Separability and Compactness Network for Image Recognition and Superresolution

• Published in: IEEE transaction on neural networks and learning systems Vol. 30; no. 11; pp. 3275 - 3286
• Main Authors: Zhou, Liguo, Wang, Zhongyuan, Luo, Yimin, Xiong, Zixiang
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.11.2019; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Artificial neural networks; Classification; Convolutional neural networks (CNNs); cosine distance loss; Face; Face recognition; Image classification; Image processing; Image resolution; image superresolution (SR); Loss measurement; Neural networks; Object recognition; Organizations; Pattern recognition; Satellite imagery; satellite video; Satellites; softmax loss; Task analysis; Training; Visual tasks
• ISSN: 2162-237X; 2162-2388; 2162-2388
• DOI: 10.1109/TNNLS.2018.2890550

Convolutional neural networks (CNNs) have wide applications in pattern recognition and image processing. Despite recent advances, much remains to be done for CNNs to learn a better representation of image samples. Therefore, constant optimizations should be provided on CNNs. To achieve a good performance on classification, intuitively, samples' interclass separability, or intraclass compactness should be simultaneously maximized. Accordingly, in this paper, we propose a new network, named separability and compactness network (SCNet) to rectify this problem. SCNet minimizes the softmax loss and the distance between features of samples from the same class under a jointly supervised framework, resulting in simultaneous maximization of interclass separability and intraclass compactness of samples. Furthermore, considering the convenience and the efficiency of the cosine similarity in face recognition tasks, we incorporate it into SCNet's distance metric to enable sample features from the same class to line up in the same direction and those from different classes to have a large angle of separation. We apply SCNet to three different tasks: visual classification, face recognition, and image superresolution. Experiments on both public data sets and real-world satellite images validate the effectiveness of our SCNet.