arXiv Open Access 2020

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

Christof Henkel Philipp Singer

Lihat Sumber

Abstrak

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.

Topik & Kata Kunci

cs.CV cs.LG

Penulis (2)

Christof Henkel

Philipp Singer

Format Sitasi

APA MLA BibTeX

Henkel, C., Singer, P. (2020). Supporting large-scale image recognition with out-of-domain samples. https://arxiv.org/abs/2010.01650

Akses Cepat

Lihat di Sumber

Informasi Jurnal

Tahun Terbit: 2020
Bahasa: en
Sumber Database: arXiv
Akses: Open Access ✓