Semantic Visual Anomaly Detection and Reasoning in AI-Generated Images

ICLR 2026 Conference Submission5834 Authors

Keywords: Anomaly Detection，AI-Generated Images

Abstract: The rapid advancement of AI-generated content (AIGC) has enabled the synthesis of visually convincing images; however, many such outputs exhibit subtle \textbf{semantic anomalies}, including unrealistic object configurations, violations of physical laws, or commonsense inconsistencies, which compromise the overall plausibility of the generated scenes. Detecting these semantic-level anomalies is essential for assessing the trustworthiness of AIGC media, especially in AIGC image analysis, explainable deepfake detection and semantic authenticity assessment.In this paper, we formalize \textbf{semantic anomaly detection and reasoning} for AIGC images and introduce \textbf{AnomReason}, a large-scale benchmark with structured annotations as quadruples \emph{(Name, Phenomenon, Reasoning, Severity)}. Annotations are produced by a modular multi-agent pipeline (\textbf{AnomAgent}) with lightweight human-in-the-loop verification, enabling scale while preserving quality. At construction time, AnomAgent processed approximately 4.17\,B GPT-4o tokens, providing scale evidence for the resulting structured annotations. We further show that models fine-tuned on AnomReason achieve consistent gains over strong vision-language baselines under our proposed semantic matching metric (\textit{SemAP} and \textit{SemF1}). Applications to {explainable deepfake detection} and {semantic reasonableness assessment of image generators} demonstrate practical utility. In summary, AnomReason and AnomAgent serve as a foundation for measuring and improving the semantic plausibility of AI-generated images. We will release code, metrics, data, and task-aligned models to support reproducible research on semantic authenticity and interpretable AIGC forensics.

Primary Area: datasets and benchmarks

Submission Number: 5834