ZHU Jie1, LI Nan1, RAO Xingnan1, WANG Jing1, WU Shufang2,3*
（1 Department of Information Management, The National Police University for Criminal Justice,Baoding 071000, Hebei, China;2 College of Management and Economics, Tianjin University, Tianjin 300072, China;3 College of Management, Hebei University, Baoding 071002, Hebei, China）
Abstract:
Tuning the weights of deep neural networks using loss and back propagation algorithm has been widely used in image retrieval. Applying triplet ranking loss to tune the weights can make the generated image representations preserve more semantic features. However, the relations among different categories of images are not fully considered in the triplet ranking loss.The quadruplet complete loss is proposed based on that inter-class similarity is smaller than the intra-class similarity, and the similarities among the query image and similar or dissimilar images are also fully considered in the loss.Further more, an effective quadruplet based deep hashing network architecture is also proposed for image retrieval. The experimental results show that our method can achieve excellent retrieval performance in CIFAR-10, SVHN and NUS-WIDE.
KeyWords:
quadruplet complete loss; adaptive margin; hash representation; image retrieval; artificial intelligence
