PocketNet

This is the official repository of the paper:

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

Paper on arxiv: arxiv

Face recognition model training

Download MS1MV2 dataset from insightface on strictly follow the licence distribution

Extract the dataset and place it in the data folder

Rename the config/config_xxxxxx.py to config/config.py

1. Train PocketNet with ArcFace loss
   • ./train.sh
2. Train PocketNet with template knowledge distillation
   • ./train_kd.sh
3. Train PocketNet with multi-step template knowledge distillation
   • ./train_kd.sh

Differentiable architecture search training

To-do

• Add pretrained model
• Training configuration
• Add NAS code
• Add evaluation results
• Add requirements

If you use any of the provided code in this repository, please cite the following paper:

@misc{boutros2021pocketnet,
      title={PocketNet: Extreme Lightweight Face Recognition Network using Neural Architecture Search and Multi-Step Knowledge Distillation}, 
      author={Fadi Boutros and Patrick Siebke and Marcel Klemt and Naser Damer and Florian Kirchbuchner and Arjan Kuijper},
      year={2021},
      eprint={2108.10710},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}