Learning Spread-Out Local Feature Descriptors

Xu Zhang, Felix X. Yu, Sanjiv Kumar, Shih-Fu Chang; The IEEE International Conference on Computer Vision (ICCV), 2017, pp. 4595-4603

Abstract


We propose a simple, yet powerful regularization technique that can be used to significantly improve both the pairwise and triplet losses in learning local feature descriptors. The idea is that in order to fully utilize the expressive power of the descriptor space, good local feature descriptors should be sufficiently "spread-out" over the space. In this work, we propose a regularization term to maximize the spread in feature descriptor inspired by the property of uniform distribution. We show that the proposed regularization with triplet loss outperforms existing Euclidean distance based descriptor learning techniques by a large margin. As an extension, the proposed regularization technique can also be used to improve image-level deep feature embedding.

Related Material


[pdf] [arXiv] [video]
[bibtex]
@InProceedings{Zhang_2017_ICCV,
author = {Zhang, Xu and Yu, Felix X. and Kumar, Sanjiv and Chang, Shih-Fu},
title = {Learning Spread-Out Local Feature Descriptors},
booktitle = {The IEEE International Conference on Computer Vision (ICCV)},
month = {Oct},
year = {2017}
}