{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,23]],"date-time":"2026-01-23T22:14:50Z","timestamp":1769206490141,"version":"3.49.0"},"reference-count":43,"publisher":"Public Library of Science (PLoS)","issue":"1","license":[{"start":{"date-parts":[[2026,1,23]],"date-time":"2026-01-23T00:00:00Z","timestamp":1769126400000},"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>Accurate segmentation of salient objects is crucial for various computer vision applications including image editing, autonomous driving, and object detection. While research on using depth information (RGB-D) in saliency detection is gaining significant attention, its broad application is limited by dependencies on depth sensors and the challenge of effectively integrating RGB and depth information. To address these issues, we propose an innovative method for salient object segmentation that integrates the Segment Anything Model (SAM), depth information, and cross-modal attention mechanisms. Our approach leverages SAM for robust feature extraction and combines it with a pre-trained depth estimation network to capture geometric information. By dynamically fusing features from RGB and depth modalities through a cross-modal attention mechanism, our method enhances the ability to handle diverse scenes. Additionally, we achieve computational efficiency without compromising precision by employing lightweight LoRA fine-tuning and freezing pre-trained weights. The use of a UNet decoder refines the segmentation output, ensuring the preservation of target boundary details in high-resolution outputs. Experiments conducted on five challenging benchmark datasets validate the effectiveness of our proposed method. Results show significant improvements over existing methods across key evaluation metrics, including MaxF, MAE, and S-measure. Particularly in tasks involving complex backgrounds, small targets, and multiple salient object segmentation, our method demonstrates superior performance and robustness. The significance of this work lies in advancing the application of depth-guided RGB in salient object segmentation while offering new insights into overcoming depth sensor dependency. Furthermore, it opens up novel pathways for the effective fusion of cross-modal information, thereby contributing to the broader development and diversification of related technologies and their applications.<\/jats:p>","DOI":"10.1371\/journal.pone.0340765","type":"journal-article","created":{"date-parts":[[2026,1,23]],"date-time":"2026-01-23T18:25:26Z","timestamp":1769192726000},"page":"e0340765","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Study on salient object segmentation based on depth information guidance and SAM low-rank adaptation fine-tuning"],"prefix":"10.1371","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2317-253X","authenticated-orcid":true,"given":"Weiping","family":"M.A.","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"340","published-online":{"date-parts":[[2026,1,23]]},"reference":[{"issue":"1","key":"pone.0340765.ref001","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1007\/s41095-020-0199-z","article-title":"RGB-D salient object detection: A survey","volume":"7","author":"T Zhou","year":"2021","journal-title":"Comput Vis Media (Beijing)"},{"issue":"3","key":"pone.0340765.ref002","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.0340765.ref003","doi-asserted-by":"crossref","first-page":"835","DOI":"10.1016\/j.ins.2020.09.003","article-title":"CNN-based encoder-decoder networks for salient object detection: A comprehensive review and recent advances","volume":"546","author":"Y Ji","year":"2021","journal-title":"Information Sciences"},{"key":"pone.0340765.ref004","doi-asserted-by":"crossref","first-page":"5257","DOI":"10.1109\/TIP.2023.3314285","article-title":"Salient Object Detection in Optical Remote Sensing Images Driven by Transformer","volume":"32","author":"G Li","year":"2023","journal-title":"IEEE Trans Image Process"},{"key":"pone.0340765.ref005","doi-asserted-by":"crossref","first-page":"104204","DOI":"10.1016\/j.engappai.2021.104204","article-title":"A better way of extracting dominant colors using salient objects with semantic segmentation","volume":"100","author":"AB Gunduz","year":"2021","journal-title":"Engineering Applications of Artificial Intelligence"},{"key":"pone.0340765.ref006","doi-asserted-by":"crossref","first-page":"541581","DOI":"10.3389\/fncom.2020.541581","article-title":"Proto-Object Based Saliency Model With Texture Detection Channel","volume":"14","author":"T Uejima","year":"2020","journal-title":"Front Comput Neurosci"},{"issue":"1","key":"pone.0340765.ref007","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1049\/cvi2.12221","article-title":"Mirror complementary transformer network for RGB\u2010thermal salient object detection","volume":"18","author":"X Jiang","year":"2023","journal-title":"IET Computer Vision"},{"key":"pone.0340765.ref008","doi-asserted-by":"crossref","first-page":"121330","DOI":"10.1109\/ACCESS.2020.3006700","article-title":"A Multi-Scale Colour and Keypoint Density-Based Approach for Visual Saliency Detection","volume":"8","author":"A Bruno","year":"2020","journal-title":"IEEE Access"},{"key":"pone.0340765.ref009","doi-asserted-by":"crossref","unstructured":"Wu Z, Su L, Huang Q. Cascaded partial decoder for fast and accurate salient object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2019. 3907\u201316.","DOI":"10.1109\/CVPR.2019.00403"},{"issue":"5","key":"pone.0340765.ref010","doi-asserted-by":"crossref","first-page":"7842","DOI":"10.1109\/TII.2024.3366221","article-title":"MINet: Multiscale Interactive Network for Real-Time Salient Object Detection of Strip Steel Surface Defects","volume":"20","author":"K Shen","year":"2024","journal-title":"IEEE Trans Ind Inf"},{"issue":"8","key":"pone.0340765.ref011","doi-asserted-by":"crossref","first-page":"2827","DOI":"10.1080\/01431161.2020.1826059","article-title":"A hierarchical object detection method in large-scale optical remote sensing satellite imagery using saliency detection and CNN","volume":"42","author":"Z Song","year":"2021","journal-title":"International Journal of Remote Sensing"},{"issue":"11","key":"pone.0340765.ref012","doi-asserted-by":"crossref","first-page":"8006","DOI":"10.1109\/TPAMI.2021.3107956","article-title":"A Highly Efficient Model to Study the Semantics of Salient Object Detection","volume":"44","author":"M-M Cheng","year":"2022","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"2","key":"pone.0340765.ref013","doi-asserted-by":"crossref","first-page":"1063","DOI":"10.1609\/aaai.v35i2.16191","article-title":"RGB-D Salient Object Detection via 3D Convolutional Neural Networks","volume":"35","author":"Q Chen","year":"2021","journal-title":"AAAI"},{"issue":"1","key":"pone.0340765.ref014","doi-asserted-by":"crossref","first-page":"87","DOI":"10.1109\/TPAMI.2022.3152247","article-title":"A Survey on Vision Transformer","volume":"45","author":"K Han","year":"2023","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"pone.0340765.ref015","article-title":"Dinov2: Learning robust visual features without supervision","author":"M Oquab","year":"2023","journal-title":"arXiv preprint"},{"issue":"8","key":"pone.0340765.ref016","doi-asserted-by":"crossref","first-page":"10663","DOI":"10.1109\/TNNLS.2023.3243246","article-title":"Learning Complementary Spatial-Temporal Transformer for Video Salient Object Detection","volume":"35","author":"N Liu","year":"2024","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"pone.0340765.ref017","doi-asserted-by":"crossref","first-page":"111075","DOI":"10.1016\/j.knosys.2023.111075","article-title":"Transformer-based hierarchical dynamic decoders for salient object detection","volume":"282","author":"Q Zheng","year":"2023","journal-title":"Knowledge-Based Systems"},{"issue":"4","key":"pone.0340765.ref018","doi-asserted-by":"crossref","first-page":"2332","DOI":"10.1109\/TCSVT.2023.3307693","article-title":"Boosting Salient Object Detection With Transformer-Based Asymmetric Bilateral U-Net","volume":"34","author":"Y Qiu","year":"2024","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"pone.0340765.ref019","doi-asserted-by":"crossref","unstructured":"Liu Z, Lin Y, Cao Y, et al. Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2021. 10012\u201322.","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"pone.0340765.ref020","doi-asserted-by":"crossref","unstructured":"Fan H, Xiong B, Mangalam K. Multiscale vision transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2021. 6824\u201335.","DOI":"10.1109\/ICCV48922.2021.00675"},{"key":"pone.0340765.ref021","article-title":"Siamese Network for RGB-D Salient Object Detection and Beyond","author":"K Fu","year":"2021","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"pone.0340765.ref022","doi-asserted-by":"crossref","first-page":"9179","DOI":"10.1109\/TIP.2021.3123548","article-title":"Dynamic Selective Network for RGB-D Salient Object Detection","volume":"30","author":"H Wen","year":"2021","journal-title":"IEEE Trans Image Process"},{"key":"pone.0340765.ref023","doi-asserted-by":"crossref","unstructured":"Li C, Cong R, Piao Y. RGB-D salient object detection with cross-modality modulation and selection. In: Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, 2020. 225\u201341.","DOI":"10.1007\/978-3-030-58598-3_14"},{"key":"pone.0340765.ref024","doi-asserted-by":"crossref","first-page":"2249","DOI":"10.1109\/TMM.2023.3294003","article-title":"CATNet: A Cascaded and Aggregated Transformer Network for RGB-D Salient Object Detection","volume":"26","author":"F Sun","year":"2024","journal-title":"IEEE Trans Multimedia"},{"key":"pone.0340765.ref025","doi-asserted-by":"crossref","unstructured":"Kirillov A, Mintun E, Ravi N. Segment anything. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2023. 4015\u201326.","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"pone.0340765.ref026","unstructured":"Ravi N, Gabeur V, Hu YT. Sam 2: Segment anything in images and videos. In: 2024. https:\/\/arxiv.org\/abs\/2408.00714"},{"key":"pone.0340765.ref027","article-title":"Segment anything in high quality","volume":"36","author":"L Ke","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"pone.0340765.ref028","article-title":"Lora: Low-rank adaptation of large language models","author":"EJ Hu","year":"2021","journal-title":"arXiv preprint"},{"key":"pone.0340765.ref029","doi-asserted-by":"crossref","unstructured":"Wang L, Lu H, Wang Y. Learning to detect salient objects with image-level supervision. In: Proceedings of the IEEE conference on computer vision and pattern recognition, 2017. 136\u201345.","DOI":"10.1109\/CVPR.2017.404"},{"key":"pone.0340765.ref030","doi-asserted-by":"crossref","unstructured":"Yan Q, Xu L, Shi J, Jia J. Hierarchical Saliency Detection. In: 2013 IEEE Conference on Computer Vision and Pattern Recognition, 2013. 1155\u201362. doi: 10.1109\/cvpr.2013.153","DOI":"10.1109\/CVPR.2013.153"},{"key":"pone.0340765.ref031","doi-asserted-by":"crossref","unstructured":"Li Y. The secrets of salient object segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2014.","DOI":"10.1109\/CVPR.2014.43"},{"key":"pone.0340765.ref032","doi-asserted-by":"crossref","unstructured":"Guanbin Li, Yu Y. Visual saliency based on multiscale deep features. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015. 5455\u201363. doi: 10.1109\/cvpr.2015.7299184","DOI":"10.1109\/CVPR.2015.7299184"},{"key":"pone.0340765.ref033","doi-asserted-by":"crossref","unstructured":"Yang C, Zhang L, Lu H. Saliency detection via graph-based manifold ranking. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2013. 3166\u201373.","DOI":"10.1109\/CVPR.2013.407"},{"key":"pone.0340765.ref034","doi-asserted-by":"crossref","unstructured":"Luo Z, Mishra A, Achkar A. Non-local deep features for salient object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017. 6609\u201317.","DOI":"10.1109\/CVPR.2017.698"},{"key":"pone.0340765.ref035","doi-asserted-by":"crossref","unstructured":"Liu N, Han J, Yang M-H. PiCANet: Learning Pixel-Wise Contextual Attention for Saliency Detection. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2018. 3089\u201398. doi: 10.1109\/cvpr.2018.00326","DOI":"10.1109\/CVPR.2018.00326"},{"key":"pone.0340765.ref036","doi-asserted-by":"crossref","unstructured":"Wu Z, Su L, Huang Q. Cascaded partial decoder for fast and accurate salient object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2019. 3907\u201316.","DOI":"10.1109\/CVPR.2019.00403"},{"key":"pone.0340765.ref037","doi-asserted-by":"crossref","unstructured":"Liu JJ, Hou Q, Cheng MM. A simple pooling-based design for real-time salient object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2019. 3917\u201326.","DOI":"10.1109\/CVPR.2019.00404"},{"key":"pone.0340765.ref038","doi-asserted-by":"crossref","unstructured":"Zhao JX, Liu JJ, Fan DP. EGNet: Edge guidance network for salient object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2019. 8779\u201388.","DOI":"10.1109\/ICCV.2019.00887"},{"key":"pone.0340765.ref039","doi-asserted-by":"crossref","unstructured":"Wu Z, Su L, Huang Q. Stacked cross refinement network for edge-aware salient object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2019. 7264\u201373.","DOI":"10.1109\/ICCV.2019.00736"},{"key":"pone.0340765.ref040","doi-asserted-by":"crossref","unstructured":"Zhou H, Xie X, Lai JH. Interactive two-stream decoder for accurate and fast saliency detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2020. 9141\u201350.","DOI":"10.1109\/CVPR42600.2020.00916"},{"key":"pone.0340765.ref041","doi-asserted-by":"crossref","unstructured":"Wei J, Wang S, Wu Z. Label decoupling framework for salient object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2020. 13025\u201334.","DOI":"10.1109\/CVPR42600.2020.01304"},{"issue":"3","key":"pone.0340765.ref042","doi-asserted-by":"crossref","first-page":"2311","DOI":"10.1609\/aaai.v35i3.16331","article-title":"Pyramidal Feature Shrinking for Salient Object Detection","volume":"35","author":"M Ma","year":"2021","journal-title":"AAAI"},{"key":"pone.0340765.ref043","doi-asserted-by":"crossref","first-page":"3125","DOI":"10.1109\/TIP.2022.3164550","article-title":"EDN: Salient Object Detection via Extremely-Downsampled Network","volume":"31","author":"Y-H Wu","year":"2022","journal-title":"IEEE Trans Image Process"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0340765","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,23]],"date-time":"2026-01-23T18:25:33Z","timestamp":1769192733000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0340765"}},"subtitle":[],"editor":[{"given":"Aiqing","family":"Fang","sequence":"first","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2026,1,23]]},"references-count":43,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,1,23]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0340765","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,23]]}}}