arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2106.01423cs.LGcs.AIcs.CVmath.MG
收藏

一种表示来统治所有的例子:用泛型表示识别少样本学习中的支持度外的例子

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

Pacific Northwest National Laboratory(太平洋西北国家实验室)
Henry Kvinge, Scott Howland, Nico Courts, Lauren A. Phillips, John Buckheit, Zachary New, Elliott Skomski, Jung H. Lee, Sandeep Tiwari, Jessica Hibler, Courtney… 展开作者

Henry Kvinge, Scott Howland, Nico Courts, Lauren A. Phillips, John Buckheit, Zachary New, Elliott Skomski, Jung H. Lee, Sandeep Tiwari, Jessica Hibler, Courtney D. Corley, Nathan O. Hodas

摘要:

少样本学习领域在开发能够在小数据范围内运行的强大模型方面取得了显著的进步。几乎所有这些方法都假设遇到的每个未标记的实例将属于少数已知的类,其中一个有例子。这对于现实世界的用例来说可能是有问题的,因为人们经常会发现“非上述”的例子。在本文中,我们描述了这种挑战,确定我们所谓的“不支持”(OOS)的例子。我们描述了这个问题是如何微妙的不同,从分布外检测,并描述了一种新的方法,确定OOS的例子在原型网络框架内使用一个固定的点,我们称之为通用表示。我们表明,我们的方法优于其他现有的方法在文献中,以及其他方法,我们在本文中提出的。最后,我们研究如何使用这样一个通用点影响模型的特征空间的几何形状。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑