Knowledge Commons of Institute of Automation,CAS
OpenMix: Exploring Outlier Samples for Misclassification Detection | |
Zhu Fei (朱飞)![]() ![]() ![]() | |
2023-06-18 | |
会议名称 | IEEE/CVF Conference on Computer Vision and Pattern Recognition |
会议日期 | Jun 18-22, 2023 |
会议地点 | Vancouver canada |
出版者 | IEEE/CVF |
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. |
是否为代表性论文 | 是 |
七大方向——子方向分类 | 模式识别基础 |
国重实验室规划方向分类 | 人工智能基础前沿理论 |
是否有论文关联数据集需要存交 | 否 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/52407 |
专题 | 多模态人工智能系统全国重点实验室_模式分析与学习 |
通讯作者 | Zhu Fei (朱飞) |
作者单位 | 1.MAIS, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China 2.School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, 100049, 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]:IEEE/CVF,2023. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
Zhu_OpenMix_Explorin(2384KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
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。
修改评论