Semantic Visual Anomaly Detection and Reasoning in AI-Generated Images
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909837708754944 |
|---|---|
| author | Tan, Chuangchuang Ming, Xiang Wang, Jinglu Tao, Renshuai Li, Bin Wei, Yunchao Zhao, Yao Lu, Yan |
| author_facet | Tan, Chuangchuang Ming, Xiang Wang, Jinglu Tao, Renshuai Li, Bin Wei, Yunchao Zhao, Yao Lu, Yan |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_10231 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Semantic Visual Anomaly Detection and Reasoning in AI-Generated Images Tan, Chuangchuang Ming, Xiang Wang, Jinglu Tao, Renshuai Li, Bin Wei, Yunchao Zhao, Yao Lu, Yan Computer Vision and Pattern Recognition 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. |
| title | Semantic Visual Anomaly Detection and Reasoning in AI-Generated Images |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2510.10231 |