Discriminatively learning for representing local image features with quadruplet model

• 来源期刊: 光电子快报（英文版）
• 年，卷（期）: 2017,（6）
• 页码范围: 462-465
• 页数: 4页
• 语种: 英文
• DOI: 10.1007/s11801-017-7198-z

摘要

Traditional hand-crafted features for representing local image patches are evolving into current data-driven and learning-based image feature,but learning a robust and discriminative descriptor which is capable of controlling various patch-level computer vision tasks is still an open problem.In this work,we propose a novel deep convolutional neural network (CNN) to learn local feature descriptors.We utilize the quadruplets with positive and negative training samples,together with a constraint to restrict the intra-class variance,to learn good discriminative CNN representations.Compared With previous works,our model reduces the overlap in feature space between corresponding and non-corresponding patch pairs,and mitigates margin varying problem caused by commonly used triplet loss.We demonstrate that our method achieves better embedding result than some latest works,like PN-Net and TN-TG,on benchmark dataset.