Open AccessLearning deep discriminative features based on cosine loss function
Author(s) -
Wang Jiabao,
Li Yang,
Miao Zhuang,
Xu Yulong,
Tao Gang
Publication year - 2017
Publication title -
electronics letters
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.375
H-Index - 146
eISSN - 1350-911X
pISSN - 0013-5194
DOI - 10.1049/el.2017.0523
Subject(s) - discriminative model , cosine similarity , artificial intelligence , pattern recognition (psychology) , feature (linguistics) , similarity (geometry) , feature learning , convolutional neural network , computer science , deep learning , trigonometric functions , representation (politics) , discrete cosine transform , feature extraction , mathematics , image (mathematics) , geometry , philosophy , linguistics , politics , political science , law
Deep feature representation is widely used in various visual applications. However, the feature extracted by the convolutional neural networks (CNNs) is inappropriate for cosine similarity measurement. Because the classical CNNs are designed for classification rather than for similarity comparison. A novel cosine loss function for learning deep discriminative features, which are fit to the cosine similarity measurement, is designed. The loss can constrain the distribution of the features in the same class to be in a narrow angle region. Furthermore, a discriminative feature learning network framework and its corresponding two‐stage learning method to learn the parameters is proposed. Experimental results show that the proposed method achieves state‐of‐the‐art performance on the public Cifar10 and Market1501 datasets.