Person re-identification based on linear classification margin

2nd International Symposium on Application of Materials Science and Energy Materials

材料科学;能源学

Chen, Bing^1 ; Zha, Yufei^1 ; Min, Wu^1 ; Yuan, Zhou^1

Aeronautics Engineering College, Air Force Engineering University, Xi'an

710038, China^1

关键词: Classification margins;    Convolutional neural network;    Discriminative ability;    Discriminative features;    Discriminative power;    Geometric interpretation;    Linear classification;    Person re identifications;   

Others  :  https://iopscience.iop.org/article/10.1088/1757-899X/490/4/042006/pdf
DOI  :  10.1088/1757-899X/490/4/042006

学科分类：材料科学（综合）

来源: IOP

【 摘 要 】

The core of the person re-identification task is to find a discriminative feature map or a good measure to measure the similarity between two pedestrians. Under the traditional softmax loss function constraint, the characteristics of the FC layer output of the convolutional neural network are only separable and the discriminative ability is insufficient. Our proposes a person re-ID method based on decision margin. By adding the traditional softmax loss function to the angle decision margin, the characteristics of strong discriminative power in network learning are enhanced. This paper provides a clear geometric interpretation by normalizing the last fully connected layer parameters and pedestrian characteristics of the network and projecting the embedded features into the geometric space for person re-identification. Combining two different classification margins, a linear classification margin is proposed and good performance is achieved. This paper validates the effectiveness of the algorithm on the mainstream databases of Market1501 and DukeMTMC-reID. The results show that our method can get more discriminative features, and its experimental performance is significantly improved compared to the existing advanced algorithms.