{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T11:56:03Z","timestamp":1782474963070,"version":"3.54.5"},"reference-count":45,"publisher":"MDPI AG","issue":"9","license":[{"start":{"date-parts":[[2025,9,13]],"date-time":"2025-09-13T00:00:00Z","timestamp":1757721600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Symmetry"],"abstract":"<jats:p>This paper proposes IFEM-YOLOv13, a high-precision underwater target detection method designed to address challenges such as image degradation, low contrast, and small target obscurity caused by light attenuation, scattering, and biofouling. Its core innovation is an end-to-end degradation-aware system featuring: (1) an Intelligent Feature Enhancement Module (IFEM) that employs learnable sharpening and pixel-level filtering for adaptive optical compensation, incorporating principles of symmetry in its multi-branch enhancement to balance color and structural recovery; (2) a degradation-aware Focal Loss incorporating dynamic gradient remapping and class balancing to mitigate sample imbalance through symmetry-preserving optimization; and (3) a cross-layer feature association mechanism for multi-scale contextual modeling that respects the inherent scale symmetry of natural objects. Evaluated on the J-EDI dataset, IFEM-YOLOv13 achieves 98.6% mAP@0.5 and 82.1% mAP@0.5:0.95, outperforming the baseline YOLOv13 by 0.7% and 3.0%, respectively. With only 2.5 M parameters and operating at 217 FPS, it surpasses methods including Faster R-CNN, YOLO variants, and RE-DETR. These results demonstrate its robust real-time detection capability for diverse underwater targets such as plastic debris, biofouled objects, and artificial structures, while effectively handling the symmetry-breaking distortions introduced by the underwater environment.<\/jats:p>","DOI":"10.3390\/sym17091531","type":"journal-article","created":{"date-parts":[[2025,9,15]],"date-time":"2025-09-15T07:56:51Z","timestamp":1757923011000},"page":"1531","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Balancing Feature Symmetry: IFEM-YOLOv13 for Robust Underwater Object Detection Under Degradation"],"prefix":"10.3390","volume":"17","author":[{"given":"Zhen","family":"Feng","sequence":"first","affiliation":[{"name":"Mechanical Engineering, Jiangsu University of Science and Technology, Zhenjiang 212003, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fanghua","family":"Liu","sequence":"additional","affiliation":[{"name":"Mechanical Engineering, Jiangsu University of Science and Technology, Zhenjiang 212003, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2025,9,13]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"134254","DOI":"10.1016\/j.scitotenv.2019.134254","article-title":"Micro- and nano-plastics in marine environment: Source, distribution and threats\u2014A review","volume":"698","author":"Peng","year":"2020","journal-title":"Sci. Total Environ."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"103846","DOI":"10.1016\/j.advwatres.2021.103846","article-title":"Simulating water and heat transport with freezing and cryosuction in unsaturated soil: Comparing an empirical, semi-empirical and physically-based approach","volume":"149","author":"Stuurop","year":"2021","journal-title":"Adv. Water Resour."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"116426","DOI":"10.1016\/j.envpol.2021.116426","article-title":"Nanoplastics impact on marine biota: A review","volume":"273","author":"Bebianno","year":"2021","journal-title":"Environ. Pollut."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Jiang, Z., Wu, B., Ma, L., Zhang, H., and Lian, J. (2024). Apm-yolov7 for small-target water-floating garbage detection based on multi-scale feature adaptive weighted fusion. Sensors, 24.","DOI":"10.3390\/s24010050"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Ho, C.-C., Tai, L.-L., and Su, E. (2022). Deep-Learning-Based Surface Texture Feature Simulation for Surface Defect Inspection. Symmetry, 14.","DOI":"10.3390\/sym14071465"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"48","DOI":"10.1038\/s41586-020-2643-8","article-title":"Floating under a levitating liquid","volume":"585","author":"Apffel","year":"2020","journal-title":"Nature"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Chen, H., Chen, Z., and Yu, H. (2023). Enhanced yolov5: An efficient road object detection method. Sensors, 23.","DOI":"10.3390\/s23208355"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Han, C., Meng, Q., Chen, J., Cui, L., Xue, J., Liu, H., and Yan, R. (2025). Variations in Soil Salt Ions and Salinization Degree in Shallow Groundwater Areas During the Freeze\u2013Thaw Period. Water, 17.","DOI":"10.3390\/w17152234"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"119862","DOI":"10.1016\/j.envpol.2022.119862","article-title":"Towards a North Pacific long-term monitoring program for ocean plastic pollution: A systematic review and recommendations for shorelines","volume":"310","author":"Uhrin","year":"2022","journal-title":"Environ. Pollut."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"28228","DOI":"10.1364\/OE.432900","article-title":"Underwater Image Restoration Via Feature Priors to Estimate Background Light and Optimized Transmission Map","volume":"29","author":"Jingchun","year":"2021","journal-title":"Optics Express"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Liu, Y., Wu, J., Zhao, H., Li, C., Mao, J., Zhang, R., Liu, J., and Zhao, Q. (2023). Ions transport in seasonal frozen farmland soil and its effect on soil salinization chemical properties. Agronomy, 13.","DOI":"10.3390\/agronomy13030660"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Biswas, P., Bushra, N.Z., and Shiddiki, A.H. (2024, January 7\u20138). Underwater Image Enhancement Techniques Using Sigmoid Fuzzy, Convolution and Fourier Transform method along with Histogram Equalization. Proceedings of the 2024 International Conference on Recent Progresses in Science, Engineering and Technology (ICRPSET), Rajshahi, Bangladesh.","DOI":"10.1109\/ICRPSET64863.2024.10955817"},{"key":"ref_13","unstructured":"Redmon, J., and Farhadi, A. (2018). Yolov3: An incremental improvement. arXiv."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"5738","DOI":"10.1109\/TNNLS.2020.3027468","article-title":"An Occlusion Compensation Learning Framework for Improving the Rendering Quality of Light Field","volume":"32","author":"Zhu","year":"2021","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref_15","first-page":"811","article-title":"Lightweight algorithm for detecting fishing boats in offshore aquaculture areas based on yolov7-tiny","volume":"19","author":"Peng","year":"2025","journal-title":"KSII Trans. Internet Inf. Syst."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1145\/3528223.3530185","article-title":"Seeing through obstructions with diffractive cloaking","volume":"41","author":"Shi","year":"2022","journal-title":"ACM Trans. Graph."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"105440","DOI":"10.1016\/j.psj.2025.105440","article-title":"Deep learning in poultry farming: Comparative analysis of yolov8, yolov9, yolov10, and yolov11 for dead chickens detection","volume":"104","author":"Umurungi","year":"2025","journal-title":"Poult. Sci."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Wang, B., Kang, Z., Dong, P., Wang, F., Ma, P., Bai, J., Liang, P., and Li, C. (2023). Underwater Image Enhancement by Maximum-Likelihood Based Adaptive Color Correction and Robust Scattering Removal. Front. Comput. Sci., 17.","DOI":"10.1007\/s11704-022-1205-7"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Jinghui, Y., Zhuang, Z., Dujuan, Z., Binghua, S., Xuanyuan, Z., Jialin, T., Yunting, L., Jiongjiang, C., and Wanxin, L. (2022). Underwater Object Detection Algorithm Based on Attention Mechanism and Cross-Stage Partial Fast Spatial Pyramidal Pooling. Front. Mar. Sci., 9.","DOI":"10.3389\/fmars.2022.1056300"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"2501","DOI":"10.3390\/rs12152501","article-title":"YOLO-Fine: One-Stage Detector of Small Objects under Various Backgrounds in Remote Sensing Images","volume":"12","author":"Luc","year":"2020","journal-title":"Remote Sens."},{"key":"ref_21","first-page":"6008705","article-title":"YOLO-DA: An Efficient YOLO-Based Detector for Remote Sensing Object Detection","volume":"20","author":"Jiehua","year":"2023","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_22","first-page":"41","article-title":"SLD-Net: A seabed garbage detection algorithm based on lightweight network","volume":"40","author":"Zhou","year":"2024","journal-title":"J. Hubei Polytech. Univ."},{"key":"ref_23","first-page":"108","article-title":"Small target biological detection based on self-attention mechanism and improved YOLOv5s","volume":"50","author":"Qi","year":"2024","journal-title":"J. Hunan Agric. Univ. (Nat. Sci. Ed.)"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Li, H., Yang, S., Zhang, R., Yu, P., Fu, Z., Wang, X., Kadoch, M., and Yang, Y. (2024). Detection of Floating Objects on Water Surface Using YOLOv5s in an Edge Computing Environment. Water, 16.","DOI":"10.3390\/w16010086"},{"key":"ref_25","first-page":"484","article-title":"Lightweight infrared image enhancement network based on generative adversarial networks","volume":"40","author":"Cheng","year":"2024","journal-title":"Signal Process."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"104722","DOI":"10.1016\/j.dsp.2024.104722","article-title":"SwiftWater: A lightweight SwiftFormer-based underwater image enhancement network with auxiliary prompt module","volume":"155","author":"Zhao","year":"2024","journal-title":"Digit. Signal Process."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"18335","DOI":"10.1109\/JIOT.2024.3361938","article-title":"A Feature-Enhanced and Adaptive Routing Framework for Fish School Detection on AUVs for Degraded Underwater Imaging Environments","volume":"11","author":"Jiang","year":"2024","journal-title":"IEEE Internet Things J."},{"key":"ref_28","first-page":"4240","article-title":"YOLO-MS: Rethinking Multi-Scale Representation Learning for Real-time Object Detection","volume":"47","author":"Chen","year":"2025","journal-title":"Comput. Res. Repos."},{"key":"ref_29","unstructured":"Lei, M.Q., Li, S.Q., Wu, Y.H., Hu, H., Zhou, Y., Zheng, X.H., Ding, G.G., Du, S.Y., Wu, Z.Z., and Gao, Y. (2025). YOLOv13: Real-Time Object Detection with Hypergraph-Enhanced Adaptive Visual Perception. arXiv."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"103900","DOI":"10.1016\/j.dsp.2022.103900","article-title":"Underwater Image Restoration for Seafloor Targets with Hybrid Attention Mechanisms and Conditional Generative Adversarial Network","volume":"134","author":"Peng","year":"2023","journal-title":"Digit. Signal Process."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"4367","DOI":"10.1007\/s10489-020-02116-1","article-title":"Image Super-Resolution Reconstruction Based on Feature Map Attention Mechanism","volume":"51","author":"Chen","year":"2021","journal-title":"Appl. Intell."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"12158","DOI":"10.1021\/acs.est.9b01424","article-title":"Global Review of Beach Debris Monitoring and Future Recommendations","volume":"53","author":"Lavers","year":"2019","journal-title":"Environ. Sci. Technol."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"112998","DOI":"10.1016\/j.marpolbul.2021.112998","article-title":"Marine Litter Pollution on Coral Reefs of Darvel Bay (east Sabah, Malaysia)","volume":"173","author":"Santodomingo","year":"2021","journal-title":"Mar. Pollut. Bull."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"425","DOI":"10.1016\/j.asoc.2019.04.025","article-title":"The Extended Marine Underwater Environment Database and Baseline Evaluations","volume":"80","author":"Jian","year":"2019","journal-title":"Appl. Soft Comput."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1038\/s41597-022-01906-1","article-title":"Image Dataset for Benchmarking Automated Fish Detection and Classification Algorithms","volume":"10","author":"Francescangeli","year":"2023","journal-title":"Sci. Data"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"114049","DOI":"10.1016\/j.marpolbul.2022.114049","article-title":"Deploying Deep Learning to Estimate the Abundance of Marine Debris from Video Footage","volume":"183","author":"Teng","year":"2022","journal-title":"Mar. Pollut. Bull."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"42","DOI":"10.1016\/j.neucom.2018.03.030","article-title":"Face detection using deep learning: An improved faster rcnn approach","volume":"299","author":"Sun","year":"2018","journal-title":"Neurocomputing"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"102007","DOI":"10.1016\/j.aei.2023.102007","article-title":"DenseSPH-YOLOv5: An automated damage detection model based on DenseNet and Swin-Transformer prediction head-enabled YOLOv5 with attention mechanism","volume":"56","author":"Roy","year":"2023","journal-title":"Adv. Eng. Inform."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"112208","DOI":"10.1016\/j.measurement.2022.112208","article-title":"Wheel hub defect detection based on the DS-Cascade RCNN","volume":"206","author":"Cheng","year":"2023","journal-title":"Measurement"},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Zhou, Z., Li, R., Gao, Y., Zhang, C., and Hei, X. (2020, January 29\u201331). SLDNet: A Branched, Spatio-Temporal Convolution Neural Network for Detecting Solid Line Driving Violation in Intelligent Transportation Systems. Proceedings of the 2020 Information Communication Technologies Conference (ICTC), Nanjing, China.","DOI":"10.1109\/ICTC49638.2020.9123284"},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.-Y., and Berg, A.C. (2016). SSD: Single Shot Multibox Detector, Springer.","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"012012","DOI":"10.1088\/1742-6596\/2906\/1\/012012","article-title":"A lightweight insulator string defect detection method based on improved yolov5","volume":"2906","author":"Gao","year":"2024","journal-title":"J. Phys. Conf. Ser."},{"key":"ref_43","first-page":"802","article-title":"Improved yolov8 for high-precision detection of rail surface defects on heavy-haul railways","volume":"34","author":"Yuan","year":"2024","journal-title":"Chin. J. Electron."},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Li, N., and Wei, D. (2025). REDETR-RISTD: Real-Time Long-Range Infrared Small Target Detection Network Based on the Reparameterized Efficient Detection Transformer. Sensors, 25.","DOI":"10.2139\/ssrn.5079458"},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"213","DOI":"10.1515\/cclm-2022-0806","article-title":"Definition and Application of Performance Specifications for Measurement Uncertainty of 23 Common Laboratory Tests: Linking Theory to Daily Practice","volume":"61","author":"Braga","year":"2023","journal-title":"Clin. Chem. Lab. Med."}],"container-title":["Symmetry"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2073-8994\/17\/9\/1531\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T18:45:09Z","timestamp":1760035509000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2073-8994\/17\/9\/1531"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,13]]},"references-count":45,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2025,9]]}},"alternative-id":["sym17091531"],"URL":"https:\/\/doi.org\/10.3390\/sym17091531","relation":{},"ISSN":["2073-8994"],"issn-type":[{"value":"2073-8994","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,13]]}}}