← Search

Anastasiia Mishchuk

2 accepted papers

2019

Beyond Cartesian Representations for Local Descriptors

ICCV 2019poster

The dominant approach for learning local patch descriptors relies on small image regions whose scale must be properly estimated a priori by a keypoint detector. In other words, if two patches are not in correspondence, their descriptors will not match. A strategy often used to alleviate this problem…

Cited by 135PDFcodeScholar
2017

Working hard to know your neighbor's margins: Local descriptor learning loss

NeurIPS 2017poster

We introduce a loss for metric learning, which is inspired by the Lowe's matching criterion for SIFT. We show that the proposed loss, that maximizes the distance between the closest positive and closest negative example in the batch, is better than complex regularization methods; it works well for b…