Unconstrained Still/Video-Based Face Verification with Deep Convolutional Neural Networks

TL;DR

This paper details a deep learning system for unconstrained face verification, covering detection, alignment, and verification, with extensive evaluation on challenging real-world datasets demonstrating its effectiveness.

Contribution

It introduces a comprehensive deep learning framework for face recognition in unconstrained environments, including novel modules and extensive evaluation on challenging datasets.

Findings

High accuracy on IJB-A and JANUS CS2 datasets

Effective handling of pose and illumination variations

Discussion of open issues in DCNN-based face verification

Abstract

Over the last five years, methods based on Deep Convolutional Neural Networks (DCNNs) have shown impressive performance improvements for object detection and recognition problems. This has been made possible due to the availability of large annotated datasets, a better understanding of the non-linear mapping between input images and class labels as well as the affordability of GPUs. In this paper, we present the design details of a deep learning system for unconstrained face recognition, including modules for face detection, association, alignment and face verification. The quantitative performance evaluation is conducted using the IARPA Janus Benchmark A (IJB-A), the JANUS Challenge Set 2 (JANUS CS2), and the LFW dataset. The IJB-A dataset includes real-world unconstrained faces of 500 subjects with significant pose and illumination variations which are much harder than the Labeled Faces in the Wild (LFW) and Youtube Face (YTF) datasets. JANUS CS2 is the extended version of IJB-A which contains not only all the images/frames of IJB-A but also includes the original videos for evaluating the video-based face verification system. Some open issues regarding DCNNs for face verification problems are then discussed.