EUVIMEDEUVIMED entdecken
Crossref

Weakly-Supervised Image Forgery Localization via Vision-Language Collaborative Reasoning Framework

Ziqi Sheng, Junyan Wu, Wei Lu, Jiantao Zhou

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (2) · 988-996

DOI: 10.1609/aaai.v40i2.37068 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Ziqi Sheng und 3 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Image forgery localization aims to precisely identify tampered regions within images, but it commonly depends on costly pixel-level annotations. To alleviate this annotation burden, weakly supervised image forgery localization (WSIFL) has emerged, yet existing methods still achieve limited localization performance as they mainly exploit intra-image consistency clues and lack external semantic guidance to compensate for insufficient supervision information. In this paper, we propose ViLaCo, a vision-language collaborative reasoning framework that introduces auxiliary semantic supervision derived from pre-trained vision-language models (VLMs), enabling accurate pixel-level localization using only image-level labels. Specifically, we first employ a vision-language feature modeling network to jointly extract textual semantics and visual features by leveraging pre-trained VLMs. Next, an adaptive vision-language reasoning network aligns these features through mutual interactions, producing semantically aligned representations. Subsequently, these representations are passed into dual prediction heads, where the coarse head performs image-level classification and the fine head generates pixel-level localization masks, allowing the coarse-grained task to provide guidance for the fine-grained localization. Moreover, a contrastive patch consistency module is introduced to cluster tampered features while separating authentic ones, facilitating more reliable forgery discrimination. Extensive experiments on multiple public datasets demonstrate that ViLaCo substantially outperforms existing WSIFL methods, achieving state-of-the-art performance in both detection and localization accuracy.

Zitieren

APA

Sheng, Z., Wu, J., Lu, W., & Zhou, J. (2026). Weakly-Supervised Image Forgery Localization via Vision-Language Collaborative Reasoning Framework. Proceedings of the AAAI Conference on Artificial Intelligence, 40(2), 988-996. https://doi.org/10.1609/aaai.v40i2.37068

Vancouver

Sheng Z, Wu J, Lu W, Zhou J. Weakly-Supervised Image Forgery Localization via Vision-Language Collaborative Reasoning Framework. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(2):988-996. doi:10.1609/aaai.v40i2.37068

BibTeX
@article{Sheng2026,
  author = {Sheng, Ziqi and Wu, Junyan and Lu, Wei and Zhou, Jiantao},
  title = {Weakly-Supervised Image Forgery Localization via Vision-Language Collaborative Reasoning Framework},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {2},
  pages = {988--996},
  doi = {10.1609/aaai.v40i2.37068}
}
Kostenlos starten →