TrueMoE: Dual-Routing Mixture of Discriminative Experts for Synthetic Image Detection

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.

Key Contributions

• Reformulates synthetic image detection as a multi-view subspace classification problem via a Mixture-of-Discriminative-Experts (MoE) framework rather than a single unified decision space.
• Introduces the Discriminative Expert Array (DEA) organized along two independent axes — manifold structure and perceptual granularity — to capture complementary forgery cues.
• Designs a dual-routing mechanism (sparse Granularity Routing Module + dense Hybrid Manifold Routing Module) that adaptively assigns inputs to the most relevant expert subspaces.

🛡️ Threat Analysis

Details

Similar Papers