Over the last 5 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 Labeled Faces in the Wild (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 LFW and Youtube Face 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. Some open issues regarding DCNNs for face verification problems are then discussed.

中文翻译：

---

使用深度卷积神经网络进行无约束静止/基于视频的人脸验证

在过去的 5 年中，基于深度卷积神经网络 (DCNN) 的方法在对象检测和识别问题上显示出令人印象深刻的性能改进。由于大型注释数据集的可用性、对输入图像和类标签之间的非线性映射的更好理解以及 GPU 的可承受性，这使得这成为可能。在本文中，我们介绍了用于无约束人脸识别的深度学习系统的设计细节，包括用于人脸检测、关联、对齐和人脸验证的模块。使用 IARPA Janus Benchmark A (IJB-A)、JANUS Challenge Set 2 (JANUS CS2) 和 Labeled Faces in the Wild (LFW) 数据集进行定量性能评估。IJB-A 数据集包括 500 个具有显着姿势和光照变化的真实世界无约束人脸，这比 LFW 和 Youtube 人脸数据集要困难得多。JANUS CS2 是 IJB-A 的扩展版本，它不仅包含 IJB-A 的所有图像/帧，还包括原始视频。然后讨论了一些关于 DCNN 用于人脸验证问题的开放性问题。