Title:	Triplet Loss with Channel Attention for Person Re-identification
Authors:	Organisciak, Daniel Riachy, Chirine Aslam, Nauman Shum, Hubert P. H.
Citation:	Journal of WSCG. 2019, vol. 27, no. 2, p. 161-169.
Issue Date:	2019
Publisher:	Václav Skala - UNION Agency
Document type:	článek article
URI:	http://hdl.handle.net/11025/35600
ISSN:	1213-6980 (CD-ROM) 1213-6972 (print) 1213-6964 (on-line)
Keywords:	opakovaná identifikace osoby;squeeze and excitation;trojnásobná ztráta;metrické učení;siamská síť;euklidy;pozornost kanálu
Keywords in different language:	person re-identification;squeeze and excitation;triplet loss;metric learning;siamese network;weighted Euclidean;channel attention
Abstract in different language:	The triplet loss function has seen extensive use within person re-identification. Most works focus on either improving the mining algorithm or adding new terms to the loss function itself. Our work instead concentrates on two other core components of the triplet loss that have been under-researched. First, we improve the standard Euclidean distance with dynamic weights, which are selected based on the standard deviation of features across the batch. Second, we exploit channel attention via a squeeze and excitation unit in the backbone model to emphasise important features throughout all layers of the model. This ensures that the output feature vector is a better representation of the image, and is also more suitable to use within our dynamically weighted Euclidean distance function. We demonstrate that our alterations provide significant performance improvement across popular reidentification data sets, including almost 10% mAP improvement on the CUHK03 data set. The proposed model attains results competitive with many state-of-the-art person re-identification models.
Rights:	© Václav Skala - UNION Agency
Appears in Collections:	Volume 27, Number 2 (2019)

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.