Deep learning and face recognition: the state of the art
It addresses the need for more challenging datasets to advance face recognition research, which is incremental as it summarizes existing work and proposes a new benchmark.
This paper reviews deep learning techniques for face recognition, noting that current benchmarks like LFW may be insufficient due to high accuracy levels (e.g., 99.63% for FaceNet) and the use of massive external datasets.
Deep Neural Networks (DNNs) have established themselves as a dominant technique in machine learning. DNNs have been top performers on a wide variety of tasks including image classification, speech recognition, and face recognition. Convolutional neural networks (CNNs) have been used in nearly all of the top performing methods on the Labeled Faces in the Wild (LFW) dataset. In this talk and accompanying paper, I attempt to provide a review and summary of the deep learning techniques used in the state-of-the-art. In addition, I highlight the need for both larger and more challenging public datasets to benchmark these systems. The high accuracy (99.63% for FaceNet at the time of publishing) and utilization of outside data (hundreds of millions of images in the case of Google's FaceNet) suggest that current face verification benchmarks such as LFW may not be challenging enough, nor provide enough data, for current techniques. There exist a variety of organizations with mobile photo sharing applications that would be capable of releasing a very large scale and highly diverse dataset of facial images captured on mobile devices. Such an "ImageNet for Face Recognition" would likely receive a warm welcome from researchers and practitioners alike.