{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T05:15:02Z","timestamp":1763442902888,"version":"3.45.0"},"reference-count":38,"publisher":"MDPI AG","issue":"22","license":[{"start":{"date-parts":[[2025,11,13]],"date-time":"2025-11-13T00:00:00Z","timestamp":1762992000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Underwater object detection is critical for marine resource utilization, ecological monitoring, and maritime security, yet it remains constrained by optical degradation, high energy consumption, and vulnerability to adversarial perturbations. To address these challenges, this study proposes an Adaptive Vision Transformer (A-ViT)-based detection framework. At the hardware level, a systematic power-modeling and endurance-estimation scheme ensures feasibility across shallow- and deep-water missions. Through the super-resolution reconstruction based on the Hybrid Attention Transformer (HAT) and the staged enhancement with the Deep Initialization and Deep Inception and Channel-wise Attention Module (DICAM), the image quality was significantly improved. Specifically, the Peak Signal-to-Noise Ratio (PSNR) increased by 74.8%, and the Structural Similarity Index (SSIM) improved by 375.8%. Furthermore, the Underwater Image Quality Measure (UIQM) rose from 3.00 to 3.85, while the Underwater Color Image Quality Evaluation (UCIQE) increased from 0.550 to 0.673, demonstrating substantial enhancement in both visual fidelity and color consistency. Detection accuracy is further enhanced by an improved YOLOv11-Coordinate Attention\u2013High-order Spatial Feature Pyramid Network (YOLOv11-CA_HSFPN), which attains a mean Average Precision at Intersection over Union 0.5 (mAP@0.5) of 56.2%, exceeding the baseline YOLOv11 by 1.5 percentage points while maintaining 10.5 ms latency. The proposed A-ViT + ROI reduces inference latency by 27.3% and memory usage by 74.6% when integrated with YOLOv11-CA_HSFPN and achieves up to 48.9% latency reduction and 80.0% VRAM savings in other detectors. An additional Image-stage Attack QuickCheck (IAQ) defense module reduces adversarial-attack-induced latency growth by 33\u201340%, effectively preventing computational overload.<\/jats:p>","DOI":"10.3390\/s25226948","type":"journal-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T14:37:52Z","timestamp":1763131072000},"page":"6948","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Energy-Efficient and Adversarially Resilient Underwater Object Detection via Adaptive Vision Transformers"],"prefix":"10.3390","volume":"25","author":[{"given":"Leqi","family":"Li","sequence":"first","affiliation":[{"name":"The School of Electronic Information and Electrical Engineering, East Campus, Yangtze University, Jingzhou 434100, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gengpei","family":"Zhang","sequence":"additional","affiliation":[{"name":"The School of Electronic Information and Electrical Engineering, East Campus, Yangtze University, Jingzhou 434100, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yongqian","family":"Zhou","sequence":"additional","affiliation":[{"name":"The School of Electronic Information and Electrical Engineering, East Campus, Yangtze University, Jingzhou 434100, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2025,11,13]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"3458","DOI":"10.1109\/TCAD.2020.3012745","article-title":"Energy-efficient image recognition system for marine life","volume":"39","author":"Demir","year":"2020","journal-title":"IEEE Trans. Comput. Aided Des. Integr. Circuits Syst."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Kesari Mary, D.R., Ko, E., Yoon, D.J., Shin, S.Y., and Park, S.H. (2022). Energy optimization techniques in underwater internet of things: Issues, state-of-the-art, and future directions. Water, 14.","DOI":"10.3390\/w14203240"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"127585","DOI":"10.1016\/j.neucom.2024.127585","article-title":"DICAM: Deep inception and channel-wise attention modules for underwater image enhancement","volume":"584","author":"Tolie","year":"2024","journal-title":"Neurocomputing"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"3227","DOI":"10.1109\/LRA.2020.2974710","article-title":"Fast underwater image enhancement for improved visual perception","volume":"5","author":"Islam","year":"2020","journal-title":"IEEE Robot. Autom. Lett."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Liu, B., Yang, Y., Zhao, M., and Hu, M. (2024). A novel lightweight model for underwater image enhancement. Sensors, 24.","DOI":"10.3390\/s24103070"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Sarala, A., and Vinoth kumar, C. (2025). A cutting-edge ensemble model for enhanced underwater image restoration and quality improvement. Sci. Rep., 15.","DOI":"10.1038\/s41598-025-96832-8"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Kahveci, S., and Avaro\u011flu, E. (2025). An Adaptive Underwater Image Enhancement Framework Combining Structural Detail Enhancement and Unsupervised Deep Fusion. Appl. Sci., 15.","DOI":"10.3390\/app15147883"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Chen, W., Lei, Y., Luo, S., Zhou, Z., Li, M., and Pun, C.M. (July, January 30). Uwformer: Underwater image enhancement via a semi-supervised multi-scale transformer. Proceedings of the 2024 International Joint Conference on Neural Networks (IJCNN), Yokohama, Japan.","DOI":"10.1109\/IJCNN60899.2024.10651366"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"77","DOI":"10.1016\/j.cag.2023.01.009","article-title":"UDAformer: Underwater image enhancement based on dual attention transformer","volume":"111","author":"Shen","year":"2023","journal-title":"Comput. Graph."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Girshick, R. (2015, January 7\u201313). Fast r-cnn. Proceedings of the IEEE International Conference on Computer Vision, Santiago, Chile.","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"277","DOI":"10.1007\/s10462-025-11284-w","article-title":"Comprehensive review of recent developments in visual object detection based on deep learning","volume":"58","author":"Edozie","year":"2025","journal-title":"Artif. Intell. Rev."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1007\/s44295-024-00023-6","article-title":"Underwater object detection and datasets: A survey","volume":"2","author":"Jian","year":"2024","journal-title":"Intell. Mar. Technol. Syst."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Cai, S., Zhang, X., and Mo, Y. (2024). A Lightweight underwater detector enhanced by Attention mechanism, GSConv and WIoU on YOLOv8. Sci. Rep., 14.","DOI":"10.1038\/s41598-024-75809-z"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"108926","DOI":"10.1016\/j.patcog.2022.108926","article-title":"SWIPENET: Object detection in noisy underwater scenes","volume":"132","author":"Chen","year":"2022","journal-title":"Pattern Recognit."},{"key":"ref_15","first-page":"5635809","article-title":"U-decn: End-to-end underwater object detection convnet with improved denoising training","volume":"63","author":"Liu","year":"2025","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_16","unstructured":"Gu, X., Tang, S., Cao, Y., and Yu, C. (2025). Underwater object detection in sonar imagery with detection transformer and Zero-shot neural architecture search. arXiv."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"123253","DOI":"10.1016\/j.eswa.2024.123253","article-title":"PE-Transformer: Path enhanced transformer for improving underwater object detection","volume":"246","author":"Gao","year":"2024","journal-title":"Expert Syst. Appl."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Sun, W., Liu, X., Hao, J., Yao, Q., Xi, H., Wu, Y., and Xing, Z. (2025). AGS-YOLO: An Efficient Underwater Small-Object Detection Network for Low-Resource Environments. J. Mar. Sci. Eng., 13.","DOI":"10.3390\/jmse13081465"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Li, X., Zhao, Y., Su, H., Wang, Y., and Chen, G. (2025). Efficient underwater object detection based on feature enhancement and attention detection head. Sci. Rep., 15.","DOI":"10.1038\/s41598-025-89421-2"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Chen, L., Huang, Y., Dong, J., Xu, Q., Kwong, S., Lu, H., Lu, H., and Li, C. (2024). Underwater object detection in the era of artificial intelligence: Current, challenge, and future. arXiv.","DOI":"10.1145\/3759243"},{"key":"ref_21","unstructured":"Dosovitskiy, A. (2020). An image is worth 16x16 words: Transformers for image recognition at scale. arXiv."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Lu, Y., and Sun, M. (2025). Lightweight multidimensional feature enhancement algorithm LPS-YOLO for UAV remote sensing target detection. Sci. Rep., 15.","DOI":"10.1038\/s41598-025-85488-z"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Setyawan, N., Sun, C.C., Hsu, M.H., Kuo, W.K., and Hsieh, J.W. (2025, January 25\u201328). MicroViT: A vision transformer with low complexity self attention for edge device. Proceedings of the 2025 IEEE International Symposium on Circuits and Systems (ISCAS), London, UK.","DOI":"10.1109\/ISCAS56072.2025.11043206"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Cai, S., Zhou, X., Cai, W., Wei, L., and Mo, Y. (2025). Lightweight underwater object detection method based on multi-scale edge information selection. Sci. Rep., 15.","DOI":"10.1038\/s41598-025-13566-3"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Chen, G., Mao, Z., Wang, K., and Shen, J. (2023). HTDet: A hybrid transformer-based approach for underwater small object detection. Remote Sens., 15.","DOI":"10.3390\/rs15041076"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Fathy, M.E., Mohamed, S.A., Awad, M.I., and Abd El Munim, H.E. (2025). A vision transformer based CNN for underwater image enhancement ViTClarityNet. Sci. Rep., 15.","DOI":"10.1038\/s41598-025-91212-8"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Lei, J., Wang, H., Lei, Z., Li, J., and Rong, S. (2025). CNN\u2013Transformer Hybrid Architecture for Underwater Sonar Image Segmentation. Remote Sens., 17.","DOI":"10.3390\/rs17040707"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Mao, X., Qi, G., Chen, Y., Li, X., Duan, R., Ye, S., He, Y., and Xue, H. (2022, January 18\u201324). Towards robust vision transformer. Proceedings of the IEEE\/CVF conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA.","DOI":"10.1109\/CVPR52688.2022.01173"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"35367","DOI":"10.1109\/JIOT.2025.3580194","article-title":"Vision Transformer with Adversarial Indicator Token against Adversarial Attacks in Radio Signal Classifications","volume":"12","author":"Zhang","year":"2025","journal-title":"IEEE Internet Things J."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Kurakin, A., Goodfellow, I.J., and Bengio, S. (2018). Adversarial Examples in the physical world. Artificial Intelligence Safety and Security, Chapman and Hall\/CRC.","DOI":"10.1201\/9781351251389-8"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Mahmood, K., Mahmood, R., and Van Dijk, M. (2021, January 11\u201317). On the robustness of vision transformers to adversarial examples. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Montreal, BC, Canada.","DOI":"10.1109\/ICCV48922.2021.00774"},{"key":"ref_32","unstructured":"Islam, C.M., Chacko, S.J., Nishino, M., and Liu, X. (2025). Mechanistic understandings of representation vulnerabilities and engineering robust vision transformers. arXiv."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"7736","DOI":"10.1109\/TITS.2023.3236016","article-title":"Multi-relay cognitive network with anti-fragile relay communication for intelligent transportation system under aggregated interference","volume":"24","author":"Ji","year":"2023","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"130417","DOI":"10.1016\/j.neucom.2025.130417","article-title":"Vision transformers on the edge: A comprehensive survey of model compression and acceleration strategies","volume":"643","author":"Saha","year":"2025","journal-title":"Neurocomputing"},{"key":"ref_35","unstructured":"Chen, X., Wang, X., Zhang, W., Kong, X., Qiao, Y., Zhou, J., and Dong, C. (2023). Hat: Hybrid attention transformer for image restoration. arXiv."},{"key":"ref_36","first-page":"13937","article-title":"Dynamicvit: Efficient vision transformers with dynamic token sparsification","volume":"34","author":"Rao","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_37","unstructured":"Bolya, D., Fu, C.Y., Dai, X., Zhang, P., Feichtenhofer, C., and Hoffman, J. (2022). Token merging: Your vit but faster. arXiv."},{"key":"ref_38","unstructured":"Fu, J., Jiang, K., Hong, L., Li, J., Guo, H., Yang, D., Chen, Z., and Zhang, W. (2025). LingoLoop Attack: Trapping MLLMs via Linguistic Context and State Entrapment into Endless Loops. arXiv."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/25\/22\/6948\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T05:11:30Z","timestamp":1763442690000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/25\/22\/6948"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,13]]},"references-count":38,"journal-issue":{"issue":"22","published-online":{"date-parts":[[2025,11]]}},"alternative-id":["s25226948"],"URL":"https:\/\/doi.org\/10.3390\/s25226948","relation":{},"ISSN":["1424-8220"],"issn-type":[{"type":"electronic","value":"1424-8220"}],"subject":[],"published":{"date-parts":[[2025,11,13]]}}}