Provided is code that demonstrates the training and evaluation of the work presented in the paper: "Noise Modeling, Synthesis, and Classification for Generic Object Anti-Spoofing" published in CVPR 2020.
See the MSU CVLab website for project details and access to the GOSet dataset.
http://cvlab.msu.edu/project-goas.html
This code is provided as example code, and may not reflect a specific combination of hyper-parameters presented in the paper.
prepare_dats.py
: Processes the dataset into binary files for network trainingdatabase.py
: Reads prepared .dat files during network trainingnetworks.py
: Defines the structure and operations of the networksgolab_train.py
: Trains the GOLab networkgolab_freeze.py
: Optimizes and freezes the GOLab model for evaluationgolab_eval.py
: Evaluates the frozen GOLab modelgolab_perf.m
: Compute evaluation metrics for GOLabgogen_train.py
: Trains the GOGen networkgogen_freeze.py
: Optimizes and freezes the GOGen model for evaluationgogen_eval.py
: Evaluates the frozen GOGen modelgogen_perf.m
: Compute evaluation metrics for GOGen
If you use or refer to this source code, please cite the following paper:
@inproceedings{cvpr2020-stehouwer,
title={Noise Modeling, Synthesis, and Classification for Generic Object Anti-Spoofing},
author={Joel Stehouwer, Amin Jourabloo, Yaojie Liu, Xiaoming Liu},
booktitle={In Proceeding of IEEE Computer Vision and Pattern Recognition (CVPR 2020)},
address={Seattle, WA},
year={2020}
}