Official test dataset for AlignGemini, accepted by ACM Multimedia 2026.
AIGI-Now covers nine contemporary image generators and provides separate subsets for evaluating semantic and pixel-artifact discrimination.
@inproceedings{chen2026aligngemini,
title={Align, Don't Blend: Orthogonal Supervision Disentanglement As the Key to Generalizable AI-Generated Image Detection},
author={Chen, Ruoxin and Gao, Jiahui and Lin, Kaiqing and Zhang, Keyue and Zhao, Yandan and Guan, Isabel and Yao, Taiping and Ding, Shouhong},
booktitle={Proceedings of the 34th ACM International Conference on Multimedia},
year={2026}
}
5 commits
Official test dataset for AlignGemini, accepted by ACM Multimedia 2026.
AIGI-Now covers nine contemporary image generators and provides separate subsets for evaluating semantic and pixel-artifact discrimination.
@inproceedings{chen2026aligngemini,
title={Align, Don't Blend: Orthogonal Supervision Disentanglement As the Key to Generalizable AI-Generated Image Detection},
author={Chen, Ruoxin and Gao, Jiahui and Lin, Kaiqing and Zhang, Keyue and Zhao, Yandan and Guan, Isabel and Yao, Taiping and Ding, Shouhong},
booktitle={Proceedings of the 34th ACM International Conference on Multimedia},
year={2026}
}
5 commits