Learn More
In modern face recognition, the conventional pipeline consists of four stages: detect ⇒ align ⇒ represent ⇒ classify. We revisit both the alignment step and the representation step by employing explicit 3D face modeling in order to apply a piecewise affine transformation, and derive a face representation from a nine-layer deep neural network. This deep(More)
Recognizing people we know from unusual poses is easy for us. However, in the absence of a clear, high-resolution frontal face, we rely on a variety of subtle cues from other body parts, such as hair style, clothes, glasses, pose and other context. While a lot of progress has been made recently in recognition from a frontal face, non-frontal views are a lot(More)
Computer vision systems have demonstrated considerable improvement in recognizing and verifying faces in digital images. Still, recognizing faces appearing in unconstrained, natural conditions remains a challenging task. In this paper, we present a face-image, pair-matching approach primarily developed and tested on the "Labeled Faces in the Wild" (LFW)(More)
The One-Shot similarity measure has recently been introduced in the context of face recognition where it was used to produce state-of-the-art results. Given two vectors, their One-Shot similarity score reflects the likelihood of each vector belonging in the same class as the other vector and not in a class defined by a fixed set of " negative " examples.(More)
Convolutional neural networks [3] have proven useful in many domains, including computer vision [1, 4, 5], audio processing [6, 7] and natural language processing [8]. These powerful models come at great cost in training time, however. Currently, long training periods make experimentation difficult and time consuming. In this work, we consider a standard(More)
The One-Shot Similarity (OSS) kernel [3, 4] has recently been introduced as a means of boosting the performance of face recognition systems. Given two vectors, their One-Shot Similarity score (Fig. 1) reflects the likelihood of each vector belonging to the same class as the other vector and not in a class defined by a fixed set of " negative " examples. In(More)
(a) (b) Figure 1: (a) The bottleneck. The representation layer splits the network between the part that converts the input into a generic face descriptor and the part that performs linear classification to specific K classes. (b) The boot-strapping method. An initial 256D-compressed representation trained on DB 1 is used to find the semantically-nearest(More)
We employ the face recognition technology developed in house at face.com to a well accepted benchmark and show that without any tuning we are able to considerably surpass state of the art results. Much of the improvement is concentrated in the high-valued performance point of zero false positive matches, where the obtained recall rate almost doubles the(More)