_all.jsp%3Farnumber%3D6460663 |
_version_ |
1681056956618375168 |