arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2103.12871cs.CVcs.AI
收藏

教师-探索者-学生学习:一种新的开集识别学习方法

Teacher-Explorer-Student Learning: A Novel Learning Method for Open Set Recognition

Yonsei University(延世大学)

Jaeyeon Jang, Chang Ouk Kim

摘要:

如果出现了在训练过程中没有看到的未知样本,大多数识别系统通常会产生过度概括的结果,并确定该样本属于已知类别之一。为了解决这个问题,教师-探索者-学生(T/E/S)学习,它采用了开集识别(OSR)的概念,旨在拒绝未知样本,同时最大限度地减少已知样本的分类性能损失,在这项研究中提出。在这种新颖的学习方法中,通过探索未知数的各种可能性,大大减少了深度学习分类器的过度泛化。在这里,教师网络通过提取关于已知的预先训练的知识来提取关于未知的一些提示,并将此提取的知识传递给学生。在学习了提炼的知识之后,学生网络与探索者网络共享所学习的信息。然后,探索者网络通过生成类似未知的样本并将样本馈送到学生网络来共享其探索结果。通过重复这种交替学习过程,学生网络经历了各种合成未知数,减少了过度泛化。实验结果表明,本文提出的每个组件都对OSR性能的提高有显著的贡献。因此,所提出的T/E/S学习方法优于当前最先进的方法。

英文摘要:

If an unknown example that is not seen during training appears, most recognition systems usually produce overgeneralized results and determine that the example belongs to one of the known classes. To address this problem, teacher-explorer-student (T/E/S) learning, which adopts the concept of open set recognition (OSR) that aims to reject unknown samples while minimizing the loss of classification performance on known samples, is proposed in this study. In this novel learning method, overgeneralization of deep learning classifiers is significantly reduced by exploring various possibilities of unknowns. Here, the teacher network extracts some hints about unknowns by distilling the pretrained knowledge about knowns and delivers this distilled knowledge to the student. After learning the distilled knowledge, the student network shares the learned information with the explorer network. Then, the explorer network shares its exploration results by generating unknown-like samples and feeding the samples to the student network. By repeating this alternating learning process, the student network experiences a variety of synthetic unknowns, reducing overgeneralization. Extensive experiments were conducted, and the experimental results showed that each component proposed in this paper significantly contributes to the improvement in OSR performance. As a result, the proposed T/E/S learning method outperformed current state-of-the-art methods.

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。

↑