.png){kind=icon}
返回
Synthetic unknown class learning for learning unknowns
.png){kind=icon}
OA
AI
DOI：10.1016/j.patcog.2024.110560.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
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, unknownis 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. Even though several generative OSR models have been proposed to explore more by generating synthetic samples and learning them as unknowns, the generated samples are limited to a small subspace of the known classes. Thus, this paper proposes a novel synthetic unknown class learning method that constantly generates unknown-like samples while maintaining diversity between the generated samples. By learning the unknownlike 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 by generating diverse realistic unknown samples.
Keyword:
Open set recognition
Overgeneralization
Knowledge distillation
Generative adversarial learning
Unknown
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
7.6
论文数:
1.3W
被引数:
4.5W
机构
引用论文
Understanding open-set recognition by Jacobian norm and inter-class separation.png)
PATTERN RECOGNITIONOAAI
PATTERN RECOGNITIONIF7.6
OAAI分享收藏Deep open-set recognition for silicon wafer production monitoring用于硅片生产监控的深度开集识别PATTERN RECOGNITIONOAAI
PATTERN RECOGNITIONIF7.6
OAAI分享收藏Joint Feature Generation and Open-set Prototype Learning for generalized zero-shot open-set classification广义零样本开集分类的联合特征生成和开集原型学习PATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏Teacher-Explorer-Student Learning: A Novel Learning Method for Open Set Recognition教师-探索者-学生学习: 一种新颖的开放集识别学习方法
OAAI
OAAI分享收藏
查看更多内容