EUVIMEDEUVIMED entdecken
Crossref

SynerDetect: Hierarchical Synergistic Learning for Generalizable AI-Generated Image Detection

Shuaibo Li, Yijun Yang, Zhaohu Xing, Hongqiu Wang, Pengfei Hao, Xingyu Li, Zekai Liu, Qing Zhang, Lei Zhu

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (8) · 6405-6414

DOI: 10.1609/aaai.v40i8.37568 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Shuaibo Li und 8 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The rapid advancement of generative models, which produce increasingly realistic synthetic images, urgently demands robust and generalizable detection methods. Consequently, research has largely pivoted to leveraging large-scale Vision Foundation Models (VFMs) for enhanced generalization. However, existing VFM-based approaches primarily adhere to either perceptual or generative paradigms, each with limitations: perceptual models capture high-level semantics but often miss subtle artifacts, whereas generative models emphasize fine-grained flaws yet overlook semantic inconsistency. To resolve this inherent trade-off, we introduce SynerDetect, a novel hierarchical synergistic framework that fundamentally unifies the two paradigms. SynerDetect achieves deep integration of heterogeneous forensic representations through two levels of synergy: Cross-Model Interactive Distillation (CMID) distills generative forensic signals into perceptual encoders via prompt-guided reconstruction; and Optimal Transport-Guided Discriminative Contrastive Learning (OT-DCL) structurally aligns and integrates these heterogeneous representations, consolidating them into a robust, unified detection space. SynerDetect achieves superior performance on standard benchmarks (AIGCDetectBenchmark and GenImage) and attains a notable 5.20% accuracy gain on the challenging Chameleon benchmark, whose synthetic images consistently pass the Visual Turing Test. These results unequivocally validate the robust, real-world generalization of our unified cross-paradigm framework.

Zitieren

APA

Li, S., Yang, Y., Xing, Z., Wang, H., Hao, P., Li, X., Liu, Z., Zhang, Q., & Zhu, L. (2026). SynerDetect: Hierarchical Synergistic Learning for Generalizable AI-Generated Image Detection. Proceedings of the AAAI Conference on Artificial Intelligence, 40(8), 6405-6414. https://doi.org/10.1609/aaai.v40i8.37568

Vancouver

Li S, Yang Y, Xing Z, Wang H, Hao P, Li X, et al. SynerDetect: Hierarchical Synergistic Learning for Generalizable AI-Generated Image Detection. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(8):6405-6414. doi:10.1609/aaai.v40i8.37568

BibTeX
@article{Li2026,
  author = {Li, Shuaibo and Yang, Yijun and Xing, Zhaohu and Wang, Hongqiu and Hao, Pengfei and Li, Xingyu and Liu, Zekai and Zhang, Qing and Zhu, Lei},
  title = {SynerDetect: Hierarchical Synergistic Learning for Generalizable AI-Generated Image Detection},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {8},
  pages = {6405--6414},
  doi = {10.1609/aaai.v40i8.37568}
}
Kostenlos starten →