{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T17:13:45Z","timestamp":1783530825597,"version":"3.55.0"},"reference-count":32,"publisher":"MDPI AG","issue":"14","license":[{"start":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T00:00:00Z","timestamp":1783468800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Collaborative Innovation Center of Novel Software Technology and Industrialization"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Underwater object detection is a fundamental task in underwater sensing and is generally approached using either optical or sonar sensors. Although optical imaging provides rich semantic information, it is highly susceptible to water turbidity and illumination variations. By contrast, sonar imaging can effectively overcome visibility limitations, yet it suffers from severe speckle noise and blurred object contours. Moreover, resource-limited platforms impose strict demands on model lightweightness and real-time performance. To this end, this paper proposes a novel cross-modal heterogeneous distillation method (CMHD) to balance detection accuracy and computational complexity. CMHD performs cross-modal knowledge transfer by leveraging the rich semantics of RGB images to enhance sonar feature representation, compensating for the information deficiency of the sonar modality. Meanwhile, a heterogeneous distillation scheme compresses the detection capability of a high-capacity teacher YOLOX-M into a lightweight student YOLOX-S-Ghost, enabling strong feature extraction under a highly compact model. To mitigate the modality gap and geometric inconsistency between RGB and sonar modalities, we design a branch-aware heterogeneous distillation strategy. To improve detection accuracy and reduce model parameters, the student network incorporates Coordinate Attention (CA) in its backbone and adopts a lightweight neck design. Experiments on the UXO\u2020 dataset demonstrate that CMHD achieves 79.6% mAP and 82.6% mAR, significantly outperforming the compared representative methods and serving as an accurate, efficient, and lightweight solution for underwater sonar object detection.<\/jats:p>","DOI":"10.3390\/s26144340","type":"journal-article","created":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T16:16:18Z","timestamp":1783527378000},"page":"4340","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Lightweight Underwater Sonar Object Detection via RGB-Guided Heterogeneous Distillation"],"prefix":"10.3390","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-7298-4137","authenticated-orcid":false,"given":"Qianqian","family":"Qiao","sequence":"first","affiliation":[{"name":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing 210093, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jia","family":"Liu","sequence":"additional","affiliation":[{"name":"Laboratory of Autonomous Underwater Vehicles, Institute of Acoustics, Chinese Academy of Sciences, Beijing 100190, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Feng","family":"Liu","sequence":"additional","affiliation":[{"name":"National Innovation Institute of Defense Technology, Academy of Military Sciences, Beijing 100097, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9643-1099","authenticated-orcid":false,"given":"Chengpeng","family":"Hao","sequence":"additional","affiliation":[{"name":"Laboratory of Autonomous Underwater Vehicles, Institute of Acoustics, Chinese Academy of Sciences, Beijing 100190, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tongwei","family":"Ren","sequence":"additional","affiliation":[{"name":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing 210093, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,7,8]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Ho\u017cy\u0144, S. (2021). A Review of Underwater Mine Detection and Classification in Sonar Imagery. Electronics, 10.","DOI":"10.3390\/electronics10232943"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"848","DOI":"10.1002\/rob.22159","article-title":"Underwater UXO Detection Using Magnetometry on Hovering AUVs","volume":"40","author":"Seidel","year":"2023","journal-title":"J. Field Robot."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Isaacs, J.C. (2015). Sonar Automatic Target Recognition for Underwater UXO Remediation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, IEEE.","DOI":"10.1109\/CVPRW.2015.7301307"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Mane, V., Patwardhan, S., Pethkar, P., and Patil, R. (2024). Underwater Object Tracking and Classification of Marine Animals. Proceedings of the International Conference on Inventive Computation Technologies, IEEE.","DOI":"10.1109\/ICICT60155.2024.10544926"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Zhu, N., Liu, Z., Wang, Z., and Xie, Z. (2025). Seafood Object Detection Method Based on Improved YOLOv5s. Sensors, 25.","DOI":"10.3390\/s25247546"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"\u00c1lvarez-Tu\u00f1\u00f3n, O., Marnet, L.R., Aubard, M., Antal, L., Costa, M., and Brodskiy, Y. (2024). SubPipe: A Submarine Pipeline Inspection Dataset for Segmentation and Visual-Inertial Localization. Proceedings of OCEANS 2024\u2013Singapore, IEEE.","DOI":"10.1109\/OCEANS51537.2024.10682150"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., and Farhadi, A. (2016). You Only Look Once: Unified, Real-Time Object Detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Varghese, R., and Sambath, M. (2024). YOLOv8: A Novel Object Detection Algorithm with Enhanced Performance and Robustness. Proceedings of the International Conference on Advances in Data Engineering and Intelligent Computing Systems, IEEE.","DOI":"10.1109\/ADICS58448.2024.10533619"},{"key":"ref_9","unstructured":"Ge, Z., Liu, S., Wang, F., Li, Z., and Sun, J. (2021). YOLOX: Exceeding YOLO Series in 2021. arXiv."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"107984","DOI":"10.52202\/079017-3429","article-title":"YOLOv10: Real-Time End-to-End Object Detection","volume":"37","author":"Wang","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"397","DOI":"10.1109\/GCIS.2009.459","article-title":"Automatic Target Detection and Analyses in Side-Scan Sonar Imagery","volume":"Volume 4","author":"Tian","year":"2009","journal-title":"Proceedings of the 2009 WRI Global Congress on Intelligent Systems"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"266","DOI":"10.1049\/iet-rsn:20060182","article-title":"Bounding the Performance of Side-Scan Sonar Automatic Target Recognition Algorithms Using Information Theory","volume":"1","author":"Myers","year":"2007","journal-title":"IET Radar Sonar Navig."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Einsidler, D., Dhanak, M., and Beaujean, P.P. (2018). A Deep Learning Approach to Target Recognition in Side-Scan Sonar Imagery. Proceedings of the OCEANS 2018 MTS\/IEEE Charleston, IEEE.","DOI":"10.1109\/OCEANS.2018.8604879"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"523","DOI":"10.1007\/s12555-019-0691-3","article-title":"Realistic Sonar Image Simulation Using Deep Learning for Underwater Object Detection","volume":"18","author":"Sung","year":"2020","journal-title":"Int. J. Control Autom. Syst."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"12618","DOI":"10.1109\/ACCESS.2024.3353688","article-title":"Underwater Target Detection Using Deep Learning: Methodologies, Challenges, Applications, and Future Evolution","volume":"12","author":"Khan","year":"2024","journal-title":"IEEE Access"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Wang, H., and Xiao, N. (2023). Underwater Object Detection Method Based on Improved Faster RCNN. Appl. Sci., 13.","DOI":"10.3390\/app13042746"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Jiang, X., Zhuang, X., Chen, J., Zhang, J., and Zhang, Y. (2024). YOLOv8-MU: An Improved YOLOv8 Underwater Detector Based on a Large Kernel Block and a Multi-Branch Reparameterization Module. Sensors, 24.","DOI":"10.20944\/preprints202404.0779.v1"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"8691","DOI":"10.1109\/ACCESS.2025.3527315","article-title":"Enhanced YOLOv10 Framework Featuring DPAM and DALSM for Real-Time Underwater Object Detection","volume":"13","author":"Sriram","year":"2025","journal-title":"IEEE Access"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"165","DOI":"10.1007\/s10462-024-10788-1","article-title":"Dynamic YOLO for Small Underwater Object Detection","volume":"57","author":"Chen","year":"2024","journal-title":"Artif. Intell. Rev."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"1178","DOI":"10.3390\/jmse11061178","article-title":"Underwater Small Target Detection Based on YOLOX Combined with MobileViT and Double Coordinate Attention","volume":"11","author":"Sun","year":"2023","journal-title":"J. Mar. Sci. Eng."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"1764","DOI":"10.3390\/jmse10111764","article-title":"B-YOLOX-S: A Lightweight Method for Underwater Object Detection Based on Data Augmentation and Multiscale Feature Fusion","volume":"10","author":"Wang","year":"2022","journal-title":"J. Mar. Sci. Eng."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Ma, Q., Jin, S., Bian, G., and Cui, Y. (2024). Multi-Scale Marine Object Detection in Side-Scan Sonar Images Based on BES-YOLO. Sensors, 24.","DOI":"10.3390\/s24144428"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Wang, W., Zhang, Q., Qi, Z., and Huang, M. (2024). CenterNet-Saccade: Enhancing Sonar Object Detection with Lightweight Global Feature Extraction. Sensors, 24.","DOI":"10.3390\/s24020665"},{"key":"ref_24","unstructured":"Hinton, G., Vinyals, O., and Dean, J. (2015). Distilling the Knowledge in a Neural Network. arXiv."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Han, K., Wang, Y., Tian, Q., Guo, J., Xu, C., and Xu, C. (2020). GhostNet: More Features from Cheap Operations. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR42600.2020.00165"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Kim, H.G., Seo, J., and Kim, S.M. (2022). Underwater Optical-Sonar Image Fusion Systems. Sensors, 22.","DOI":"10.3390\/s22218445"},{"key":"ref_27","unstructured":"Lei, C., Rajani, H., Franchi, V., Garcia, R., Gracias, N., Wang, H., and Qiang, W. (2026). Physically Motivated Knowledge Distillation for Blind Geometric Correction of Side-Scan Sonar Imagery. arXiv."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"27339","DOI":"10.1109\/ACCESS.2026.3666096","article-title":"Cross-Modality Object-Level Knowledge Distillation for Enhanced Underwater Sonar Object Detection","volume":"14","author":"Aydogmus","year":"2026","journal-title":"IEEE Access"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Bang, G., Seong, M., Kim, J., Baek, G., Oh, D., Kim, J., Koh, J., and Choi, J.W. (2025). RCTDistill: Cross-Modal Knowledge Distillation Framework for Radar-Camera 3D Object Detection with Temporal Fusion. Proceedings of the IEEE\/CVF International Conference on Computer Vision, IEEE.","DOI":"10.1109\/ICCV51701.2025.02348"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Hou, Q., Zhou, D., and Feng, J. (2021). Coordinate Attention for Efficient Mobile Network Design. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR46437.2021.01350"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Dahn, N., Firvida, M.B., Sharma, P., Christensen, L., Geisle, O., Mohrmann, J., Frey, T., Sanghamreddy, P.K., and Kirchner, F. (2024). An Acoustic and Optical Dataset for the Perception of Underwater Unexploded Ordnance. Proceedings of the OCEANS 2024 Halifax, IEEE.","DOI":"10.1109\/OCEANS55160.2024.10754316"},{"key":"ref_32","unstructured":"Aubard, M., Antal, L., Madureira, A., and \u00c1brah\u00e1m, E. (2024). Knowledge Distillation in YOLOX-ViT for Side-Scan Sonar Object Detection. arXiv."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/14\/4340\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T16:19:07Z","timestamp":1783527547000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/14\/4340"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,8]]},"references-count":32,"journal-issue":{"issue":"14","published-online":{"date-parts":[[2026,7]]}},"alternative-id":["s26144340"],"URL":"https:\/\/doi.org\/10.3390\/s26144340","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,8]]}}}