File Download
  Links for fulltext
     (May Require Subscription)
Supplementary

Article: A Color/Illuminance Aware Data Augmentation and Style Adaptation Approach to Person Re-Identification

TitleA Color/Illuminance Aware Data Augmentation and Style Adaptation Approach to Person Re-Identification
Authors
KeywordsData augmentation
local metric learning
small sample size problem
person re-identification
Issue Date2021
PublisherInstitute of Electrical and Electronics Engineers: Open Access Journals. The Journal's web site is located at http://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp?punumber=6287639
Citation
IEEE Access, 2021, v. 9, p. 115826-115838 How to Cite?
AbstractPerson re-identification problems usually suffer from large subject appearance variations and limited training data. This paper proposes a novel physically motivated Color/Illuminance-Aware data-augmentation (CIADA) scheme and a style-adaptive fusion approach to address these issues. The CIADA scheme estimates the color/illuminance distribution from the training data via manifold learning and generates new samples under different color/illuminance perturbations to better capture objects’ appearance for mitigating the small-sample-size and color variation problems. A Color/Illuminance Aware Feature Augmentation (CIAFA) approach, which is applicable to state-of-the-art features and metric learning algorithms, is then proposed to integrate the features generated by the augmented samples for metric learning. A new Color/Illuminance-Aware Style Fusion (CIASF) scheme, which allows the learning and matching process to be performed independently on each pair of datasets generated for estimating a set of ‘local’ distance functions, is also proposed. A canonical correlation analysis-based weighting scheme is developed to fuse these local distances to an overall distance for recognition. This reduces the memory requirement and complexity over the original CIAFA. Experiments on common datasets show that the proposed methodologies substantially improve the performance of state-of-the-art subspace learning algorithms. It is applicable to both small and large datasets with hand-craft and deep features.
Persistent Identifierhttp://hdl.handle.net/10722/307872
ISSN
2023 Impact Factor: 3.4
2023 SCImago Journal Rankings: 0.960
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorLin, Z-
dc.contributor.authorLIU, C-
dc.contributor.authorQI, W-
dc.contributor.authorChan, SC-
dc.date.accessioned2021-11-12T13:39:08Z-
dc.date.available2021-11-12T13:39:08Z-
dc.date.issued2021-
dc.identifier.citationIEEE Access, 2021, v. 9, p. 115826-115838-
dc.identifier.issn2169-3536-
dc.identifier.urihttp://hdl.handle.net/10722/307872-
dc.description.abstractPerson re-identification problems usually suffer from large subject appearance variations and limited training data. This paper proposes a novel physically motivated Color/Illuminance-Aware data-augmentation (CIADA) scheme and a style-adaptive fusion approach to address these issues. The CIADA scheme estimates the color/illuminance distribution from the training data via manifold learning and generates new samples under different color/illuminance perturbations to better capture objects’ appearance for mitigating the small-sample-size and color variation problems. A Color/Illuminance Aware Feature Augmentation (CIAFA) approach, which is applicable to state-of-the-art features and metric learning algorithms, is then proposed to integrate the features generated by the augmented samples for metric learning. A new Color/Illuminance-Aware Style Fusion (CIASF) scheme, which allows the learning and matching process to be performed independently on each pair of datasets generated for estimating a set of ‘local’ distance functions, is also proposed. A canonical correlation analysis-based weighting scheme is developed to fuse these local distances to an overall distance for recognition. This reduces the memory requirement and complexity over the original CIAFA. Experiments on common datasets show that the proposed methodologies substantially improve the performance of state-of-the-art subspace learning algorithms. It is applicable to both small and large datasets with hand-craft and deep features.-
dc.languageeng-
dc.publisherInstitute of Electrical and Electronics Engineers: Open Access Journals. The Journal's web site is located at http://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp?punumber=6287639-
dc.relation.ispartofIEEE Access-
dc.rightsIEEE Access. Copyright © Institute of Electrical and Electronics Engineers: Open Access Journals.-
dc.rightsThis work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.-
dc.subjectData augmentation-
dc.subjectlocal metric learning-
dc.subjectsmall sample size problem-
dc.subjectperson re-identification-
dc.titleA Color/Illuminance Aware Data Augmentation and Style Adaptation Approach to Person Re-Identification-
dc.typeArticle-
dc.identifier.emailLin, Z: zclin@hku.hk-
dc.identifier.emailChan, SC: scchan@eee.hku.hk-
dc.identifier.authorityChan, SC=rp00094-
dc.description.naturepublished_or_final_version-
dc.identifier.doi10.1109/ACCESS.2021.3100571-
dc.identifier.scopuseid_2-s2.0-85111605973-
dc.identifier.hkuros329438-
dc.identifier.volume9-
dc.identifier.spage115826-
dc.identifier.epage115838-
dc.identifier.isiWOS:000690425000001-
dc.publisher.placeUnited States-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats