Filters








3,266 Hits in 4.6 sec

Domain Adaptation through Synthesis for Unsupervised Person Re-identification [article]

Slawomir Bak, Peter Carr, Jean-Francois Lalonde
2018 arXiv   pre-print
Drastic variations in illumination across surveillance cameras make the person re-identification problem extremely challenging.  ...  To achieve better accuracy in unseen illumination conditions we propose a novel domain adaptation technique that takes advantage of our synthetic data and performs fine-tuning in a completely unsupervised  ...  -We improve re-identification accuracy in an unsupervised fashion using a novel three-step domain adaptation technique.  ... 
arXiv:1804.10094v1 fatcat:lenvoegct5bqfa554drwv7strq

Domain Adaptation Through Synthesis for Unsupervised Person Re-identification [chapter]

Sławomir Bąk, Peter Carr, Jean-François Lalonde
2018 Lecture Notes in Computer Science  
Drastic variations in illumination across surveillance cameras make the person re-identification problem extremely challenging.  ...  To achieve better accuracy in unseen illumination conditions we propose a novel domain adaptation technique that takes advantage of our synthetic data and performs fine-tuning in a completely unsupervised  ...  -We improve re-identification accuracy in an unsupervised fashion using a novel three-step domain adaptation technique.  ... 
doi:10.1007/978-3-030-01261-8_12 fatcat:fdpyp2dh7vf2jfrzzwduifbeee

Unsupervised Domain Adaptation in Person re-ID via k-Reciprocal Clustering and Large-Scale Heterogeneous Environment Synthesis [article]

Devinder Kumar, Parthipan Siva, Paul Marchwica, Alexander Wong
2020 arXiv   pre-print
In this paper, we address the aforementioned challenges faced in person re-identification for real-world, practical scenarios by introducing a novel, unsupervised domain adaptation approach for person  ...  This is accomplished through the introduction of: i) k-reciprocal tracklet Clustering for Unsupervised Domain Adaptation (ktCUDA) (for pseudo-label generation on target domain), and ii) Synthesized Heterogeneous  ...  Figure 2 . 2 Overview of the proposed k-reciprocal tracklet Clustering for Unsupervised Domain Adaptation (ktCUDA) in person re-ID.  ... 
arXiv:2001.04928v1 fatcat:p3kwnyb4bnebfhwhydjq2gvwaq

Dictionary-Based Domain Adaptation Methods for the Re-identification of Faces [chapter]

Qiang Qiu, Jie Ni, Rama Chellappa
2014 Person Re-Identification  
In particular, we discuss the adaptation of dictionary-based methods for re-identification of faces.  ...  Re-identification refers to the problem of recognizing a person at a different location after one has been captured by a camera at a previous location.  ...  We are interested in face re-identification as face is an important biometric signature to determine the identity of a person.  ... 
doi:10.1007/978-1-4471-6296-4_13 dblp:series/acvpr/QiuNC14 fatcat:w5ggcnr4kzglzfgpip37iamjsq

Unsupervised Domain Adaptation in Person re-ID via k-Reciprocal Clustering and Large-Scale Heterogeneous Environment Synthesis

Devinder Kumar, Parthipan Siva, Paul Marchwica, Alexander Wong
2020 2020 IEEE Winter Conference on Applications of Computer Vision (WACV)  
In this paper, we address the aforementioned challenges faced in person re-identification for real-world, practical scenarios by introducing a novel, unsupervised domain adaptation approach for person  ...  This is accomplished through the introduction of: i) k-reciprocal tracklet Clustering for Unsupervised Domain Adaptation (ktCUDA) (for pseudo-label generation on target domain), and ii) Synthesized Heterogeneous  ...  Figure 2 . 2 Overview of the proposed k-reciprocal tracklet Clustering for Unsupervised Domain Adaptation (ktCUDA) in person re-ID.  ... 
doi:10.1109/wacv45572.2020.9093606 dblp:conf/wacv/KumarSMW20 fatcat:qcdsyzsbsfe5fgvz7dc73jxejy

Joint Disentangling and Adaptation for Cross-Domain Person Re-Identification [article]

Yang Zou, Xiaodong Yang, Zhiding Yu, B.V.K. Vijaya Kumar, Jan Kautz
2020 arXiv   pre-print
Although a significant progress has been witnessed in supervised person re-identification (re-id), it remains challenging to generalize re-id models to new domains due to the huge domain gaps.  ...  Recently, there has been a growing interest in using unsupervised domain adaptation to address this scalability issue.  ...  We hope the proposed approach would inspire more work of integrating disentangling and adaptation for unsupervised cross-domain person re-id.  ... 
arXiv:2007.10315v1 fatcat:b63qxatktrbcpnsklapuzmuoey

Frustratingly Easy Person Re-Identification: Generalizing Person Re-ID in Practice [article]

Jieru Jia, Qiuqi Ruan, Timothy M. Hospedales
2019 arXiv   pre-print
This paper alleviates this issue by proposing a simple baseline for domain generalizable (DG) person re-identification.  ...  Contemporary person re-identification () methods usually require access to data from the deployment camera network during training in order to perform well.  ...  Method Setup For domain generalization person re-ID, we as- [7] .  ... 
arXiv:1905.03422v3 fatcat:2oarv5t3dvcmnklsmb2jrm47da

Transferable Joint Attribute-Identity Deep Learning for Unsupervised Person Re-identification

Jingya Wang, Xiatian Zhu, Shaogang Gong, Wei Li
2018 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition  
Most existing person re-identification (re-id) methods require supervised model learning from a separate large set of pairwise labelled training data for every single camera pair.  ...  to any new (unseen) target domain for re-id tasks without the need for collecting new labelled training data from the target domain (i.e. unsupervised learning in the target domain).  ...  Vision Semantics Ltd, Royal Society Newton Advanced Fellowship Programme (NA150459), and In-novateUK Industrial Challenge Project on Developing and Commercialising Intelligent Video Analytics Solutions for  ... 
doi:10.1109/cvpr.2018.00242 dblp:conf/cvpr/WangZGL18 fatcat:6t46zlmqendb5i2fbuorvsrcw4

UnrealPerson: An Adaptive Pipeline towards Costless Person Re-identification [article]

Tianyu Zhang and Lingxi Xie and Longhui Wei and Zijie Zhuang and Yongfei Zhang and Bo Li and Qi Tian
2020 arXiv   pre-print
The main difficulty of person re-identification (ReID) lies in collecting annotated data and transferring the model across different domains.  ...  This offers a good basis for unsupervised domain adaption, where our pre-trained model is easily plugged into the state-of-the-art algorithms towards higher accuracy.  ...  Conclusions This paper presents UnrealPerson, a novel pipeline for person re-identification (ReID).  ... 
arXiv:2012.04268v2 fatcat:t5euwqyoajdfndf6xr2avplyvq

Transferable Joint Attribute-Identity Deep Learning for Unsupervised Person Re-Identification [article]

Jingya Wang, Xiatian Zhu, Shaogang Gong, Wei Li
2018 arXiv   pre-print
Most existing person re-identification (re-id) methods require supervised model learning from a separate large set of pairwise labelled training data for every single camera pair.  ...  to any new (unseen) target domain for re-id tasks without the need for collecting new labelled training data from the target domain (i.e. unsupervised learning in the target domain).  ...  Vision Semantics Ltd, Royal Society Newton Advanced Fellowship Programme (NA150459), and In-novateUK Industrial Challenge Project on Developing and Commercialising Intelligent Video Analytics Solutions for  ... 
arXiv:1803.09786v1 fatcat:zgdruvntp5f7feds5czgfvh7wa

Unsupervised Tracklet Person Re-Identification [article]

Minxian Li, Xiatian Zhu, Shaogang Gong
2019 arXiv   pre-print
Extensive experiments demonstrate the superiority of the proposed model over the state-of-the-art unsupervised learning and domain adaptation person re-id methods on eight benchmarking datasets.  ...  Most existing person re-identification (re-id) methods rely on supervised model learning on per-camera-pair manually labelled pairwise training data.  ...  RELATED WORK Person Re-Identification.  ... 
arXiv:1903.00535v1 fatcat:b2y3min6ezhwrayhvtvo2pf27m

Unsupervised Tracklet Person Re-Identification

Minxian Li, Xiatian Zhu, Shaogang Gong
2019 IEEE Transactions on Pattern Analysis and Machine Intelligence  
Extensive experiments demonstrate the superiority of the proposed model over the state-of-the-art unsupervised learning and domain adaptation person re-id methods on eight benchmarking datasets.  ...  Most existing person re-identification (re-id) methods rely on supervised model learning on per-camera-pair manually labelled pairwise training data.  ...  RELATED WORK Person Re-Identification.  ... 
doi:10.1109/tpami.2019.2903058 pmid:30843803 fatcat:sdwp2cebhfhw3aszo5jptwzlkm

Instance-Guided Context Rendering for Cross-Domain Person Re-Identification

Yanbei Chen, Xiatian Zhu, Shaogang Gong
2019 2019 IEEE/CVF International Conference on Computer Vision (ICCV)  
Existing person re-identification (re-id) methods mostly assume the availability of large-scale identity labels for model learning in any target domain deployment.  ...  Unlike previous image synthesis methods that transform the source person images into limited fixed target styles, our approach produces more visually plausible, and diverse synthetic training data.  ...  Related Work Unsupervised Cross-Domain Person Re-Identification aims to transfer the identity discriminative knowledge from a labelled source domain to an unlabelled target domain.  ... 
doi:10.1109/iccv.2019.00032 dblp:conf/iccv/ChenZG19 fatcat:2ehie77suzbnjpa7hhgzwwwcce

Lifelong Unsupervised Domain Adaptive Person Re-identification with Coordinated Anti-forgetting and Adaptation [article]

Zhipeng Huang, Zhizheng Zhang, Cuiling Lan, Wenjun Zeng, Peng Chu, Quanzeng You, Jiang Wang, Zicheng Liu, Zheng-jun Zha
2022 arXiv   pre-print
Unsupervised domain adaptive person re-identification (ReID) has been extensively investigated to mitigate the adverse effects of domain gaps.  ...  In this paper, to address more practical scenarios, we propose a new task, Lifelong Unsupervised Domain Adaptive (LUDA) person ReID.  ...  Our contributions can be summarized in three aspects: Related Works Domain Adaptive Person Re-identification Person re-identification (ReID) has been widely investigated and applied in many real-world  ... 
arXiv:2112.06632v2 fatcat:sninsegzbjhkrcw6vmmr22mxaq

Unsupervised clothing change adaptive person ReID [article]

Ziyue Zhang, Shuai Jiang, Congzhentao Huang, Richard YiDa Xu
2021 arXiv   pre-print
We design a novel unsupervised model, Sync-Person-Cloud ReID, to solve the unsupervised clothing change person ReID problem.  ...  For the last challenge, some researchers try to make model learn information from a labeled dataset as a source to an unlabeled dataset. Whereas purely unsupervised training is less used.  ...  Introduction Person re-identification (ReID) (Ye et al. 2021) is designed to match specific pedestrians in images or video sequences.  ... 
arXiv:2109.03702v2 fatcat:m37puuo2tfanbidhgh4pluzpnu
« Previous Showing results 1 — 15 out of 3,266 results