Supporting large-scale image recognition with out-of-domain samples

10/04/2020
by   Christof Henkel, et al.
0

This article presents an efficient end-to-end method to perform instance-level recognition employed to the task of labeling and ranking landmark images. In a first step, we embed images in a high dimensional feature space using convolutional neural networks trained with an additive angular margin loss and classify images using visual similarity. We then efficiently re-rank predictions and filter noise utilizing similarity to out-of-domain images. Using this approach we achieved the 1st place in the 2020 edition of the Google Landmark Recognition challenge.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset