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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Cui, Jialei, Du, Jianwei, Li, Yanzhe, Gao, Lei, Jiang, Hui, Bao, Chenfu
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913962471194624
author Cui, Jialei
Du, Jianwei
Li, Yanzhe
Gao, Lei
Jiang, Hui
Bao, Chenfu
author_facet Cui, Jialei
Du, Jianwei
Li, Yanzhe
Gao, Lei
Jiang, Hui
Bao, Chenfu
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2507_20913
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle HAMLET-FFD: Hierarchical Adaptive Multi-modal Learning Embeddings Transformation for Face Forgery Detection
Cui, Jialei
Du, Jianwei
Li, Yanzhe
Gao, Lei
Jiang, Hui
Bao, Chenfu
Computer Vision and Pattern Recognition
Artificial Intelligence
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.
title HAMLET-FFD: Hierarchical Adaptive Multi-modal Learning Embeddings Transformation for Face Forgery Detection
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2507.20913