Dmytro Mishkin presents HardNet: a Convolutional Network for Local Image Description
On 2017-06-06 14:30:00 at G205, Karlovo náměstí 13, Praha 2
In the talk, a novel loss for learning local feature descriptors inspired by
the
SIFT matching scheme will be presented. 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. The loss 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.
the
SIFT matching scheme will be presented. 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. The loss 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.