Metraipolis › archive › dc_65d168f01ccd
A Multi-View and Confusion-Guided Ensemble Framework for Robust Synthetic Image Attribution — arXiv:2609.11188
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.11188
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T06:35:19.465Z
- SHA-256 of the archived text
7d711d155d44fa0dc92eacfeff132d2fb4ab806348febcd37388328613ae7324- Stable URL of this page
https://metraipolis.com/documento/dc_65d168f01ccd
How to cite
A Multi-View and Confusion-Guided Ensemble Framework for Robust Synthetic Image Attribution — arXiv:2609.11188 — arXiv (en), https://arxiv.org/abs/2609.11188 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_65d168f01ccd (Metraipolis archive dc_65d168f01ccd, sha256 7d711d155d44fa0dc92eacfeff132d2fb4ab806348febcd37388328613ae7324)
BibTeX
@misc{dc65d168f01ccd,
title = {A Multi-View and Confusion-Guided Ensemble Framework for Robust Synthetic Image Attribution — arXiv:2609.11188},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.11188},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_65d168f01ccd; sha256 7d711d155d44fa0dc92eacfeff132d2fb4ab806348febcd37388328613ae7324},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.11188. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Synthetic image attribution (SIA) has become increasingly important with the rapid advancement of text-to-image generation models. However, accurately identifying the source model of a generated image remains challenging due to the growing similarity among modern diffusion-based generators and the presence of diverse post-processing operations. In this report, we present a multi-view and confusion-guided ensemble framework for the Synthetic Image Attribution Challenge of the DLMMDD Workshop at ICANN 2026. Our approach integrates multiple complementary architectures, including FFT-ConvNeXt, DINOv2, CLIP, and Xception, to capture diverse attribution cues from frequency, semantic, and forensic perspectives. To improve robustness against unknown degradations and image manipulations, extensive data augmentation strategies are employed during training, simulating realistic post-processing operations such as compression, resizing, grayscale conversion, and blur. Furthermore, we analyze the confusion patterns of the ensemble model and observe severe ambiguity between Stable Diffusion 3 and Stable Diffusion 3.5. To address this issue, we introduce a dedicated binary expert classifier that is selectively activated under low-confidence conditions. We additionally apply class-adaptive confidence calibration to improve the discrimination of challenging classes such as Tencent Hunyuan. The proposed framework achieved 99.53% on the public leaderboard and 99.20% on the private leaderboard. The source code and implementation details are publicly available at this https URL . Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-11 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.11188 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-16T06:06:28.759Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).