Working hard to know your neighbor's margins:Local descriptor learning loss
Anastasiya Mishchuk
and
Dmytro Mishkin
and
Filip Radenovic
and
Jiri Matas
arXiv e-Print archive - 2017 via Local arXiv
Keywords:
cs.CV
First published: 2017/05/30 (7 years ago) Abstract: We introduce a novel loss for learning local feature descriptors that is
inspired by the SIFT matching scheme. We show that the proposed loss that
relies on the maximization of the distance between the closest positive and
closest negative patches can replace more complex regularization methods which
have been used in local descriptor learning; it works well for both shallow and
deep convolution network architectures. The resulting descriptor is compact --
it has the same dimensionality as SIFT (128), it shows state-of-art performance
on matching, patch verification and retrieval benchmarks and it is fast to
compute on a GPU.
