Face Recognition Using Deep Multi-Pose Representations
This addresses pose sensitivity in face recognition systems, which is a practical problem for security and identification applications, though it appears incremental as it builds on existing deep learning and 3D rendering techniques.
The paper tackles face recognition under pose variations by processing face images through multiple pose-specific deep CNN models, achieving state-of-the-art results on IARPA's CS2 and NIST's IJB-A datasets for verification and identification tasks.
We introduce our method and system for face recognition using multiple pose-aware deep learning models. In our representation, a face image is processed by several pose-specific deep convolutional neural network (CNN) models to generate multiple pose-specific features. 3D rendering is used to generate multiple face poses from the input image. Sensitivity of the recognition system to pose variations is reduced since we use an ensemble of pose-specific CNN features. The paper presents extensive experimental results on the effect of landmark detection, CNN layer selection and pose model selection on the performance of the recognition pipeline. Our novel representation achieves better results than the state-of-the-art on IARPA's CS2 and NIST's IJB-A in both verification and identification (i.e. search) tasks.