Weighted multi-scale and wavelet-enhanced Segment Anything Model for salient object detection
PLOS One · 11.08.2026 · 21 (8) · e0355742
DOI: 10.1371/journal.pone.0355742 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS One, online erschienen am 11.08.2026. Verfasst von Zhe Liu und 1 weiteren Autor:innen. Beteiligte Einrichtung: School of Intelligent Science and Information Engineering, Shenyang University, Shenyang, Liaoning, China. Hauptthemen laut MEDLINE: Image Processing, Computer-Assisted, Models, Theoretical. Die Arbeit nennt 59 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Salient Object Detection (SOD) is concerned with isolating the visually most noticeable objects in an image via precise segmentation. Previous approaches, especially those that adapt the Segment Anything Model (SAM), often yield saliency maps that contain incomplete object masks, blurred boundaries, and a lack of fine-grained details. This issue is especially severe for scenes with objects of different scales or complex textures. We argue that these issues stem from three inherent limitations of existing adaptation strategies: (1) existing adapters rely on rigid multi-scale fusion strategies, lacking learnable cross-scale calibration to handle objects of diverse sizes, (2) simple feature concatenation ignores cross-level semantic correlations, (3) spatial-domain operations inevitably discard high-frequency details. The proposed WMW-SAM, a Weighted Multi-Scale and Wavelet-Enhanced SAM, is designed to handle these limitations for SOD. Specifically, we develop the Weighted Multi-Scale Adapter (WMSA), which utilizes learnable weighting across multiple receptive fields to calibrate features of different scales. Then, our Multi-level Feature Cross-fusion Module (MFCM) employs cascaded top-down cross-attention to facilitate deep interaction that connects high-level semantics with low-level details. Finally, we develop a Detail Enhancement Module (DEM) that leverages the Discrete Wavelet Transform (DWT) to explicitly extract and enhance high-frequency sub-bands. This operation effectively recovers sharp boundaries and intricate textures, which are often overlooked by spatial-domain operations. Extensive experiments on multiple benchmark datasets demonstrate the superior performance of our proposed WMW-SAM, which achieves accurate and detailed saliency predictions.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- School of Intelligent Science and Information Engineering, Shenyang University, Shenyang, Liaoning, China.
ORCID-Profile: Zhe Liu
Zitieren
APA
Liu, Z., & Tian, D. (2026). Weighted multi-scale and wavelet-enhanced Segment Anything Model for salient object detection. PLOS One, 21(8), e0355742. https://doi.org/10.1371/journal.pone.0355742
Vancouver
Liu Z, Tian D. Weighted multi-scale and wavelet-enhanced Segment Anything Model for salient object detection. PLOS One. 2026;21(8):e0355742. doi:10.1371/journal.pone.0355742
BibTeX
@article{Liu2026,
author = {Liu, Zhe and Tian, Dan},
title = {Weighted multi-scale and wavelet-enhanced Segment Anything Model for salient object detection},
journal = {PLOS One},
year = {2026},
volume = {21},
number = {8},
pages = {e0355742},
doi = {10.1371/journal.pone.0355742}
}
EUVIMED