Multi-Domain Incremental Learning for Face Presentation Attack Detection

Authors: Keyao Wang, Guosheng Zhang, Haixiao Yue, Ajian Liu, Gang Zhang, Haocheng Feng, Junyu Han, Errui Ding, Jingdong Wang

AAAI 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments show that our proposed method achieves state-of-the-art performance compared to prior methods of incremental learning. Excitingly, under more stringent setting conditions, our method approximates or even outperforms DA/DG-based methods.
Researcher Affiliation Collaboration Keyao Wang*1, Guosheng Zhang*1, Haixiao Yue*1, Ajian Liu 2, Gang Zhang1, Haocheng Feng1, Junyu Han1, Errui Ding1, Jingdong Wang1 1Department of Computer Vision Technology (VIS), Baidu Inc 2CBSR&MAIS, Institute of Automation, Chinese Academy of Sciences (CASIA)
Pseudocode Yes Algorithm 1: The Procedure of MDIL-PAD.
Open Source Code No The paper does not provide any explicit statement about releasing source code or a link to a code repository.
Open Datasets Yes We evaluate the effectiveness of our method on five PAD datasets: OULU-NPU (Boulkenafet et al. 2017) (O for short), CASIA-MFSD (Zhang et al. 2012) (C for short), Idiap Replay Attack (Chingovska, Anjos, and Marcel 2012) (I for short), MSU-MFSD (Wen, Han, and Jain 2015) (M for short), and Si W (Liu, Jourabloo, and Liu 2018) (S for short).
Dataset Splits No The paper describes training and testing on different datasets in an incremental manner, but it does not specify explicit train/validation/test dataset splits with percentages, sample counts, or cross-validation details for reproduction of the data partitioning.
Hardware Specification No The paper describes implementation details but does not provide specific hardware information such as CPU or GPU models, or memory specifications used for running the experiments.
Software Dependencies No The paper mentions using a 'Stochastic Gradient Descent (SGD) optimizer' and a 'Vi T-B/16' network, but it does not specify version numbers for any software dependencies like programming languages, libraries, or frameworks (e.g., Python, PyTorch, TensorFlow versions).
Experiment Setup Yes We train our method using the Stochastic Gradient Descent (SGD) optimizer with a momentum of 0.9, an initial learning rate of 0.01, and a batch size of 48. Input images are resized to 224 224.