EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

UAMP: Consistent video object segmentation with uncertainty-aware memory propagation

Yichuang Luo, Fang Wang, Xiaohu Liu iD

PLOS One · 07.07.2026 · 21 (7) · e0353156

DOI: 10.1371/journal.pone.0353156 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, online erschienen am 07.07.2026. Verfasst von Yichuang Luo und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Intelligent Science and Engineering, Xi'an Peihua University, Xi'an, China. Hauptthemen laut MEDLINE: Video Recording, Memory, Image Processing, Computer-Assisted. Die Arbeit nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Shaanxi University of Technology.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The Segment Anything Model 2 (SAM 2) has emerged as a robust foundational model for video object segmentation. Nevertheless, it exhibits notable limitations in crowded scenarios, particularly those involving fast-moving objects or self-occlusion. Furthermore, its greedy-selection memory architecture is afflicted by “error accumulation,” which collectively impairs its performance in consistent object segmentation tasks. To address these critical drawbacks and enhance the consistency and robustness of SAM 2 in complex video scenarios, an enhanced variant of SAM 2, termed UAMP, is proposed, which integrates memory propagation based on explicit appearance and motion uncertainty modeling, coupled with a dual mechanism encompassing long-term memory updating and short-term memory selection. By fusing uncertainty-aware representations with these dual memory mechanisms, UAMP effectively accommodates dynamic variations in object appearance and motion, further refines the object memory bank, and thereby realizes consistent video object segmentation. Quantitative and qualitative evaluations conducted on diverse benchmark datasets demonstrate that UAMP achieves superior performance, particularly in scenarios involving occlusions and object reappearances. Specifically, UAMP yields consistent performance improvements over state-of-the-art (SOTA) methods across five video object segmentation (VOS) benchmarks, with a maximum enhancement of 5.6 points in the J&F metric. These findings underscore the robustness and effectiveness of the proposed UAMP method in addressing complex tracking scenarios, thus providing a valuable enhancement to SAM 2 for practical video object segmentation applications.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Video RecordingMemoryImage Processing, Computer-AssistedUncertaintyAlgorithmsHumans

Autor:innen und Institutionen

  • Department of Intelligent Science and Engineering, Xi'an Peihua University, Xi'an, China.
  • Trine Engineering Institute, Shaanxi University of Technology, Hanzhong, China.

ORCID-Profile: Xiaohu Liu

Förderung

  • Shaanxi University of Technology

Zitieren

APA

Luo, Y., Wang, F., & Liu, X. (2026). UAMP: Consistent video object segmentation with uncertainty-aware memory propagation. PLOS One, 21(7), e0353156. https://doi.org/10.1371/journal.pone.0353156

Vancouver

Luo Y, Wang F, Liu X. UAMP: Consistent video object segmentation with uncertainty-aware memory propagation. PLOS One. 2026;21(7):e0353156. doi:10.1371/journal.pone.0353156

BibTeX
@article{Luo2026,
  author = {Luo, Yichuang and Wang, Fang and Liu, Xiaohu},
  title = {UAMP: Consistent video object segmentation with uncertainty-aware memory propagation},
  journal = {PLOS One},
  year = {2026},
  volume = {21},
  number = {7},
  pages = {e0353156},
  doi = {10.1371/journal.pone.0353156}
}
Kostenlos starten →