TrueMoE: Dual-Routing Mixture of Discriminative Experts for Synthetic Image Detection
This addresses the challenge of detecting synthetic images for security and verification applications, representing a novel method rather than an incremental improvement.
The paper tackles the problem of synthetic image detection by proposing TrueMoE, a dual-routing Mixture-of-Discriminative-Experts framework that uses multiple specialized discriminative subspaces, achieving superior generalization and robustness across various generative models.
The rapid progress of generative models has made synthetic image detection an increasingly critical task. Most existing approaches attempt to construct a single, universal discriminative space to separate real from fake content. However, such unified spaces tend to be complex and brittle, often struggling to generalize to unseen generative patterns. In this work, we propose TrueMoE, a novel dual-routing Mixture-of-Discriminative-Experts framework that reformulates the detection task as a collaborative inference across multiple specialized and lightweight discriminative subspaces. At the core of TrueMoE is a Discriminative Expert Array (DEA) organized along complementary axes of manifold structure and perceptual granularity, enabling diverse forgery cues to be captured across subspaces. A dual-routing mechanism, comprising a granularity-aware sparse router and a manifold-aware dense router, adaptively assigns input images to the most relevant experts. Extensive experiments across a wide spectrum of generative models demonstrate that TrueMoE achieves superior generalization and robustness.