OpenMix: Exploring Outlier Samples for Misclassification Detection
文献类型:会议论文
作者 | Zhu Fei (朱飞); Zhen Cheng; Xu-Yao Zhang; Cheng-Lin Liu |
出版日期 | 2023-06-18 |
会议日期 | Jun 18-22, 2023 |
会议地点 | Vancouver canada |
英文摘要 | Reliable confidence estimation for deep neural classifiers is a challenging yet fundamental requirement in highstakes applications. Unfortunately, modern deep neural networks are often overconfident for their erroneous predictions. In this work, we exploit the easily available outlier samples, i.e., unlabeled samples coming from non-target classes, for helping detect misclassification errors. Particularly, we find that the well-known Outlier Exposure, which is powerful in detecting out-of-distribution (OOD) samples from unknown classes, does not provide any gain in identifying misclassification errors. Based on these observations, we propose a novel method called OpenMix, which incorporates open-world knowledge by learning to reject uncertain pseudo-samples generated via outlier transformation. OpenMix significantly improves confidence reliability under various scenarios, establishing a strong and unified framework for detecting both misclassified samples from known classes and OOD samples from unknown classes. The code is publicly available at https://github. com/Impression2805/OpenMix. |
会议录出版者 | IEEE/CVF |
源URL | [http://ir.ia.ac.cn/handle/173211/52407] |
专题 | 自动化研究所_模式识别国家重点实验室_模式分析与学习团队 |
通讯作者 | Zhu Fei (朱飞) |
作者单位 | 1.School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, 100049, China 2.MAIS, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China |
推荐引用方式 GB/T 7714 | Zhu Fei ,Zhen Cheng,Xu-Yao Zhang,et al. OpenMix: Exploring Outlier Samples for Misclassification Detection[C]. 见:. Vancouver canada. Jun 18-22, 2023. |
入库方式: OAI收割
来源:自动化研究所
其他版本
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。