HAMLET-FFD: Hierarchical Adaptive Multi-modal Learning Embeddings Transformation for Face Forgery Detection

TL;DR

HAMLET-FFD is a hierarchical, multi-modal framework inspired by cognition that improves face forgery detection by integrating visual and textual cues through a bidirectional fusion mechanism, enhancing cross-domain generalization.

Contribution

It introduces a novel hierarchical multi-modal learning approach with a knowledge refinement loop and bidirectional fusion, leveraging CLIP without fine-tuning for improved forgery detection.

Findings

Outperforms existing methods on unseen manipulations

Enhances cross-domain generalization in face forgery detection

Reveals specialized embeddings for artifact recognition

Abstract

The rapid evolution of face manipulation techniques poses a critical challenge for face forgery detection: cross-domain generalization. Conventional methods, which rely on simple classification objectives, often fail to learn domain-invariant representations. We propose HAMLET-FFD, a cognitively inspired Hierarchical Adaptive Multi-modal Learning framework that tackles this challenge via bidirectional cross-modal reasoning. Building on contrastive vision-language models such as CLIP, HAMLET-FFD introduces a knowledge refinement loop that iteratively assesses authenticity by integrating visual evidence with conceptual cues, emulating expert forensic analysis. A key innovation is a bidirectional fusion mechanism in which textual authenticity embeddings guide the aggregation of hierarchical visual features, while modulated visual features refine text embeddings to generate image-adaptive prompts. This closed-loop process progressively aligns visual observations with semantic priors to enhance authenticity assessment. By design, HAMLET-FFD freezes all pretrained parameters, serving as an external plugin that preserves CLIP's original capabilities. Extensive experiments demonstrate its superior generalization to unseen manipulations across multiple benchmarks, and visual analyses reveal a division of labor among embeddings, with distinct representations specializing in fine-grained artifact recognition.