A Probabilistic Analysis of Sparse Coded Feature Pooling and Its Application for Image Retrieval.
Feature coding and pooling as a key component of image retrieval have been widely studied over the past several years. Recently sparse coding with max-pooling is regarded as the state-of-the-art for image classification. However there is no comprehensive study concerning the application of sparse co...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Public Library of Science (PLoS)
2015-01-01
|
Series: | PLoS ONE |
Online Access: | http://europepmc.org/articles/PMC4489107?pdf=render |
id |
doaj-5bf72aed67de4e398f0adfd3e983b09c |
---|---|
record_format |
Article |
spelling |
doaj-5bf72aed67de4e398f0adfd3e983b09c2020-11-25T02:04:35ZengPublic Library of Science (PLoS)PLoS ONE1932-62032015-01-01107e013172110.1371/journal.pone.0131721A Probabilistic Analysis of Sparse Coded Feature Pooling and Its Application for Image Retrieval.Yunchao ZhangJing ChenXiujie HuangYongtian WangFeature coding and pooling as a key component of image retrieval have been widely studied over the past several years. Recently sparse coding with max-pooling is regarded as the state-of-the-art for image classification. However there is no comprehensive study concerning the application of sparse coding for image retrieval. In this paper, we first analyze the effects of different sampling strategies for image retrieval, then we discuss feature pooling strategies on image retrieval performance with a probabilistic explanation in the context of sparse coding framework, and propose a modified sum pooling procedure which can improve the retrieval accuracy significantly. Further we apply sparse coding method to aggregate multiple types of features for large-scale image retrieval. Extensive experiments on commonly-used evaluation datasets demonstrate that our final compact image representation improves the retrieval accuracy significantly.http://europepmc.org/articles/PMC4489107?pdf=render |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Yunchao Zhang Jing Chen Xiujie Huang Yongtian Wang |
spellingShingle |
Yunchao Zhang Jing Chen Xiujie Huang Yongtian Wang A Probabilistic Analysis of Sparse Coded Feature Pooling and Its Application for Image Retrieval. PLoS ONE |
author_facet |
Yunchao Zhang Jing Chen Xiujie Huang Yongtian Wang |
author_sort |
Yunchao Zhang |
title |
A Probabilistic Analysis of Sparse Coded Feature Pooling and Its Application for Image Retrieval. |
title_short |
A Probabilistic Analysis of Sparse Coded Feature Pooling and Its Application for Image Retrieval. |
title_full |
A Probabilistic Analysis of Sparse Coded Feature Pooling and Its Application for Image Retrieval. |
title_fullStr |
A Probabilistic Analysis of Sparse Coded Feature Pooling and Its Application for Image Retrieval. |
title_full_unstemmed |
A Probabilistic Analysis of Sparse Coded Feature Pooling and Its Application for Image Retrieval. |
title_sort |
probabilistic analysis of sparse coded feature pooling and its application for image retrieval. |
publisher |
Public Library of Science (PLoS) |
series |
PLoS ONE |
issn |
1932-6203 |
publishDate |
2015-01-01 |
description |
Feature coding and pooling as a key component of image retrieval have been widely studied over the past several years. Recently sparse coding with max-pooling is regarded as the state-of-the-art for image classification. However there is no comprehensive study concerning the application of sparse coding for image retrieval. In this paper, we first analyze the effects of different sampling strategies for image retrieval, then we discuss feature pooling strategies on image retrieval performance with a probabilistic explanation in the context of sparse coding framework, and propose a modified sum pooling procedure which can improve the retrieval accuracy significantly. Further we apply sparse coding method to aggregate multiple types of features for large-scale image retrieval. Extensive experiments on commonly-used evaluation datasets demonstrate that our final compact image representation improves the retrieval accuracy significantly. |
url |
http://europepmc.org/articles/PMC4489107?pdf=render |
work_keys_str_mv |
AT yunchaozhang aprobabilisticanalysisofsparsecodedfeaturepoolinganditsapplicationforimageretrieval AT jingchen aprobabilisticanalysisofsparsecodedfeaturepoolinganditsapplicationforimageretrieval AT xiujiehuang aprobabilisticanalysisofsparsecodedfeaturepoolinganditsapplicationforimageretrieval AT yongtianwang aprobabilisticanalysisofsparsecodedfeaturepoolinganditsapplicationforimageretrieval AT yunchaozhang probabilisticanalysisofsparsecodedfeaturepoolinganditsapplicationforimageretrieval AT jingchen probabilisticanalysisofsparsecodedfeaturepoolinganditsapplicationforimageretrieval AT xiujiehuang probabilisticanalysisofsparsecodedfeaturepoolinganditsapplicationforimageretrieval AT yongtianwang probabilisticanalysisofsparsecodedfeaturepoolinganditsapplicationforimageretrieval |
_version_ |
1724942376192966656 |