EUVIMEDEUVIMED entdecken
Crossref

Dual-Branch Asymmetric Discrepancy Learning Based on Fake Image Pattern-Coexistence for AI-Generated Image Detection

Chunli Song, Jie Liu, Peiyang Wang, Ying Huang, Guixuan Zhang, Zhi Zeng, Shuwu Zhang

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (2) · 1015-1023

DOI: 10.1609/aaai.v40i2.37071 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Chunli Song und 6 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

With the rapid advancement of generative models, high-fidelity AI-generated images have become increasingly indistinguishable from real images, posing significant challenges to traditional detection methods that rely on explicit artifacts or uniform feature learning. We hypothesize that detection ambiguity originates from pattern coexistence: synthetic images simultaneously embed (a) authentic patterns inherited from real-image distributions and (b) synthetic patterns induced by generative architectures, whereas real images maintain consistent patterns. We validate this hypothesis through SHAP-based quantitative analysis, demonstrating that synthetic images inherently exhibit a dual distribution—simultaneously containing authentic patterns and synthetic traces—while real images show a unimodal distribution. Building on this insight, this paper proposes a Dual-Branch Asymmetric Discrepancy Learning (DADL) framework. The DADL leverages multi-scale feature extraction and Asymmetric Feature Discrepancy Loss to capture and amplify such pattern differences across multiple scales. Extensive experiments on three benchmarks (AIGCDetectBenchmark, GenImage, and Chameleon) show that DADL achieves state-of-the-art performance, with particular strengths in detecting high-fidelity synthetic images from diffusion models (e.g., Midjourney, SDv1.4, SDv1.5) and enhancing generalization across diverse generative paradigms. This study not only offers an effective approach for AIGI detection but also sheds light on the intrinsic properties of synthetic images, providing a new perspective for advancing AIGI forensics.

Zitieren

APA

Song, C., Liu, J., Wang, P., Huang, Y., Zhang, G., Zeng, Z., & Zhang, S. (2026). Dual-Branch Asymmetric Discrepancy Learning Based on Fake Image Pattern-Coexistence for AI-Generated Image Detection. Proceedings of the AAAI Conference on Artificial Intelligence, 40(2), 1015-1023. https://doi.org/10.1609/aaai.v40i2.37071

Vancouver

Song C, Liu J, Wang P, Huang Y, Zhang G, Zeng Z, et al. Dual-Branch Asymmetric Discrepancy Learning Based on Fake Image Pattern-Coexistence for AI-Generated Image Detection. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(2):1015-1023. doi:10.1609/aaai.v40i2.37071

BibTeX
@article{Song2026,
  author = {Song, Chunli and Liu, Jie and Wang, Peiyang and Huang, Ying and Zhang, Guixuan and Zeng, Zhi and Zhang, Shuwu},
  title = {Dual-Branch Asymmetric Discrepancy Learning Based on Fake Image Pattern-Coexistence for AI-Generated Image Detection},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {2},
  pages = {1015--1023},
  doi = {10.1609/aaai.v40i2.37071}
}
Kostenlos starten →