Deep Learning for Computer Vision

FaceNet

The FaceNet model proposed by Schroff et al. (https://arxiv.org/pdf/1503.03832.pdf) solves the face verification problem. It learns one deep CNN, then transforms a face image to an embedding. The embedding can be used to compare faces to see how similar they are and can be used in the following three ways:

• Face verification considers two faces and it is decides whether they are similar or not. Face verification can be done by computing the distance metric.
• Face recognition is a classification problem for labelling a face with a name. The embedding vector can be used for training the final labels.
• Face Clustering groups similar faces together like how photo applications cluster photos of the same person together. A clustering algorithm ...