Archive > Volume 13 Issue 6 > 2017,13(6):462-465. DOI:https://doi.org/10.1007/s11801-017-7198-z CSTR:[cstr] Prev Next
Discriminatively learning for representing local image features with quadruplet model
- Article
- Figures
- Metrics
- Preview PDF
- Reference
- Related
- Cited by
- Materials
Abstract:
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.
Keywords:
Project Supported:
Clc Number:
