Multiple Contexts and Frequencies Aggregation Network forDeepfake Detection

TL;DR

This paper introduces MkfaNet, a novel deepfake detection network that leverages spatial and frequency domain priors through specialized aggregators, achieving superior accuracy and efficiency across multiple benchmarks.

Contribution

The paper proposes MkfaNet, a new backbone architecture with multi-kernel and multi-frequency aggregators for improved deepfake detection.

Findings

Achieves state-of-the-art performance on seven benchmarks.

Effective in both within-domain and cross-domain evaluations.

Demonstrates high efficiency with fewer parameters.

Abstract

Deepfake detection faces increasing challenges since the fast growth of generative models in developing massive and diverse Deepfake technologies. Recent advances rely on introducing heuristic features from spatial or frequency domains rather than modeling general forgery features within backbones. To address this issue, we turn to the backbone design with two intuitive priors from spatial and frequency detectors, \textit{i.e.,} learning robust spatial attributes and frequency distributions that are discriminative for real and fake samples. To this end, we propose an efficient network for face forgery detection named MkfaNet, which consists of two core modules. For spatial contexts, we design a Multi-Kernel Aggregator that adaptively selects organ features extracted by multiple convolutions for modeling subtle facial differences between real and fake faces. For the frequency components, we propose a Multi-Frequency Aggregator to process different bands of frequency components by adaptively reweighing high-frequency and low-frequency features. Comprehensive experiments on seven popular deepfake detection benchmarks demonstrate that our proposed MkfaNet variants achieve superior performances in both within-domain and across-domain evaluations with impressive efficiency of parameter usage.