DeepNCM: Deep Nearest Class Mean Classifiers

Samantha Guerriero, Barbara Caputo, Thomas Mensink

Abstract: In this paper we introduce DeepNCM, a Nearest Class Mean classification method enhanced to directly learn highly non-linear deep (visual) representations of the data. To overcome the computational expensive process of recomputing the class means after every update of the representation, we opt for approximating the class means with an online estimate. Moreover, to allow the class means to follow closely the drifting representation we introduce per epoch mean condensation. Using online class means with condensation, DeepNCM can train efficiently on large datasets. Our experimental results indicate that DeepNCM performs on par with SoftMax optimised networks.

TL;DR: We propose DeepNCM, an efficient NCM classifier which learns deep visual representations