Multi-Prototype Networks for Unconstrained Set-based Face Recognition
arXiv:1902.04755
Abstract
In this paper, we study the challenging unconstrained set-based face recognition problem where each subject face is instantiated by a set of media (images and videos) instead of a single image. Naively aggregating information from all the media within a set would suffer from the large intra-set variance caused by heterogeneous factors (e.g., varying media modalities, poses and illuminations) and fail to learn discriminative face representations. A novel Multi-Prototype Network (MPNet) model is thus proposed to learn multiple prototype face representations adaptively from the media sets. Each learned prototype is representative for the subject face under certain condition in terms of pose, illumination and media modality. Instead of handcrafting the set partition for prototype learning, MPNet introduces a Dense SubGraph (DSG) learning sub-net that implicitly untangles inconsistent media and learns a number of representative prototypes. Qualitative and quantitative experiments clearly demonstrate superiority of the proposed model over state-of-the-arts.
References in corpus (8)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Deep Learning Face Representation by Joint Identification-Verification
- DeepID3: Face Recognition with Very Deep Neural Networks
- Multicolumn Networks for Face Recognition
- Face Search at Scale: 80 Million Gallery
- Do We Really Need to Collect Millions of Faces for Effective Face Recognition?
- Sample-to-Sample Correspondence for Unsupervised Domain Adaptation
- An All-In-One Convolutional Neural Network for Face Analysis