Paper on arxiv: arxiv
| Model | Pretrained model |
|---|---|
| ResNet100 | pretrained-mode |
| ResNet100 W8A8 (Real data) | pretrained-mode |
| ResNet100 W8A8 (Synthetic data) | pretrained-mode |
| ResNet100 W6A6 (Real data) | pretrained-mode |
| ResNet100 W6A6 (Synthetic data) | pretrained-mode |
| ResNet50 | pretrained-mode |
| ResNet50 W8A8 (Real data) | pretrained-mode |
| ResNet50 W8A8 (Synthetic data) | pretrained-mode |
| ResNet50 W6A6 (Real data) | pretrained-mode |
| ResNet50 W6A6 (Synthetic data) | pretrained-mode |
| ResNet18 | pretrained-mode |
| ResNet18 W8A8 (Real data) | pretrained-mode |
| ResNet18 W8A8 (Synthetic data) | pretrained-mode |
| ResNet18 W6A6 (Real data) | pretrained-mode |
| ResNet18 W6A6 (Synthetic data) | pretrained-mode |
| MobileFaceNet | pretrained-mode |
| MobileFaceNet W8A8 (Real data) | pretrained-mode |
| MobileFaceNet W8A8 (Synthetic data) | pretrained-mode |
| MobileFaceNet W6A6 (Real data) | pretrained-mode |
| MobileFaceNet W6A6 (Synthetic data) | pretrained-mode |
If you use any of the code provided in this repository, please cite the following paper:
@inproceedings{quantface_boutros,
title = {QuantFace: Towards Lightweight Face Recognition by Synthetic Data Low-bit Quantization},
author = {Fadi Boutros and Naser Damer and Arjan Kuijper},
year = 2022,
booktitle = {26th International Conference on Pattern Recognition, {ICPR} 2022,
Montreal,Quebec ,August 21-25, 2021},
publisher = {{IEEE}},
year = {2022},
}
The dataset, the implementation, or trained models, use is restricted to research purpuses. The use of the dataset or the implementation/trained models for product development.
This project is licensed under the terms of the Attribution-NonCommercial-ShareAlike 4.0
International (CC BY-NC-SA 4.0) license.
Copyright (c) 2021 Fraunhofer Institute for Computer Graphics Research IGD Darmstadt