A visualization method for data domain changes in CNN networks and the optimization method for selecting thresholds in classification tasks

TL;DR

This paper introduces a visualization method for understanding CNN data domain changes and an optimization approach for threshold selection in face anti-spoofing, improving cross-domain detection and deployment performance.

Contribution

It presents a novel visualization technique for CNN training outcomes and a threshold optimization method based on data distribution, addressing cross-domain FAS challenges.

Findings

Visualization effectively reflects model training results.

Data augmentation improves cross-domain FAS performance.

Threshold setting based on data distribution enhances deployment accuracy.

Abstract

In recent years, Face Anti-Spoofing (FAS) has played a crucial role in preserving the security of face recognition technology. With the rise of counterfeit face generation techniques, the challenge posed by digitally edited faces to face anti-spoofing is escalating. Existing FAS technologies primarily focus on intercepting physically forged faces and lack a robust solution for cross-domain FAS challenges. Moreover, determining an appropriate threshold to achieve optimal deployment results remains an issue for intra-domain FAS. To address these issues, we propose a visualization method that intuitively reflects the training outcomes of models by visualizing the prediction results on datasets. Additionally, we demonstrate that employing data augmentation techniques, such as downsampling and Gaussian blur, can effectively enhance performance on cross-domain tasks. Building upon our data visualization approach, we also introduce a methodology for setting threshold values based on the distribution of the training dataset. Ultimately, our methods secured us second place in both the Unified Physical-Digital Face Attack Detection competition and the Snapshot Spectral Imaging Face Anti-spoofing contest. The training code is available at https://github.com/SeaRecluse/CVPRW2024.