PocketNet

Introduced by Boutros et al. in PocketNet: Extreme Lightweight Face Recognition Network using Neural Architecture Search and Multi-Step Knowledge Distillation

PocketNet is a face recognition model family discovered through neural architecture search. The training is based on multi-step knowledge distillation.

Source: PocketNet: Extreme Lightweight Face Recognition Network using Neural Architecture Search and Multi-Step Knowledge Distillation

Read Paper See Code

Papers

Paper	Code	Results	Date	Stars

Tasks

Task	Papers	Share
Face Recognition	1	50.00%
Lightweight Face Recognition	1	50.00%

Usage Over Time

This feature is experimental; we are continuously improving our matching algorithm.

Components

Component	Type	Add Remove
Batch Normalization	Normalization
Convolution	Convolutions
Depthwise Convolution	Convolutions
Depthwise Separable Convolution	Convolutions
PReLU	Activation Functions

Categories

Add Remove

Convolutional Neural Networks

Face Recognition Models