Ring-push metric learning for person reidentification

He, Botao; Yu, Shaohua

doi:10.1117/1.jei.26.3.033005

Cited by 4 publications

(1 citation statement)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Many new solutions have been developed in recent years, which can be classified into two groups: the feature-based methods [1][2][3][4][5][6] and the model training-based methods. [7][8][9][10][11][12][13][14][15][16][17][18] Among the model training-based methods, metric learning, [7][8][9][10] multitask learning, [11][12][13] and dictionary learning (also known as sparse coding) [14][15][16][17][18] are studied largely. Apart from the above-mentioned, methods based on deep learning have achieved satisfying accuracy in computer vision, including re-id problem, [19][20][21] whether it is based on the method of extracting deep features or the end-to-end method.…”

Section: Introductionmentioning

confidence: 99%

Person reidentification by semisupervised dictionary rectification learning with retraining module

et al. 2018

View full text Add to dashboard Cite

At present, in the field of person reidentification (re-id), the commonly used supervised learning algorithms require a large amount of labeled samples, which is not conducive to the model promotion. On the other hand, the accuracy of unsupervised learning algorithms is lower than supervised algorithms due to the lack of discriminant information. To address these issues, we make use of a small amount of labeled samples to add discriminant information in the basic dictionary learning. Moreover, the sparse coefficients of dictionary learning are decomposed into a projection problem of the original features, and the projection matrix is trained by labeled samples, which is transformed into a metric learning problem. It thus integrates the advantages of the two methods through combining dictionary learning and metric learning. After the data are trained, a projection matrix is used to project the unlabeled features into a feature subspace and the labels of the samples are reconstructed. The semisupervised learning problem is then transformed to a supervised learning problem with a graph regularization term. Experiments on different public pedestrian datasets, such as VIPeR, PRID, iLIDS, and CUHK01, show that the recognition accuracy of our method is better than some other existing person re-id methods. © The Authors. Published by SPIE under a Creative Commons Attribution 3.0 Unported License. Distribution or reproduction of this work in whole or in part requires full attribution of the original publication, including its DOI.

show abstract