EUVIMEDEUVIMED entdecken
Crossref

Consensus-Driven Coarse-to-Fine Consistency Learning for Co-Salient Object Detection

Zun Li, Jiashuai Xie, Shaoyue Song, Jian Zhao, Lifang Wu

ACM Transactions on Intelligent Systems and Technology · 16.11.2026

DOI: 10.1145/3859250 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Intelligent Systems and Technology, online erschienen am 16.11.2026. Verfasst von Zun Li und 4 weiteren Autor:innen. Die Arbeit nennt 57 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Co-salient object detection aims to identify common salient objects within related group images. The key challenge involves effectively capturing and utilizing the intrinsic consensus across group representations. Existing methods usually mine consensus from global high-level semantics and inject it into basic multi-level features, yet suffer from two key challenges: incomplete consensus exploration due to limited structural modeling under scale/position variations, and non-consensus noise introduced during consensus utilization. In this paper, we propose a novel consensus-driven coarse-to-fine consistency learning method named CCFC, which explores and exploits semantic consensus to achieve multi-level consistent salient features in a coarse-to-fine learning manner. Specifically, we first design a semantic consensus mining module that jointly interacts local structures and global semantics to capture semantic consensus. Then, under the guidance of such consensus, we develop a consensus-driven feature interaction module, which discovers fine-grained low-level and mid-level consistent salient features with cross-attention mechanism. Collaborating with these two modules, the proposed CCFC adaptively propagates semantic consensus across each level consistent features, preserving discriminative consistent salient cues while filtering out redundant noise, and thus predicts co-salient objects with complete contents and clear boundaries. Extensive experiments on three challenging benchmark datasets verify that CCFC achieves superior performance over state-of-the-art methods, with 0.797 \(S_{\alpha}\) and 0.065 MAE on the challenging CoCA dataset. Source code is available at: https://github.com/xiye2002/CCFC.

Zitieren

APA

Li, Z., Xie, J., Song, S., Zhao, J., & Wu, L. (2026). Consensus-Driven Coarse-to-Fine Consistency Learning for Co-Salient Object Detection. ACM Transactions on Intelligent Systems and Technology. https://doi.org/10.1145/3859250

Vancouver

Li Z, Xie J, Song S, Zhao J, Wu L. Consensus-Driven Coarse-to-Fine Consistency Learning for Co-Salient Object Detection. ACM Transactions on Intelligent Systems and Technology. 2026. doi:10.1145/3859250

BibTeX
@article{Li2026,
  author = {Li, Zun and Xie, Jiashuai and Song, Shaoyue and Zhao, Jian and Wu, Lifang},
  title = {Consensus-Driven Coarse-to-Fine Consistency Learning for Co-Salient Object Detection},
  journal = {ACM Transactions on Intelligent Systems and Technology},
  year = {2026},
  doi = {10.1145/3859250}
}
Kostenlos starten →