Distribution probability‐based self‐adaption metric learning for person re‐identification

Abstract

Person re-identification addresses the problem of pedestrian image matching in a nonoverlapped surveillance network. Traditional metric learning methods try to learn a fixed pedestrian images matching metric model. However, existing metric learning-based methods have the problem of overfitting the training data. In order to solve this problem, a sample-specific metric learning-based method is proposed. In the perspective of probability distribution, the over-fitting problem is attributed to the problem that the generalisation ability of projection features is weak. Firstly, the proposed method learns a metric subspace, which projects the raw feature to a discriminative subspace. Then, a projection feature selection method is established based on the probability distribution of positive image pairs. According to the proposed method, the probability that the test samples following the training data distribution is closely related to the adaptability. The proposed projection feature selection method selects different projection features for each individual's similarity distance measure. Finally, extensive experiments on four published datasets verify the effectiveness of the proposed metric learning method. It performs favourably against the comparison methods, especially on the rank-1 rate.

Adaptive Metric Learning for Dimensionality Reduction

“…The existence of 2, p l -norm makes it difficult to solve the objective function (3) directly. [30] adopts an iterative algorithm for solving the objective function in the form of 2, p l -norm.…”

“…Metric learning, which aims to supply a metric to measure the distance or simi-larity between the data, is a vital issue in the field of computer vision or pattern recognition. Metric learning has enormously wide spectrum of applications, such as classification [1] [2], person re-identification [3] [4], object tracking [5] [6], image retrieval [7], feature reduction [8] [9] and clustering [10] [11] [12] [13]. It should be noted that the performance of all these applications depends in part on the effectiveness of metric learning.…”

ACGAN: Age‐compensated makeup transfer based on homologous continuity generative adversarial network model

“…The other category is based on deep learning methods. With the continuous development of deep learning, it has a wide range of applications in various fields [3][4][5][6][7], and good results have been obtained in the field of makeup transformation. Some authors proposed a model based on deep local makeup migration; although this method can achieve the intensity of makeup control, the effect is not ideal and the overall effect is not natural enough.…”