Frequency-Aware Semantic Fusion with Gated Injection for AI-generated Image Detection

TL;DR

This paper introduces FGINet, a novel method combining frequency-aware encoding and gated injection to enhance the generalization of AI-generated image detection models across unseen generators.

Contribution

It proposes a Frequency-aware Gated Injection Network with a band-masked frequency encoder and hierarchical gated frequency injection to improve detection generalization.

Findings

FGINet achieves state-of-the-art performance on multiple datasets.

The band-masked frequency encoder reduces reliance on generator-specific cues.

Hierarchical gated injection aligns frequency cues with model hierarchy.

Abstract

AI-generated images are becoming increasingly realistic and diverse, posing significant challenges for generalizable detection. While Vision Foundation Models (VFMs) provide rich semantic representations and frequency-based methods capture complementary artifact cues, existing approaches that combine these modalities still suffer from limited generalization, with notable performance degradation on unseen generative models. We attribute this limitation to two key factors: frequency shortcut bias toward easily distinguishable cues associated with specific generators and cross-domain representation conflict between high-level semantics and low-level frequency patterns. To address these issues, we propose a Frequency-aware Gated Injection Network (FGINet) to improve generalization. Specifically, we design a Band-Masked Frequency Encoder (BMFE) that applies cross-band masking in the frequency domain to reduce reliance on generator-specific patterns and encourage more diverse and generalizable representations. We further introduce a Layer-wise Gated Frequency Injection (LGFI) mechanism to progressively inject frequency cues into the VFM backbone with adaptive gating, aligning with its hierarchical abstraction and alleviating representation conflict. Moreover, we propose a Hyperspherical Compactness Learning (HCL) framework with a cosine margin objective to learn compact and well-separated representations. Extensive experiments demonstrate that FGINet achieves state-of-the-art performance and strong generalization across multiple challenging datasets.