{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T18:29:41Z","timestamp":1786472981247,"version":"build-2736575974"},"reference-count":59,"publisher":"Public Library of Science (PLoS)","issue":"8","license":[{"start":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T00:00:00Z","timestamp":1786406400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>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.<\/jats:p>","DOI":"10.1371\/journal.pone.0355742","type":"journal-article","created":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T17:32:41Z","timestamp":1786469561000},"page":"e0355742","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Weighted multi-scale and wavelet-enhanced Segment Anything Model for salient object detection"],"prefix":"10.1371","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-7204-8843","authenticated-orcid":true,"given":"Zhe","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dan","family":"Tian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,8,11]]},"reference":[{"issue":"12","key":"pone.0355742.ref001","doi-asserted-by":"crossref","first-page":"5706","DOI":"10.1109\/TIP.2015.2487833","article-title":"Salient object detection: a benchmark","volume":"24","author":"A Borji","year":"2015","journal-title":"IEEE Trans Image Process"},{"key":"pone.0355742.ref002","doi-asserted-by":"crossref","first-page":"107130","DOI":"10.1016\/j.patcog.2019.107130","article-title":"Non-rigid object tracking via deep multi-scale spatial-temporal discriminative saliency maps","volume":"100","author":"P Zhang","year":"2020","journal-title":"Pattern Recogn"},{"key":"pone.0355742.ref003","doi-asserted-by":"crossref","unstructured":"Zhou Z, Pei W, Li X, Wang H, Zheng F, He Z. Saliency-associated object tracking. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. 2021. pp. 9866\u201375.","DOI":"10.1109\/ICCV48922.2021.00972"},{"key":"pone.0355742.ref004","doi-asserted-by":"crossref","unstructured":"Wang W, Shen J, Porikli F. Saliency-aware geodesic video object segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition. 2015. pp. 3395\u2013402.","DOI":"10.1109\/CVPR.2015.7298961"},{"key":"pone.0355742.ref005","doi-asserted-by":"crossref","first-page":"702","DOI":"10.1016\/j.patcog.2018.12.021","article-title":"Deep gated attention networks for large-scale street-level scene segmentation","volume":"88","author":"P Zhang","year":"2019","journal-title":"Pattern Recogn"},{"key":"pone.0355742.ref006","first-page":"2660","article-title":"Part Representation Learning with Teacher-Student Decoder for Occluded Person Re-Identification.","volume-title":"IEEE International Conference on Acoustics, Speech and Signal Processing","author":"S Gao","year":"2024"},{"key":"pone.0355742.ref007","doi-asserted-by":"crossref","first-page":"103809","DOI":"10.1016\/j.imavis.2019.07.009","article-title":"Improved person re-identification based on saliency and semantic parsing with deep neural network models","volume":"92","author":"R Quispe","year":"2019","journal-title":"Image Vision Comput"},{"key":"pone.0355742.ref008","article-title":"FSINet: a robust feature separation and integration network for multiscale SAR object detection","author":"A Wei","year":"2026","journal-title":"IEEE J Select Top Appl Earth Observ Remote Sens"},{"key":"pone.0355742.ref009","doi-asserted-by":"crossref","first-page":"134066","DOI":"10.1016\/j.neucom.2026.134066","article-title":"SWS-YOLO: An energy-efficient spiking neural network for water-surface object detection","author":"Y He","year":"2026","journal-title":"Neurocomputing"},{"key":"pone.0355742.ref010","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"A Dosovitskiy","year":"2020","journal-title":"arXiv preprint"},{"key":"pone.0355742.ref011","doi-asserted-by":"crossref","unstructured":"Kirillov A, Mintun E, Ravi N, Mao H, Rolland C, Gustafson L, et al. Segment anything. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. 2023. pp. 4015\u201326.","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"pone.0355742.ref012","doi-asserted-by":"crossref","unstructured":"Chen T, Zhu L, Deng C, Cao R, Wang Y, Zhang S, et al. Sam-adapter: Adapting segment anything in underperformed scenes. In Proceedings of the IEEE\/CVF International Conference on Computer Vision. 2023. pp. 3367\u201375.","DOI":"10.1109\/ICCVW60793.2023.00361"},{"issue":"1","key":"pone.0355742.ref013","doi-asserted-by":"crossref","first-page":"654","DOI":"10.1038\/s41467-024-44824-z","article-title":"Segment anything in medical images","volume":"15","author":"J Ma","year":"2024","journal-title":"Nat Commun"},{"key":"pone.0355742.ref014","unstructured":"Ren T, Liu S, Zeng A, Lin J, Li K, Cao H, et al. Grounded sam: Assembling open-world models for diverse visual tasks. arXiv preprint. 2024."},{"key":"pone.0355742.ref015","article-title":"MAS-SAM: Segment Any Marine Animal with Aggregated Features","author":"T Yan","year":"2024","journal-title":"arXiv preprint"},{"key":"pone.0355742.ref016","doi-asserted-by":"crossref","unstructured":"Zhang P, Yan T, Liu Y, Lu H. Fantastic Animals and Where to Find Them: Segment Any Marine Animal with Dual SAM. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 2024. pp. 2578\u201387.","DOI":"10.1109\/CVPR52733.2024.00249"},{"key":"pone.0355742.ref017","doi-asserted-by":"crossref","unstructured":"Gao S, Zhang P, Yan T, Lu H. Multi-scale and detail-enhanced segment anything model for salient object detection. Proceedings of the 32nd ACM international conference on multimedia. 2024. pp. 9894\u2013903.","DOI":"10.1145\/3664647.3680650"},{"key":"pone.0355742.ref018","article-title":"Very deep convolutional networks for large-scale image recognition","author":"K Simonyan","year":"2014","journal-title":"arXiv preprint."},{"key":"pone.0355742.ref019","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2016. pp. 770\u20138.","DOI":"10.1109\/CVPR.2016.90"},{"key":"pone.0355742.ref020","doi-asserted-by":"crossref","unstructured":"Zhang P, Wang D, Lu H, Wang H, Ruan X. Amulet: Aggregating multi-level convolutional features for salient object detection. In: Proceedings of the IEEE international conference on computer vision. 2017. pp. 202\u201311.","DOI":"10.1109\/ICCV.2017.31"},{"key":"pone.0355742.ref021","doi-asserted-by":"crossref","unstructured":"Zeng Y, Zhang P, Zhang J, Lin Z, Lu H. Towards high-resolution salient object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. 2019. pp. 7234\u201343.","DOI":"10.1109\/ICCV.2019.00733"},{"issue":"07","key":"pone.0355742.ref022","first-page":"12321","article-title":"F\u00b3Net: Fusion, Feedback and Focus for Salient Object Detection","volume":"34","author":"J Wei","year":"2020","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"pone.0355742.ref023","doi-asserted-by":"crossref","first-page":"107303","DOI":"10.1016\/j.patcog.2020.107303","article-title":"CAGNet: content-aware guidance for salient object detection","volume":"103","author":"S Mohammadi","year":"2020","journal-title":"Pattern Recogn"},{"key":"pone.0355742.ref024","doi-asserted-by":"crossref","first-page":"8652","DOI":"10.1109\/TIP.2020.3017352","article-title":"Dynamic feature integration for simultaneous detection of salient object, edge and skeleton","volume":"29","author":"J-J Liu","year":"2020","journal-title":"IEEE Trans Image Process"},{"key":"pone.0355742.ref025","first-page":"35","article-title":"Suppress and balance: A simple gated network for salient object detection.","volume-title":"Proceedings of European Conference on Computer Vision","author":"X Zhao","year":"2020"},{"key":"pone.0355742.ref026","doi-asserted-by":"crossref","unstructured":"Pang Y, Zhao X, Zhang L, Lu H. Multi-scale interactive network for salient object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 9413\u20139422, 2020.","DOI":"10.1109\/CVPR42600.2020.00943"},{"key":"pone.0355742.ref027","doi-asserted-by":"crossref","unstructured":"Wei J, Wang S, Wu Z, Su C, Huang Q, Tian Q. Label decoupling framework for salient object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 2020. pp. 13025\u201334.","DOI":"10.1109\/CVPR42600.2020.01304"},{"key":"pone.0355742.ref028","doi-asserted-by":"crossref","unstructured":"Wang Y, Wang R, Fan X, Wang T, He X. Pixels, regions, and objects: Multiple enhancement for salient object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 2023. pp. 10031\u201340.","DOI":"10.1109\/CVPR52729.2023.00967"},{"key":"pone.0355742.ref029","doi-asserted-by":"crossref","unstructured":"Liu N, Zhang N, Wan K, Shao L, Han J. Visual saliency transformer. In: Proceedings of the IEEE\/CVF international conference on computer vision. 2021. pp. 4722\u201332.","DOI":"10.1109\/ICCV48922.2021.00468"},{"key":"pone.0355742.ref030","doi-asserted-by":"crossref","unstructured":"Yuan L, Chen Y, Wang T, Yu W, Shi Y, Jiang ZH, et al. Tokens-to-token vit: Training vision transformers from scratch on imagenet. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. 2021. pp. 558\u201367.","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"pone.0355742.ref031","article-title":"Selfreformer: Self-refined network with transformer for salient object detection","author":"YK Yun","year":"2022","journal-title":"arXiv preprint"},{"issue":"3","key":"pone.0355742.ref032","first-page":"3738","article-title":"Salient Object Detection via Integrity Learning","volume":"45","author":"M Zhuge","year":"2023","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"pone.0355742.ref033","doi-asserted-by":"crossref","unstructured":"Liu Z, Lin Y, Cao Y, Hu H, Wei Y, Zhang Z, et al. Swin transformer: Hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. 2021. pp. 10012\u201322.","DOI":"10.1109\/ICCV48922.2021.00986"},{"issue":"11","key":"pone.0355742.ref034","doi-asserted-by":"crossref","first-page":"11592","DOI":"10.1109\/TCSVT.2024.3424651","article-title":"Learning Local-Global Representation for Scribble-Based RGB-D Salient Object Detection via Transformer","volume":"34","author":"Y Wang","year":"2024","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"pone.0355742.ref035","doi-asserted-by":"crossref","unstructured":"Deng X, Zhang P, Liu W, Lu H. Recurrent multi-scale transformer for high-resolution salient object detection. In Proceedings of the 31st ACM International Conference on Multimedia. 2023. pp. 7413\u201323.","DOI":"10.1145\/3581783.3611983"},{"key":"pone.0355742.ref036","article-title":"Adaptive low rank adaptation of segment anything to salient object detection","author":"R Cui","year":"2023","journal-title":"arXiv preprint"},{"issue":"4","key":"pone.0355742.ref037","doi-asserted-by":"crossref","first-page":"2987","DOI":"10.1109\/TCSVT.2024.3368053","article-title":"Multidimensional exploration of segment anything model for weakly supervised video salient object detection","volume":"35","author":"B Xu","year":"2025","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"pone.0355742.ref038","doi-asserted-by":"crossref","unstructured":"Ke L, Ye M, Danelljan M, Tai YW, Tang CK, Yu F, et al. Segment anything in high quality. Advances in Neural Information Processing Systems. 2024. 36.","DOI":"10.52202\/075280-1303"},{"key":"pone.0355742.ref039","first-page":"2790","article-title":"Parameter-efficient transfer learning for NLP.","volume-title":"International conference on machine learning","author":"N Houlsby","year":"2019"},{"key":"pone.0355742.ref040","article-title":"Attention is all you need","volume":"30","author":"A Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"pone.0355742.ref041","article-title":"Layer normalization","author":"JL Ba","year":"2016","journal-title":"arXiv preprint"},{"key":"pone.0355742.ref042","article-title":"Gaussian error linear units (gelus)","author":"D Hendrycks","year":"2016","journal-title":"arXiv preprint"},{"key":"pone.0355742.ref043","doi-asserted-by":"crossref","unstructured":"Hu J, Shen L, Sun G. Squeeze-and-excitation networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition. 2018. pp. 7132\u201341.","DOI":"10.1109\/CVPR.2018.00745"},{"key":"pone.0355742.ref044","doi-asserted-by":"crossref","unstructured":"Liu W, Yan Q, Zhao Y. Densely self-guided wavelet network for image denoising. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. Workshops (CVPRW). 2020. pp. 1742\u201350.","DOI":"10.1109\/CVPRW50498.2020.00224"},{"key":"pone.0355742.ref045","doi-asserted-by":"crossref","unstructured":"Wang L, Lu H, Wang Y, Feng M, Wang D, Yin B, et al. Learning to detect salient objects with image-level supervision. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2017. pp. 136\u201345.","DOI":"10.1109\/CVPR.2017.404"},{"key":"pone.0355742.ref046","doi-asserted-by":"crossref","unstructured":"Yang C, Zhang L, Lu H, Ruan X, Yang M. Saliency detection via graph-based manifold ranking. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2013. pp. 3166\u201373.","DOI":"10.1109\/CVPR.2013.407"},{"key":"pone.0355742.ref047","doi-asserted-by":"crossref","unstructured":"Li G, Yu Y. Visual saliency based on multiscale deep features. In: Proceedings of the IEEE conference on Computer Vision and Pattern Recognition. 2015. pp. 5455\u201363.","DOI":"10.1109\/CVPR.2015.7299184"},{"key":"pone.0355742.ref048","doi-asserted-by":"crossref","unstructured":"Yan Q, Xu L, Shi J, Jia J. Hierarchical saliency detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2013. pp. 1155\u201362.","DOI":"10.1109\/CVPR.2013.153"},{"key":"pone.0355742.ref049","doi-asserted-by":"crossref","unstructured":"Li Y, Hou X, Koch C, Rehg JM, Yuille AL. The secrets of salient object segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2014. pp. 280\u201387.","DOI":"10.1109\/CVPR.2014.43"},{"key":"pone.0355742.ref050","first-page":"733","article-title":"Saliency filters: Contrast based filtering for salient region detection.","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"F Perazzi","year":"2012"},{"key":"pone.0355742.ref051","doi-asserted-by":"crossref","unstructured":"Fan DP, Cheng MM, Liu Y, Li T, Borji A. Structure-measure: A new way to evaluate foreground maps. In: Proceedings of the IEEE international conference on computer vision. 2017. pp. 4548\u201357.","DOI":"10.1109\/ICCV.2017.487"},{"key":"pone.0355742.ref052","article-title":"Enhanced-alignment measure for binary foreground map evaluation","author":"DP Fan","year":"2018","journal-title":"arXiv preprint"},{"key":"pone.0355742.ref053","doi-asserted-by":"crossref","first-page":"1026","DOI":"10.1109\/TIP.2022.3232209","article-title":"Boosting Broader Receptive Fields for Salient Object Detection","volume":"32","author":"M Ma","year":"2023","journal-title":"IEEE Trans Image Process"},{"issue":"3","key":"pone.0355742.ref054","doi-asserted-by":"crossref","first-page":"569","DOI":"10.1109\/TPAMI.2014.2345401","article-title":"Global Contrast Based Salient Region Detection","volume":"37","author":"M-M Cheng","year":"2015","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"pone.0355742.ref055","doi-asserted-by":"crossref","unstructured":"Achanta R, Hemami S, Estrada F, Susstrunk S. Frequency-tuned salient region detection. IEEE Conference on Computer Vision and Pattern Recognition. 2009. pp. 1597\u2013604.","DOI":"10.1109\/CVPR.2009.5206596"},{"key":"pone.0355742.ref056","article-title":"DualGazeNet: A Biologically Inspired Dual-Gaze Query Network for Salient Object Detection","author":"Y Zhang","year":"2025","journal-title":"arXiv preprint"},{"key":"pone.0355742.ref057","article-title":"Bilateral reference for high-resolution dichotomous image segmentation","author":"P Zheng","year":"2024","journal-title":"arXiv preprint"},{"key":"pone.0355742.ref058","article-title":"DGSSM: Diffusion guided state-space models for multimodal salient object detection","author":"S Ghosh","year":"2026","journal-title":"arXiv preprint"},{"key":"pone.0355742.ref059","article-title":"Cpdr: Towards highly-efficient salient object detection via crossed post-decoder refinement","author":"Y Li","year":"2025","journal-title":"arXiv preprint"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0355742","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T17:32:56Z","timestamp":1786469576000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0355742"}},"subtitle":[],"editor":[{"given":"Yongjie","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,8,11]]},"references-count":59,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2026,8,11]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0355742","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,11]]}}}