Home > Research > Publications & Outputs > Identity adaptation for person re-identification

Associated organisational unit

Links

Text available via DOI:

View graph of relations

Identity adaptation for person re-identification

Research output: Contribution to Journal/MagazineJournal articlepeer-review

E-pub ahead of print

Standard

Identity adaptation for person re-identification. / Ke, Qiuhong; Bennamoun, Mohammed; Rahmani, Hossein et al.
In: IEEE Access, Vol. 6, 31.08.2018, p. 48147-48145.

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Harvard

Ke, Q, Bennamoun, M, Rahmani, H, An, S, Sohel, F & Boussaid, F 2018, 'Identity adaptation for person re-identification', IEEE Access, vol. 6, pp. 48147-48145. https://doi.org/10.1109/ACCESS.2018.2867898

APA

Ke, Q., Bennamoun, M., Rahmani, H., An, S., Sohel, F., & Boussaid, F. (2018). Identity adaptation for person re-identification. IEEE Access, 6, 48147-48145. Advance online publication. https://doi.org/10.1109/ACCESS.2018.2867898

Vancouver

Ke Q, Bennamoun M, Rahmani H, An S, Sohel F, Boussaid F. Identity adaptation for person re-identification. IEEE Access. 2018 Aug 31;6:48147-48145. Epub 2018 Aug 31. doi: 10.1109/ACCESS.2018.2867898

Author

Ke, Qiuhong ; Bennamoun, Mohammed ; Rahmani, Hossein et al. / Identity adaptation for person re-identification. In: IEEE Access. 2018 ; Vol. 6. pp. 48147-48145.

Bibtex

@article{b3f9cd2a7753462b839e406d4e0e8a91,
title = "Identity adaptation for person re-identification",
abstract = "Person re-identification (re-ID), which aims to identify the same individual from a gallerycollected with different cameras, has attracted increasing attention in the multimedia retrieval community.Current deep learning methods for person re-ID focus on learning classification models on training identities to obtain an ID-discriminative embedding (IDE) extractor, which is used to extract features from testing images for re-ID. The IDE features of the testing identities might not be discriminative due to that the training identities are different from the testing identities. In this paper, we introduce a new ID-adaptation network (ID-AdaptNet), which aims to improve the discriminative power of the IDE features of the testing identities for better person re-ID. The main idea of the ID-AdaptNet is to transform the IDE features to acommon discriminative latent space, where the representations of the {\textquoteleft}{\textquoteleft}seen{\textquoteright}{\textquoteright} training identities are enforcedto adapt to those of the {\textquoteleft}{\textquoteleft}unseen{\textquoteright}{\textquoteright} training identities. More specifically, the ID-AdaptNet is trained bysimultaneously minimizing the classification cross-entropy and the discrepancy between the {\textquoteleft}{\textquoteleft}seen{\textquoteright}{\textquoteright} and the{\textquoteleft}{\textquoteleft}unseen{\textquoteright}{\textquoteright} training identities in the hidden space. To calculate the discrepancy, we represent their probabilitydistributions as moment sequences and calculate their distance using their central moments. We furtherpropose a stacking ID-AdaptNet that jointly trains multiple ID-AdaptNets with a regularization methodfor better re-ID. Experiments show that the ID-AdaptNet and stacking ID-AdaptNet effectively improve thediscriminative power of IDE features.",
author = "Qiuhong Ke and Mohammed Bennamoun and Hossein Rahmani and Senjian An and Ferdous Sohel and Farid Boussaid",
year = "2018",
month = aug,
day = "31",
doi = "10.1109/ACCESS.2018.2867898",
language = "English",
volume = "6",
pages = "48147--48145",
journal = "IEEE Access",
issn = "2169-3536",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

RIS

TY - JOUR

T1 - Identity adaptation for person re-identification

AU - Ke, Qiuhong

AU - Bennamoun, Mohammed

AU - Rahmani, Hossein

AU - An, Senjian

AU - Sohel, Ferdous

AU - Boussaid, Farid

PY - 2018/8/31

Y1 - 2018/8/31

N2 - Person re-identification (re-ID), which aims to identify the same individual from a gallerycollected with different cameras, has attracted increasing attention in the multimedia retrieval community.Current deep learning methods for person re-ID focus on learning classification models on training identities to obtain an ID-discriminative embedding (IDE) extractor, which is used to extract features from testing images for re-ID. The IDE features of the testing identities might not be discriminative due to that the training identities are different from the testing identities. In this paper, we introduce a new ID-adaptation network (ID-AdaptNet), which aims to improve the discriminative power of the IDE features of the testing identities for better person re-ID. The main idea of the ID-AdaptNet is to transform the IDE features to acommon discriminative latent space, where the representations of the ‘‘seen’’ training identities are enforcedto adapt to those of the ‘‘unseen’’ training identities. More specifically, the ID-AdaptNet is trained bysimultaneously minimizing the classification cross-entropy and the discrepancy between the ‘‘seen’’ and the‘‘unseen’’ training identities in the hidden space. To calculate the discrepancy, we represent their probabilitydistributions as moment sequences and calculate their distance using their central moments. We furtherpropose a stacking ID-AdaptNet that jointly trains multiple ID-AdaptNets with a regularization methodfor better re-ID. Experiments show that the ID-AdaptNet and stacking ID-AdaptNet effectively improve thediscriminative power of IDE features.

AB - Person re-identification (re-ID), which aims to identify the same individual from a gallerycollected with different cameras, has attracted increasing attention in the multimedia retrieval community.Current deep learning methods for person re-ID focus on learning classification models on training identities to obtain an ID-discriminative embedding (IDE) extractor, which is used to extract features from testing images for re-ID. The IDE features of the testing identities might not be discriminative due to that the training identities are different from the testing identities. In this paper, we introduce a new ID-adaptation network (ID-AdaptNet), which aims to improve the discriminative power of the IDE features of the testing identities for better person re-ID. The main idea of the ID-AdaptNet is to transform the IDE features to acommon discriminative latent space, where the representations of the ‘‘seen’’ training identities are enforcedto adapt to those of the ‘‘unseen’’ training identities. More specifically, the ID-AdaptNet is trained bysimultaneously minimizing the classification cross-entropy and the discrepancy between the ‘‘seen’’ and the‘‘unseen’’ training identities in the hidden space. To calculate the discrepancy, we represent their probabilitydistributions as moment sequences and calculate their distance using their central moments. We furtherpropose a stacking ID-AdaptNet that jointly trains multiple ID-AdaptNets with a regularization methodfor better re-ID. Experiments show that the ID-AdaptNet and stacking ID-AdaptNet effectively improve thediscriminative power of IDE features.

U2 - 10.1109/ACCESS.2018.2867898

DO - 10.1109/ACCESS.2018.2867898

M3 - Journal article

VL - 6

SP - 48147

EP - 48145

JO - IEEE Access

JF - IEEE Access

SN - 2169-3536

ER -