One Representation to Rule Them All: Identifying Out-of-Support Examples in Few-shot Learning with Generic Representations

Anonymous

Keywords: few-shot learning, out-of-distribution detection, representation learning, 'none-of-the-above' detection

TL;DR: We propose a new method for identifying when a query instance does not correspond to any labeled support class within the episodic framework of few-shot learning.

Abstract: The field of few-shot learning has made remarkable strides in developing powerful models that can operate in the small data regime. Nearly all of these methods assume every unlabeled instance encountered will belong to a handful of known classes for which one has examples. This can be problematic for real-world use cases where one routinely finds 'none-of-the-above' examples. In this paper we describe this challenge of identifying what we term `out-of-support' (OOS) examples. We describe how this problem is subtly different from out-of-distribution detection and describe a new method of identifying OOS examples within the Prototypical Networks framework using a fixed point which we call the generic representation. We show that our method outperforms other existing approaches in the literature as well as other approaches that we propose in this paper. Finally, we investigate how the use of such a generic point affects the geometry of a model's feature space.