EUVIMEDEUVIMED entdecken
Crossref

Advanced Discriminative Co-Saliency and Background Mining Transformer for Co-Salient Object Detection

Long Li, Huichao Xie, Nian Liu, Dingwen Zhang, Rao Muhammad Anwer, Hisham Cholakkal, Junwei Han

IEEE Transactions on Pattern Analysis and Machine Intelligence · 2025-09 · 47 (9) · 7733-7751

DOI: 10.1109/tpami.2025.3573054 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025-09. Verfasst von Long Li und 6 weiteren Autor:innen. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 73 Literaturangaben. Gefördert von: Noncommunicable Chronic Diseases-National Science and Technology Major Project, Key-Area Research and Development Program of Guangdong Province, National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Most existing CoSOD models focus solely on extracting co-saliency cues while neglecting explicit exploration of background regions, potentially leading to difficulties in handling interference from complex background areas. To address this, this paper proposes a Discriminative co-saliency and background Mining Transformer framework (DMT) to explicitly mine both co-saliency and background information and effectively model their discriminability. DMT first learns two types of tokens by disjointly extracting co-saliency and background information from segmentation features, then performs discriminability within the segmentation features guided by these well-learned tokens. In the first phase, we propose economic multi-grained correlation modules for efficient detection information extraction, including Region-to-Region (R2R), Contrast-induced Pixel-to-Token (CtP2T), and Co-saliency Token-to-Token (CoT2T) correlation modules. In the subsequent phase, we introduce Token-Guided Feature Refinement (TGFR) modules to enhance discriminability within the segmentation features. To further enhance the discriminative modeling and practicality of DMT, we first upgrade the original TGFR's intra-image modeling approach to an intra-group one, thus proposing Group TGFR (G-TGFR), which is more suitable for the co-saliency task. Subsequently, we designed a Noise Propagation Suppression (NPS) mechanism to apply our model to a more practical open-world scenario, ultimately presenting our extended version, i.e. DMT+O. Extensive experimental results on both conventional CoSOD and open-world CoSOD benchmark datasets demonstrate the effectiveness of our proposed model.

Förderung

  • Noncommunicable Chronic Diseases-National Science and Technology Major Project
  • Key-Area Research and Development Program of Guangdong Province
  • National Natural Science Foundation of China

Zitieren

APA

Li, L., Xie, H., Liu, N., Zhang, D., Anwer, R. M., Cholakkal, H., & Han, J. (2025). Advanced Discriminative Co-Saliency and Background Mining Transformer for Co-Salient Object Detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 47(9), 7733-7751. https://doi.org/10.1109/tpami.2025.3573054

Vancouver

Li L, Xie H, Liu N, Zhang D, Anwer RM, Cholakkal H, et al. Advanced Discriminative Co-Saliency and Background Mining Transformer for Co-Salient Object Detection. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2025;47(9):7733-7751. doi:10.1109/tpami.2025.3573054

BibTeX
@article{Li2025,
  author = {Li, Long and Xie, Huichao and Liu, Nian and Zhang, Dingwen and Anwer, Rao Muhammad and Cholakkal, Hisham and Han, Junwei},
  title = {Advanced Discriminative Co-Saliency and Background Mining Transformer for Co-Salient Object Detection},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2025},
  volume = {47},
  number = {9},
  pages = {7733--7751},
  doi = {10.1109/tpami.2025.3573054}
}
Kostenlos starten →