4.8 Article

End2End Occluded Face Recognition by Masking Corrupted Features

出版社

IEEE COMPUTER SOC
DOI: 10.1109/TPAMI.2021.3098962

关键词

Face recognition; Training; Decoding; Feature extraction; Mouth; Image restoration; Detectors; Occluded face recognition; feature mask; dynamically; end-to-end; deep convolutional neural network

向作者/读者索取更多资源

This article introduces a novel face recognition method called FROM that is robust to occlusions. By learning how to detect and clean corrupted features, FROM effectively addresses the limited generalization ability of general face recognition models under occlusions. Experimental results demonstrate that FROM performs well on multiple datasets.
With the recent advancement of deep convolutional neural networks, significant progress has been made in general face recognition. However, the state-of-the-art general face recognition models do not generalize well to occluded face images, which are exactly the common cases in real-world scenarios. The potential reasons are the absences of large-scale occluded face data for training and specific designs for tackling corrupted features brought by occlusions. This article presents a novel face recognition method that is robust to occlusions based on a single end-to-end deep neural network. Our approach, named FROM (Face Recognition with Occlusion Masks), learns to discover the corrupted features from the deep convolutional neural networks, and clean them by the dynamically learned masks. In addition, we construct massive occluded face images to train FROM effectively and efficiently. FROM is simple yet powerful compared to the existing methods that either rely on external detectors to discover the occlusions or employ shallow models which are less discriminative. Experimental results on the LFW, Megaface challenge 1, RMF2, AR dataset and other simulated occluded/masked datasets confirm that FROM dramatically improves the accuracy under occlusions, and generalizes well on general face recognition.

作者

我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

4.8
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

暂无数据
暂无数据