Online multimodal distance metric learning with application to image retrieval
Recent years have witnessed extensive studies on distance metric learning (DML) for improving similarity search in multimedia information retrieval tasks. Despite their successes, most existing DML methods suffer from two critical limitations: (i) they typically attempt to learn a linear distance fu...
Main Authors: | , , , , , |
---|---|
Format: | Text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2013
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/sis_research/2333 https://ink.library.smu.edu.sg/cgi/viewcontent.cgi?article=3333&context=sis_research |
id |
ftsingaporemuniv:oai:ink.library.smu.edu.sg:sis_research-3333 |
---|---|
record_format |
openpolar |
spelling |
ftsingaporemuniv:oai:ink.library.smu.edu.sg:sis_research-3333 2023-05-15T16:01:42+02:00 Online multimodal distance metric learning with application to image retrieval WU, Pengcheng HOI, Steven C. H. XIA, Hao ZHAO, Peilin WANG, Dayong MIAO, Chunyan 2013-10-01T07:00:00Z application/pdf https://ink.library.smu.edu.sg/sis_research/2333 https://ink.library.smu.edu.sg/cgi/viewcontent.cgi?article=3333&context=sis_research eng eng Institutional Knowledge at Singapore Management University https://ink.library.smu.edu.sg/sis_research/2333 https://ink.library.smu.edu.sg/cgi/viewcontent.cgi?article=3333&context=sis_research http://creativecommons.org/licenses/by-nc-nd/4.0/ CC-BY-NC-ND Research Collection School Of Computing and Information Systems Deep learning Distance metric learning Image retrieval Online learning Similarity learning Computer Sciences Databases and Information Systems Numerical Analysis and Scientific Computing text 2013 ftsingaporemuniv 2021-08-31T17:36:36Z Recent years have witnessed extensive studies on distance metric learning (DML) for improving similarity search in multimedia information retrieval tasks. Despite their successes, most existing DML methods suffer from two critical limitations: (i) they typically attempt to learn a linear distance function on the input feature space, in which the assumption of linearity limits their capacity of measuring the similarity on complex patterns in real-world applications; (ii) they are often designed for learning distance metrics on uni-modal data, which may not effectively handle the similarity measures for multimedia objects with multimodal representations. To address these limitations, in this paper, we propose a novel framework of online multimodal deep similarity learning (OMDSL), which aims to optimally integrate multiple deep neural networks pretrained with stacked denoising autoencoder. In particular, the proposed framework explores a unified two-stage online learning scheme that consists of (i) learning a flexible nonlinear transformation function for each individual modality, and (ii) learning to find the optimal combination of multiple diverse modalities simultaneously in a coherent process. We conduct an extensive set of experiments to evaluate the performance of the proposed algorithms for multimodal image retrieval tasks, in which the encouraging results validate the effectiveness of the proposed technique. Text DML Institutional Knowledge (InK) at Singapore Management University Handle The ENVELOPE(161.983,161.983,-78.000,-78.000) |
institution |
Open Polar |
collection |
Institutional Knowledge (InK) at Singapore Management University |
op_collection_id |
ftsingaporemuniv |
language |
English |
topic |
Deep learning Distance metric learning Image retrieval Online learning Similarity learning Computer Sciences Databases and Information Systems Numerical Analysis and Scientific Computing |
spellingShingle |
Deep learning Distance metric learning Image retrieval Online learning Similarity learning Computer Sciences Databases and Information Systems Numerical Analysis and Scientific Computing WU, Pengcheng HOI, Steven C. H. XIA, Hao ZHAO, Peilin WANG, Dayong MIAO, Chunyan Online multimodal distance metric learning with application to image retrieval |
topic_facet |
Deep learning Distance metric learning Image retrieval Online learning Similarity learning Computer Sciences Databases and Information Systems Numerical Analysis and Scientific Computing |
description |
Recent years have witnessed extensive studies on distance metric learning (DML) for improving similarity search in multimedia information retrieval tasks. Despite their successes, most existing DML methods suffer from two critical limitations: (i) they typically attempt to learn a linear distance function on the input feature space, in which the assumption of linearity limits their capacity of measuring the similarity on complex patterns in real-world applications; (ii) they are often designed for learning distance metrics on uni-modal data, which may not effectively handle the similarity measures for multimedia objects with multimodal representations. To address these limitations, in this paper, we propose a novel framework of online multimodal deep similarity learning (OMDSL), which aims to optimally integrate multiple deep neural networks pretrained with stacked denoising autoencoder. In particular, the proposed framework explores a unified two-stage online learning scheme that consists of (i) learning a flexible nonlinear transformation function for each individual modality, and (ii) learning to find the optimal combination of multiple diverse modalities simultaneously in a coherent process. We conduct an extensive set of experiments to evaluate the performance of the proposed algorithms for multimodal image retrieval tasks, in which the encouraging results validate the effectiveness of the proposed technique. |
format |
Text |
author |
WU, Pengcheng HOI, Steven C. H. XIA, Hao ZHAO, Peilin WANG, Dayong MIAO, Chunyan |
author_facet |
WU, Pengcheng HOI, Steven C. H. XIA, Hao ZHAO, Peilin WANG, Dayong MIAO, Chunyan |
author_sort |
WU, Pengcheng |
title |
Online multimodal distance metric learning with application to image retrieval |
title_short |
Online multimodal distance metric learning with application to image retrieval |
title_full |
Online multimodal distance metric learning with application to image retrieval |
title_fullStr |
Online multimodal distance metric learning with application to image retrieval |
title_full_unstemmed |
Online multimodal distance metric learning with application to image retrieval |
title_sort |
online multimodal distance metric learning with application to image retrieval |
publisher |
Institutional Knowledge at Singapore Management University |
publishDate |
2013 |
url |
https://ink.library.smu.edu.sg/sis_research/2333 https://ink.library.smu.edu.sg/cgi/viewcontent.cgi?article=3333&context=sis_research |
long_lat |
ENVELOPE(161.983,161.983,-78.000,-78.000) |
geographic |
Handle The |
geographic_facet |
Handle The |
genre |
DML |
genre_facet |
DML |
op_source |
Research Collection School Of Computing and Information Systems |
op_relation |
https://ink.library.smu.edu.sg/sis_research/2333 https://ink.library.smu.edu.sg/cgi/viewcontent.cgi?article=3333&context=sis_research |
op_rights |
http://creativecommons.org/licenses/by-nc-nd/4.0/ |
op_rightsnorm |
CC-BY-NC-ND |
_version_ |
1766397460208418816 |