arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2111.08062cs.CV
收藏

学习未知数的合成未知类学习

Synthetic Unknown Class Learning for Learning Unknowns

Northwestern University(西北大学)

Jaeyeon Jang

摘要:

本文讨论了开集识别(OSR)问题,其目标是正确分类已知类的样本,同时检测未知样本拒绝。在OSR问题中,“未知”被假设为具有无限的可能性,因为我们在未知出现之前对它们一无所知。直觉上,OSR系统探索未知的可能性越多,就越有可能检测到未知。因此,本文提出了一种新的合成未知类学习方法,生成未知类样本,同时保持所生成的样本之间的多样性,并学习这些样本。除了这个未知样本生成过程外,还引入了知识蒸馏,为学习合成未知量提供了空间。通过交替学习类未知样本和已知样本,该方法不仅可以体验不同的合成未知数,而且还可以减少相对于已知类的过度泛化。在多个基准数据集上的实验表明,该方法的性能明显优于其他最先进的方法。它还表明,现实的未知数字可以通过所提出的方法在MNIST数据集上训练后生成和学习。

英文摘要:

This paper addresses the open set recognition (OSR) problem, where the goal is to correctly classify samples of known classes while detecting unknown samples to reject. In the OSR problem, "unknown" is assumed to have infinite possibilities because we have no knowledge about unknowns until they emerge. Intuitively, the more an OSR system explores the possibilities of unknowns, the more likely it is to detect unknowns. Thus, this paper proposes a novel synthetic unknown class learning method that generates unknown-like samples while maintaining diversity between the generated samples and learns these samples. In addition to this unknown sample generation process, knowledge distillation is introduced to provide room for learning synthetic unknowns. By learning the unknown-like samples and known samples in an alternating manner, the proposed method can not only experience diverse synthetic unknowns but also reduce overgeneralization with respect to known classes. Experiments on several benchmark datasets show that the proposed method significantly outperforms other state-of-the-art approaches. It is also shown that realistic unknown digits can be generated and learned via the proposed method after training on the MNIST dataset.

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。

↑