Hyperspherical embedding for novel class classification

Rafael S. Pereira, alexis joly, Patrick Valduriez, Fábio Porto

Keywords: Metric Learning, open set, deep learning

Abstract:

Deep neural networks proved to be useful to learn representations and perform classification on many different modalities of data. Traditional approaches work well on the closed set problem. For learning tasks involving novel classes, known as the open set problem, the metric learning approach has been proposed. However, while promising, common metric learning approaches require pairwise learning, which significantly increases training cost while adding additional challenges. In this paper we present a method in which the similarity of samples projected onto a feature space is enforced by a metric learning approach without requiring
pairwise evaluation. We compare our approach against known methods in different datasets, achieving results up to $81\%$ more accurate.

One-sentence Summary: An novel metric learning approach which is cheap to optimize and weights for novel classes can be analitically defined.

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/arxiv:2102.03243/code)