{"ID":2843508,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.08423","arxiv_id":"2511.08423","title":"OmniAID: Decoupling Semantic and Artifacts for Universal AI-Generated Image Detection in the Wild","abstract":"A truly universal AI-Generated Image (AIGI) detector must simultaneously generalize across diverse generative models and varied semantic content. Current methods learn a single, entangled forgery representation, conflating content-dependent flaws with content-agnostic artifacts, and are further constrained by outdated benchmarks. We propose OmniAID, a novel framework centered on a decoupled Mixture-of-Experts (MoE) architecture that separates: (1) semantic flaws across distinct content domains via Routable Specialized Semantic Experts, and (2) content-agnostic universal artifacts from content-dependent flaws via a Fixed Universal Artifact Expert. A two-stage training strategy first specializes experts independently with domain-specific hard-sampling, then trains a lightweight gating network for effective input routing. By explicitly decoupling \"what is generated\" (content-specific flaws) from \"how it is generated\" (universal artifacts), OmniAID achieves robust generalization. We also introduce Mirage, a large-scale, contemporary dataset comprising a modern training set and a challenging test set. Extensive experiments demonstrate that OmniAID surpasses existing detectors, establishing a new standard for AIGI detection against modern, in-the-wild threats. Code is available at https://github.com/yunncheng/OmniAID.","short_abstract":"A truly universal AI-Generated Image (AIGI) detector must simultaneously generalize across diverse generative models and varied semantic content. Current methods learn a single, entangled forgery representation, conflating content-dependent flaws with content-agnostic artifacts, and are further constrained by outdated...","url_abs":"https://arxiv.org/abs/2511.08423","url_pdf":"https://arxiv.org/pdf/2511.08423v3","authors":"[\"Yuncheng Guo\",\"Junyan Ye\",\"Chenjue Zhang\",\"Hengrui Kang\",\"Haohuan Fu\",\"Conghui He\",\"Weijia Li\"]","published":"2025-11-11T16:33:49Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false,"code_links":[{"ID":607223,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2843508,"paper_url":"https://arxiv.org/abs/2511.08423","paper_title":"OmniAID: Decoupling Semantic and Artifacts for Universal AI-Generated Image Detection in the Wild","repo_url":"https://github.com/yunncheng/OmniAID","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}