FaceNet is a

facial recognition system A facial recognition system is a technology capable of matching a human face from a digital image or a video frame against a database of faces. Such a system is typically employed to authenticate users through ID verification services, and wor ...

developed by Florian Schroff, Dmitry Kalenichenko and James Philbina, a group of researchers affiliated with

Google Google LLC () is an American Multinational corporation, multinational technology company focusing on Search Engine, search engine technology, online advertising, cloud computing, software, computer software, quantum computing, e-commerce, ar ...

. The system was first presented at the 2015

IEEE The Institute of Electrical and Electronics Engineers (IEEE) is a 501(c)(3) professional association for electronic engineering and electrical engineering (and associated disciplines) with its corporate office in New York City and its operati ...

Conference on Computer Vision and Pattern Recognition. The system uses a deep convolutional neural network to learn a

mapping Mapping may refer to: * Mapping (cartography), the process of making a map * Mapping (mathematics), a synonym for a mathematical function and its generalizations ** Mapping (logic), a synonym for functional predicate Types of mapping * Animated m ...

(also called an

embedding In mathematics, an embedding (or imbedding) is one instance of some mathematical structure contained within another instance, such as a group that is a subgroup. When some object X is said to be embedded in another object Y, the embedding is giv ...

) from a set of face images to a 128-dimensional

Euclidean space Euclidean space is the fundamental space of geometry, intended to represent physical space. Originally, that is, in Euclid's ''Elements'', it was the three-dimensional space of Euclidean geometry, but in modern mathematics there are Euclidean sp ...

, and assesses the

similarity Similarity may refer to: In mathematics and computing * Similarity (geometry), the property of sharing the same shape * Matrix similarity, a relation between matrices * Similarity measure, a function that quantifies the similarity of two objects * ...

between faces based on the square of the Euclidean distance between the images' corresponding normalized vectors in the 128-dimensional Euclidean space. The system uses the

triplet loss Triplet loss is a loss function for machine learning algorithms where a reference input (called anchor) is compared to a matching input (called positive) and a non-matching input (called negative). The distance from the anchor to the positive is mi ...

function as its cost function and introduced a new online triplet mining method. The system achieved an accuracy of 99.63%, which is the highest score to date on the Labeled Faces in the Wild dataset using the ''unrestricted with labeled outside data'' protocol.

Structure

Basic structure

The structure of FaceNet is represented schematically in Figure 1. Structure_of_FaceNet_System

For training, researchers used input batches of about 1800 images. For each identity represented in the input batches, there were 40 similar images of that identity and several randomly selected images of other identities. These batches were fed to a deep convolutional neural network, which was trained using

stochastic gradient descent Stochastic gradient descent (often abbreviated SGD) is an iterative method for optimizing an objective function with suitable smoothness properties (e.g. differentiable or subdifferentiable). It can be regarded as a stochastic approximation of ...

with standard

backpropagation In machine learning, backpropagation (backprop, BP) is a widely used algorithm for training feedforward artificial neural networks. Generalizations of backpropagation exist for other artificial neural networks (ANNs), and for functions gener ...

and the Adaptive Gradient Optimizer (AdaGrad) algorithm. The

learning rate In machine learning and statistics, the learning rate is a Hyperparameter (machine learning), tuning parameter in an Mathematical optimization, optimization algorithm that determines the step size at each iteration while moving toward a minimum of ...

was initially set at 0.05, which was later lowered while finalizing the model.

Structure of the CNN

The researchers used two types of architectures, which they called NN1 and NN2, and explored their trade-offs. The practical differences between the models lie in the difference of parameters and FLOPS. The details of the NN1 model are presented in the table below.

Triplet loss

A key innovation of the system was the triplet loss function and its associated mining method. This function was has since become central in a variety of other

one-shot learning One-shot learning is an object categorization problem, found mostly in computer vision. Whereas most machine learning-based object categorization algorithms require training on hundreds or thousands of examples, one-shot learning aims to classify ...

problems.

Performance

On the widely used Labeled Faces in the Wild (LFW) dataset, the FaceNet system achieved an accuracy of 99.63% which is the highest score on LFW in the unrestricted with labeled outside data protocol. On YouTube Faces DB the system achieved an accuracy of 95.12%.

References

{{reflist Facial recognition software Image search Deep learning software applications Artificial neural networks