An end-to-end exemplar association for unsupervised person Re-identification

Authors: Wu, J., Yang, Y., Lei, Z., Wang, J., Li, S.Z., Tiwari, P. and Pandey, H.M.

Journal: Neural Networks

Volume: 129

Pages: 43-54

eISSN: 1879-2782

ISSN: 0893-6080

DOI: 10.1016/j.neunet.2020.05.015

Abstract:

Tracklet association methods learn the cross camera retrieval ability though associating underlying cross camera positive samples, which have proven to be successful in unsupervised person re-identification task. However, most of them use poor-efficiency association strategies which costs long training hours but gains the low performance. To solve this, we propose an effective end-to-end exemplar associations (EEA) framework in this work. EEA mainly adapts three strategies to improve efficiency: (1) end-to-end exemplar-based training, (2) exemplar association and (3) dynamic selection threshold. The first one is to accelerate the training process, while the others aim to improve the tracklet association precision. Compared with existing tracklet associating methods, EEA obviously reduces the training cost and achieves the higher performance. Extensive experiments and ablation studies on seven RE-ID datasets demonstrate the superiority of the proposed EEA over most state-of-the-art unsupervised and domain adaptation RE-ID methods.

Source: Scopus

An end-to-end exemplar association for unsupervised person Re-identification.

Authors: Wu, J., Yang, Y., Lei, Z., Wang, J., Li, S.Z., Tiwari, P. and Pandey, H.M.

Journal: Neural Netw

Volume: 129

Pages: 43-54

eISSN: 1879-2782

DOI: 10.1016/j.neunet.2020.05.015

Abstract:

Tracklet association methods learn the cross camera retrieval ability though associating underlying cross camera positive samples, which have proven to be successful in unsupervised person re-identification task. However, most of them use poor-efficiency association strategies which costs long training hours but gains the low performance. To solve this, we propose an effective end-to-end exemplar associations (EEA) framework in this work. EEA mainly adapts three strategies to improve efficiency: (1) end-to-end exemplar-based training, (2) exemplar association and (3) dynamic selection threshold. The first one is to accelerate the training process, while the others aim to improve the tracklet association precision. Compared with existing tracklet associating methods, EEA obviously reduces the training cost and achieves the higher performance. Extensive experiments and ablation studies on seven RE-ID datasets demonstrate the superiority of the proposed EEA over most state-of-the-art unsupervised and domain adaptation RE-ID methods.

Source: PubMed

An end-to-end exemplar association for unsupervised person Re-identification

Authors: Wu, J., Yang, Y., Lei, Z., Wang, J., Li, S.Z., Tiwari, P. and Pandey, H.M.

Journal: NEURAL NETWORKS

Volume: 129

Pages: 43-54

eISSN: 1879-2782

ISSN: 0893-6080

DOI: 10.1016/j.neunet.2020.05.015

Source: Web of Science (Lite)

An end-to-end exemplar association for unsupervised person Re-identification.

Authors: Wu, J., Yang, Y., Lei, Z., Wang, J., Li, S.Z., Tiwari, P. and Pandey, H.M.

Journal: Neural networks : the official journal of the International Neural Network Society

Volume: 129

Pages: 43-54

eISSN: 1879-2782

ISSN: 0893-6080

DOI: 10.1016/j.neunet.2020.05.015

Abstract:

Tracklet association methods learn the cross camera retrieval ability though associating underlying cross camera positive samples, which have proven to be successful in unsupervised person re-identification task. However, most of them use poor-efficiency association strategies which costs long training hours but gains the low performance. To solve this, we propose an effective end-to-end exemplar associations (EEA) framework in this work. EEA mainly adapts three strategies to improve efficiency: (1) end-to-end exemplar-based training, (2) exemplar association and (3) dynamic selection threshold. The first one is to accelerate the training process, while the others aim to improve the tracklet association precision. Compared with existing tracklet associating methods, EEA obviously reduces the training cost and achieves the higher performance. Extensive experiments and ablation studies on seven RE-ID datasets demonstrate the superiority of the proposed EEA over most state-of-the-art unsupervised and domain adaptation RE-ID methods.

Source: Europe PubMed Central