Zobrazeno 1 - 1
of 1
pro vyhledávání: '"David McNeely-White"'
We present evidence that many common convolutional neural networks (CNNs) trained for face verification learn functions that are nearly equivalent under rotation. More specifically, we demonstrate that one face verification model's embeddings (i.e. l
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8febec5396baed37b683433f1b21695a
http://arxiv.org/abs/2106.07822
http://arxiv.org/abs/2106.07822
