Multi-Task Convolutional Neural Network for Pose-Invariant Face Recognition
From MaRDI portal
Publication:4617072
DOI10.1109/TIP.2017.2765830zbMATH Open1409.94718arXiv1702.04710OpenAlexW3098883884WikidataQ88662820 ScholiaQ88662820MaRDI QIDQ4617072FDOQ4617072
Authors: Xi Yin, Xiaoming Liu 
Publication date: 6 February 2019
Published in: IEEE Transactions on Image Processing (Search for Journal in Brave)
Abstract: This paper explores multi-task learning (MTL) for face recognition. We answer the questions of how and why MTL can improve the face recognition performance. First, we propose a multi-task Convolutional Neural Network (CNN) for face recognition where identity classification is the main task and pose, illumination, and expression estimations are the side tasks. Second, we develop a dynamic-weighting scheme to automatically assign the loss weight to each side task, which is a crucial problem in MTL. Third, we propose a pose-directed multi-task CNN by grouping different poses to learn pose-specific identity features, simultaneously across all poses. Last but not least, we propose an energy-based weight analysis method to explore how CNN-based MTL works. We observe that the side tasks serve as regularizations to disentangle the variations from the learnt identity features. Extensive experiments on the entire Multi-PIE dataset demonstrate the effectiveness of the proposed approach. To the best of our knowledge, this is the first work using all data in Multi-PIE for face recognition. Our approach is also applicable to in-the-wild datasets for pose-invariant face recognition and achieves comparable or better performance than state of the art on LFW, CFP, and IJB-A datasets.
Full work available at URL: https://arxiv.org/abs/1702.04710
Image processing (compression, reconstruction, etc.) in information and communication theory (94A08)
Cited In (1)
This page was built for publication: Multi-Task Convolutional Neural Network for Pose-Invariant Face Recognition
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4617072)
