Latent Spatiotemporal Adaptation for Generalized Face Forgery Video Detection

TL;DR

This paper introduces LAST, a novel method that models and adapts to the spatiotemporal patterns of face forgery videos in latent space, significantly improving generalization to unseen forgery methods.

Contribution

The paper proposes a latent spatiotemporal adaptation approach that enhances face forgery detection generalization by modeling patterns in latent space and using semi-supervised learning.

Findings

Achieves state-of-the-art results on public datasets.

Demonstrates strong generalization to unseen forgery methods.

Pre-training with self-supervised tasks improves robustness.

Abstract

Face forgery videos have caused severe public concerns, and many detectors have been proposed. However, most of these detectors suffer from limited generalization when detecting videos from unknown distributions, such as from unseen forgery methods. In this paper, we find that different forgery videos have distinct spatiotemporal patterns, which may be the key to generalization. To leverage this finding, we propose a Latent Spatiotemporal Adaptation~(LAST) approach to facilitate generalized face forgery video detection. The key idea is to optimize the detector adaptive to the spatiotemporal patterns of unknown videos in latent space to improve the generalization. Specifically, we first model the spatiotemporal patterns of face videos by incorporating a lightweight CNN to extract local spatial features of each frame and then cascading a vision transformer to learn the long-term spatiotemporal representations in latent space, which should contain more clues than in pixel space. Then by optimizing a transferable linear head to perform the usual forgery detection task on known videos and recover the spatiotemporal clues of unknown target videos in a semi-supervised manner, our detector could flexibly adapt to unknown videos' spatiotemporal patterns, leading to improved generalization. Additionally, to eliminate the influence of specific forgery videos, we pre-train our CNN and transformer only on real videos with two simple yet effective self-supervised tasks: reconstruction and contrastive learning in latent space and keep them frozen during fine-tuning. Extensive experiments on public datasets demonstrate that our approach achieves state-of-the-art performance against other competitors with impressive generalization and robustness.