Knowledge Commons of Institute of Automation,CAS
Out-of-Distribution Detection for Reliable Face Recognition | |
Yu C(于畅)1,2![]() ![]() ![]() ![]() | |
发表期刊 | IEEE Signal Processing Letters
![]() |
2020 | |
页码 | 710-714 |
摘要 | In real applications, face recognition systems are always faced with non-face inputs and low-quality faces due to the complicated conditions like mis-detections by face detectors. However, in deep learning based methods, these outliers are always ignored during training phase and the models tend to make unreasonable decisions on these images. For example, matching a texturerich patch to an old-man face overconfidently. We formulate this challenge on the task of out-of-distribution detection (OOD), where a network must determine whether or not an input is outside of the set on which the network can safely perform. In this paper, we propose to detect out-of-distribution samples based on uncertainty prediction and the L2-norm of features, so as to effectively filter out non-face and low-quality faces. We demonstrate that the proposed method can reliably detect out-of-distribution samples and improve the performance of face recognition, without the need of labelled OOD data. |
七大方向——子方向分类 | 生物特征识别 |
国重实验室规划方向分类 | 视觉信息处理 |
是否有论文关联数据集需要存交 | 否 |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/56728 |
专题 | 多模态人工智能系统全国重点实验室 |
通讯作者 | Lei Z(雷震) |
作者单位 | 1.中国科学院自动化所 2.中国科学院大学 |
推荐引用方式 GB/T 7714 | Yu C,Zhu XY,Lei Z,et al. Out-of-Distribution Detection for Reliable Face Recognition[J]. IEEE Signal Processing Letters,2020:710-714. |
APA | Yu C,Zhu XY,Lei Z,&Li ZQ.(2020).Out-of-Distribution Detection for Reliable Face Recognition.IEEE Signal Processing Letters,710-714. |
MLA | Yu C,et al."Out-of-Distribution Detection for Reliable Face Recognition".IEEE Signal Processing Letters (2020):710-714. |
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 | ||
spl20out.pdf(1434KB) | 期刊论文 | 作者接受稿 | 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