Filters








596 Hits in 6.1 sec

Asymmetric Co-Teaching for Unsupervised Cross-Domain Person Re-Identification

Fengxiang Yang, Ke Li, Zhun Zhong, Zhiming Luo, Xing Sun, Hao Cheng, Xiaowei Guo, Feiyue Huang, Rongrong Ji, Shaozi Li
<span title="2020-04-03">2020</span> <i title="Association for the Advancement of Artificial Intelligence (AAAI)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/wtjcymhabjantmdtuptkk62mlq" style="color: black;">PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE</a> </i> &nbsp;
To this end, we design an asymmetric co-teaching framework, which resists noisy labels by cooperating two models to select data with possibly clean labels for each other.  ...  Person re-identification (re-ID), is a challenging task due to the high variance within identity samples and imaging conditions.  ...  Conclusion In this paper, we propose a novel asymmetric co-training framework for unsupervised cross-domain re-ID.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1609/aaai.v34i07.6950">doi:10.1609/aaai.v34i07.6950</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/k4vkyme3g5eulpcohi2w5fksou">fatcat:k4vkyme3g5eulpcohi2w5fksou</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201103205809/https://aaai.org/ojs/index.php/AAAI/article/download/6950/6804" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/f7/69/f769ccb252ce3c0307552aeae37f9a602806b807.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1609/aaai.v34i07.6950"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Asymmetric Co-Teaching for Unsupervised Cross Domain Person Re-Identification [article]

Fengxiang Yang, Ke Li, Zhun Zhong, Zhiming Luo, Xing Sun, Hao Cheng, Xiaowei Guo, Feiyue Huang, Rongrong Ji, Shaozi Li
<span title="2019-12-03">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
To this end, we design an asymmetric co-teaching framework, which resists noisy labels by cooperating two models to select data with possibly clean labels for each other.  ...  Person re-identification (re-ID), is a challenging task due to the high variance within identity samples and imaging conditions.  ...  Conclusion In this paper, we propose a novel asymmetric co-training framework for unsupervised cross-domain re-ID.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1912.01349v1">arXiv:1912.01349v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ttbn62j5mvacnosn3lnab3loby">fatcat:ttbn62j5mvacnosn3lnab3loby</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200903225803/https://arxiv.org/pdf/1912.01349v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/7b/9b/7b9b4f4b29af7d2dd74247815c81ea9915d1259a.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1912.01349v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Asymmetric Mutual Mean-Teaching for Unsupervised Domain Adaptive Person Re-Identification

Yachao Dong, Hongzhe Liu, Cheng Xu
<span title="">2021</span> <i title="Institute of Electrical and Electronics Engineers (IEEE)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/q7qi7j4ckfac7ehf3mjbso4hne" style="color: black;">IEEE Access</a> </i> &nbsp;
To solve this problem, this paper proposes an asymmetric mutual mean-teaching method for unsupervised adaptive person re-identification.  ...  INDEX TERMS Deep learning, person re-identification, unsupervised domain adaptation, mutual mean-teaching.  ...  CONCLUSION We proposed an asymmetric mutual mean-teaching method to solve the unsupervised domain adaptive person re-identification task.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/access.2021.3077952">doi:10.1109/access.2021.3077952</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/4xnf33xcmfdhra5hd4g72pgfr4">fatcat:4xnf33xcmfdhra5hd4g72pgfr4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210520234504/https://ieeexplore.ieee.org/ielx7/6287639/9312710/09424557.pdf?tp=&amp;arnumber=9424557&amp;isnumber=9312710&amp;ref=" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/b1/d0/b1d0a6bb0a5d61faf81f72ebff6d0eaf4190937e.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/access.2021.3077952"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> ieee.com </button> </a>

Enhancing Diversity in Teacher-Student Networks via Asymmetric branches for Unsupervised Person Re-identification

Hao Chen, Benoit Lagadec, Francois Bremond
<span title="">2021</span> <i title="IEEE"> 2021 IEEE Winter Conference on Applications of Computer Vision (WACV) </i> &nbsp;
The objective of unsupervised person re-identification (Re-ID) is to learn discriminative features without laborintensive identity annotations.  ...  State-of-the-art unsupervised Re-ID methods assign pseudo labels to unlabeled images in the target domain and learn from these noisy pseudo labels.  ...  Introduction Person re-identification (Re-ID) targets at retrieving a person of interest across non-overlapping cameras.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/wacv48630.2021.00005">doi:10.1109/wacv48630.2021.00005</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/faaamm5gnbaefk57umtnwcal4a">fatcat:faaamm5gnbaefk57umtnwcal4a</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220308034828/https://hal.archives-ouvertes.fr/hal-03028661/file/0067.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/2d/0f/2d0f8031553ac2092d5f8fb32845d32453230b59.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/wacv48630.2021.00005"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

Learning from Self-Discrepancy via Multiple Co-teaching for Cross-Domain Person Re-Identification [article]

Suncheng Xiang, Yuzhuo Fu, Mengyuan Guan, Ting Liu
<span title="2021-09-07">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
To address this issue, in this paper, we propose a multiple co-teaching framework for domain adaptive person re-ID, opening up a promising direction about self-discrepancy problem under unsupervised condition  ...  Employing clustering strategy to assign unlabeled target images with pseudo labels has become a trend for person re-identification (re-ID) algorithms in domain adaptation.  ...  Introduction Given a query image, person re-identification (re-ID) aims to match the person-of-interest across multiple non-overlapped cameras distributed in different places.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2104.02265v5">arXiv:2104.02265v5</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/bo5z3j7rnfel3h55scyd45yhby">fatcat:bo5z3j7rnfel3h55scyd45yhby</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211011175350/https://arxiv.org/pdf/2104.02265v4.pdf" title="fulltext PDF download [not primary version]" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <span style="color: #f43e3e;">&#10033;</span> <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/f2/a4/f2a4341af211f1a3ca05de3bc1650d63b73d3f17.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2104.02265v5" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Unsupervised Horizontal Pyramid Similarity Learning for Cross-domain Adaptive Person Re-identification

Wenhui Dong, Peishu Qu, Chunsheng Liu, Yanke Tang, Ning Gai
<span title="">2021</span> <i title="Institute of Electrical and Electronics Engineers (IEEE)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/q7qi7j4ckfac7ehf3mjbso4hne" style="color: black;">IEEE Access</a> </i> &nbsp;
Many works focus on unsupervised cross domain person re-identification [7] - [16] .  ...  UNSUPERVISED CROSS-DOMAIN ADAPTIVE PERSON RE-IDENTIFICATION Since it is costly to label the dataset of interest, unsupervised cross-domain adaptive person re-identification becomes one popular solution  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/access.2021.3093083">doi:10.1109/access.2021.3093083</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ivxowzfrsbh53mosmfiw44moxy">fatcat:ivxowzfrsbh53mosmfiw44moxy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210718051531/https://ieeexplore.ieee.org/ielx7/6287639/6514899/09466837.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/ab/18/ab18584160aabe95a5df33ea70af3729ef30045d.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/access.2021.3093083"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> ieee.com </button> </a>

Dynamic Re-Weighting and Cross-Camera Learning for Unsupervised Person Re-Identification

Qingze Yin, Guan'an Wang, Jinlin Wu, Haonan Luo, Zhenmin Tang
<span title="2022-05-12">2022</span> <i title="MDPI AG"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/ye33srllvnanjouxn4tmrfgjsq" style="color: black;">Mathematics</a> </i> &nbsp;
Person Re-Identification (ReID) has witnessed tremendous improvements with the help of deep convolutional neural networks (CNN).  ...  Then, cross-camera triplet loss is proposed to fine-tune the source domain model.  ...  [42] proposed a novel clustering-based method based on the asymmetric co-teaching tactic.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/math10101654">doi:10.3390/math10101654</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/drjkeoompvdkvhfxhh7f44izqm">fatcat:drjkeoompvdkvhfxhh7f44izqm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220514210858/https://mdpi-res.com/d_attachment/mathematics/mathematics-10-01654/article_deploy/mathematics-10-01654-v2.pdf?version=1652441357" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/d0/ad/d0ad8b7c37637c9956727c520c2afaef0b4c0b87.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/math10101654"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> mdpi.com </button> </a>

Unsupervised Clustering Active Learning for Person Re-identification [article]

Wenjing Gao, Minxian Li
<span title="2021-12-26">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Supervised person re-identification (re-id) approaches require a large amount of pairwise manual labeled data, which is not applicable in most real-world scenarios for re-id deployment.  ...  On the other hand, unsupervised re-id methods rely on unlabeled data to train models but performs poorly compared with supervised re-id methods.  ...  Asymmetric co-teaching for unsuper- vised cross-domain person re-identification. In AAAI Conf. on Art.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2112.13308v1">arXiv:2112.13308v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/kk5d5ghlh5bvvblpsdcirmfow4">fatcat:kk5d5ghlh5bvvblpsdcirmfow4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220106032549/https://arxiv.org/pdf/2112.13308v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/b5/9c/b59cf8751baccace6d976606d1e27cd579e6e105.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2112.13308v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Unsupervised Person Re-Identification: A Systematic Survey of Challenges and Solutions [article]

Xiangtan Lin and Pengzhen Ren and Chung-Hsing Yeh and Lina Yao and Andy Song and Xiaojun Chang
<span title="2021-10-02">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Therefore, unsupervised person Re-ID has drawn increasing attention for its potential to address the scalability issue in person Re-ID.  ...  person feature learning; 2) learning discriminative person features with pseudo-supervision; 3) learning cross-camera invariant person feature, and 4) the domain shift between datasets.  ...  ACT [77] design an asymmetric co-teaching framework with two models to select samples from each other.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2109.06057v2">arXiv:2109.06057v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/epfow7w3trevff5iku2uvb4ov4">fatcat:epfow7w3trevff5iku2uvb4ov4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211006043406/https://arxiv.org/pdf/2109.06057v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/a0/3c/a03cbc6299f02566433b056eb68b22a2ef7a8374.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2109.06057v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Global Distance-distributions Separation for Unsupervised Person Re-identification [article]

Xin Jin, Cuiling Lan, Wenjun Zeng, Zhibo Chen
<span title="2020-07-10">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Supervised person re-identification (ReID) often has poor scalability and usability in real-world deployments due to domain gaps and the lack of annotations for the target domain data.  ...  Unsupervised person ReID through domain adaptation is attractive yet challenging.  ...  Yang, F., Li, K., Zhong, Z., Luo, Z., Sun, X., Cheng, H., Guo, X., Huang, F., Ji, R., Li, S.: Asymmetric co-teaching for unsupervised cross domain person reidentification.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2006.00752v3">arXiv:2006.00752v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/zqkcryiqdfayxg3zn2jqz3yuve">fatcat:zqkcryiqdfayxg3zn2jqz3yuve</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200714002943/https://arxiv.org/pdf/2006.00752v3.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2006.00752v3" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Unsupervised Domain Adaptation for Person Re-Identification through Source-Guided Pseudo-Labeling [article]

Fabian Dubourvieux, Romaric Audigier, Angelique Loesch, Samia Ainouz, Stephane Canu
<span title="2020-09-20">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Person Re-Identification (re-ID) aims at retrieving images of the same person taken by different cameras.  ...  Unsupervised Domain Adaptation (UDA) is an interesting research direction for this challenge as it avoids a costly annotation of the target data.  ...  second model for asymmetric co-teaching).  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2009.09445v1">arXiv:2009.09445v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/wsd4mh3xkra2vlnrg6bx6wurei">fatcat:wsd4mh3xkra2vlnrg6bx6wurei</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200927075256/https://arxiv.org/pdf/2009.09445v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2009.09445v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Unsupervised Person Re-Identification with Multi-Label Learning Guided Self-Paced Clustering [article]

Qing Li, Xiaojiang Peng, Yu Qiao, Qi Hao
<span title="2021-03-08">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Although unsupervised person re-identification (Re-ID) has drawn increasing research attention recently, it remains challenging to learn discriminative features without annotations across disjoint camera  ...  In this paper, we address the unsupervised person Re-ID with a conceptually novel yet simple framework, termed as Multi-label Learning guided self-paced Clustering (MLC).  ...  methods. h Related work In this section, we review the Person Re-Identification (Re-ID) technology in the view of supervised learning, unsupervised domain adaption (UDA), and unsupervised learning.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2103.04580v1">arXiv:2103.04580v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/rkdapufnwfh27gx4htyxjxo7mu">fatcat:rkdapufnwfh27gx4htyxjxo7mu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210313095838/https://arxiv.org/pdf/2103.04580v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/00/c5/00c509531b972ee37a3023ba6393357e029eb1f5.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2103.04580v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Unsupervised Domain Adaptation for Person Re-Identification through Source-Guided Pseudo-Labeling

Fabian Dubourvieux, Romaric Audigier, Angelique Loesch, Samia Ainouz, Stephane Canu
<span title="2021-01-10">2021</span> <i title="IEEE"> 2020 25th International Conference on Pattern Recognition (ICPR) </i> &nbsp;
vised domain adaptation for person re-identification through source-guided pseudo-labeling. ICPR  ...  second model for asymmetric co-teaching).  ...  Abstract-Person Re-Identification (re-ID) aims at retrieving images of the same person taken by different cameras.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/icpr48806.2021.9412964">doi:10.1109/icpr48806.2021.9412964</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/6b5l7o74zfcunek2r5owyixc5e">fatcat:6b5l7o74zfcunek2r5owyixc5e</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210716105552/https://hal-cea.archives-ouvertes.fr/cea-03251813/file/icpr_paper_arxiv.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/13/75/1375568ce566e0943762611804d93814177ae534.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/icpr48806.2021.9412964"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

Complementary Pseudo Labels For Unsupervised Domain Adaptation On Person Re-identification [article]

Hao Feng, Minghao Chen, Jinming Hu, Dong Shen, Haifeng Liu, Deng Cai
<span title="2021-02-07">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In recent years, supervised person re-identification (re-ID) models have received increasing studies.  ...  Extensive experiments on three large-scale datasets demonstrate that our method can achieve state-of-the-art performance under the unsupervised domain adaptation re-ID setting.  ...  There are also some methods [34] , [35] designed for unsupervised cross-domain person re-ID. [35] designs an asymmetric co-teaching framework for pseudo labels generated by DBSCAN [15] .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2101.12521v2">arXiv:2101.12521v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/yizuuwzvsbeajea653sksqbmie">fatcat:yizuuwzvsbeajea653sksqbmie</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210210192215/https://arxiv.org/pdf/2101.12521v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/d8/5e/d85eb82c77dbf7cbad1b0d20508f2b1473e9287f.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2101.12521v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Unsupervised Multi-Source Domain Adaptation for Person Re-Identification [article]

Zechen Bai, Zhigang Wang, Jian Wang, Di Hu, Errui Ding
<span title="2021-04-27">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Unsupervised domain adaptation (UDA) methods for person re-identification (re-ID) aim at transferring re-ID knowledge from labeled source data to unlabeled target data.  ...  Although achieving great success, most of them only use limited data from a single-source domain for model pre-training, making the rich labeled data insufficiently exploited.  ...  Related Work Unsupervised Domain Adaptation for Person Re-ID Mainstream unsupervised domain adaptation methods for person re-ID can be categorized into two branches.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2104.12961v1">arXiv:2104.12961v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/o2cvch6gorblxniv2fl5injnuy">fatcat:o2cvch6gorblxniv2fl5injnuy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210429152233/https://arxiv.org/pdf/2104.12961v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/fc/56/fc56ced05759ba1b2024ca77da8774439aefe93d.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2104.12961v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>
&laquo; Previous Showing results 1 &mdash; 15 out of 596 results