TIBER-YOLO: an improved lightweight model for underwater object detection

Abstract

This study presents TRACON + Inner-WIoU + BiFPN + EMPC-DetectoR (TIBER-YOLO), an improved lightweight detector for underwater object detection. Built on You Only Look Once version 8 small (YOLOv8s), the model introduces four modifications to address image degradation, small-object detection, and computational cost. First, the Triple attention Receptive-field Attention CONvolution (TRACON) module combines a triplet attention mechanism (TAM) with receptive-field attention convolution (RFAConv) to strengthen feature extraction, particularly for small targets. Second, we design inner wise intersection over union (Inner-WIoU) by integrating Inner-IoU and WIoU-v3 to improve localization accuracy and generalization. Third, a bidirectional feature pyramid network (BiFPN) improves multiscale feature fusion while reducing the number of model parameters. Finally, the efficient multiscale partial convolution detector (EMPC-Detector) combines efficient multiscale convolution (EMSConv) and partial convolution (PConv) to capture fine-grained details with lower computational complexity. TIBER-YOLO achieves mAP@0.5 scores of 87.1%, 86.0%, and 86.1% on the DUO, UTDAC2020, and RUOD datasets, respectively. Compared with the YOLOv8s baseline, it reduces model size, parameter count, and computational demand by 40.4%, 42.3%, and 28.2%, respectively.

Keywords

Underwater target detection / Receptive-field attention convolution (RFAConv) / Bidirectional feature pyramid network (BiFPN) / Triple attention mechanism / Inner wise intersection over union (Inner-WIoU) / Efficient multiscale partial convolution detector (EMPC-Detector)

References

[1] Afif M, Ayachi R, Said Y, Pissaloux E, Atri M. An evaluation of RetinaNet on indoor object detection for blind and visually impaired persons assistance navigation. Neural Process Lett, 2020, 51: 2265-2279

[2] Bhalla S, Kumar A, Kushwaha R. Analysis of recent techniques in marine object detection: a review. Multimed Tools Appl, 2025, 84: 20339-20437

[3] Chen J, Er MJ. Dynamic YOLO for small underwater object detection. Artif Intell Rev, 2024, 57: 165

[4] Chen JR, Kao SH, He H, Zhuo WP, Wen S, Lee CH et al (2023) Run, don’t walk: chasing higher FLOPS for faster neural networks. In: 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, pp 12021–12031. https://doi.org/10.1109/CVPR52729.2023.01157

[5] Chiley V, Thangarasa V, Gupta A, Samar A, Hestness J, DeCoste D (2023) RevBiFPN: the fully reversible bidirectional feature pyramid network. In: Proceedings of the 6th Machine Learning and Systems. IEEE, pp 1–21

[6] Cui JR, Liu HL, Zhong HW, Huang C, Zhang WF. Lightweight Transformers make strong encoders for underwater object detection. Signal Image Video Process, 2023, 17: 1889-1896

[7] Dalal N, Triggs B (2005) Histograms of oriented gradients for human detection. In: 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’05). IEEE, pp 886–893. https://doi.org/10.1109/CVPR.2005.177

[8] Felzenszwalb P, McAllester D, Ramanan D (2008) A discriminatively trained, multiscale, deformable part model. In: 26th IEEE Conference on Computer Vision and Pattern Recognition. IEEE, pp 1–8. https://doi.org/10.1109/CVPR.2008.4587597

[9] Fu CP, Liu RS, Fan X, Chen PY, Fu H, Yuan WQ, et al.. Rethinking general underwater object detection: datasets, challenges, and solutions. Neurocomputing, 2023, 517: 243-256

[10] Guo A, Sun KQ, Zhang ZY. A lightweight YOLOv8 integrating FasterNet for real-time underwater object detection. J Real-Time Image Process, 2024, 21: 49

[11] Guo X, Zhao JH, Casanovas P, Graham S, Hopkins G, Xue B et al (2025) Deep learning-based crab classification for marine pest monitoring. In: 2025 40th International Conference on Image and Vision Computing New Zealand (IVCNZ). IEEE, pp 1–6. https://doi.org/10.1109/IVCNZ67716.2025.11281857

[12] Hua X, Cui XP, Xu XH, Qiu SH, Liang YJ, Bao XQ, et al.. Underwater object detection algorithm based on feature enhancement and progressive dynamic aggregation strategy. Pattern Recognit, 2023, 139: 109511

[13] Joshi R, Usmani K, Krishnan G, Blackmon F, Javidi B. Underwater object detection and temporal signal detection in turbid water using 3D-integral imaging and deep learning. Opt Express, 2024, 32: 1789-1801

[14] Khan A, Fouda MM, Do DT, Almaleh A, Alqahtani AM, Rahman AU. Underwater target detection using deep learning: methodologies, challenges, applications, and future evolution. IEEE Access, 2024, 12: 12618-12635

[15] Li L, Li YP, Yue CH, Xu GP, Wang HL, Feng XS. Real-time underwater target detection for AUV using side scan sonar images based on deep learning. Appl Ocean Res, 2023, 138: 103630

[16] Li ZM, Zheng B, Chao D, Zhu WB, Li HB, Duan J, et al.. Underwater-Yolo: underwater object detection network with dilated deformable convolutions and dual-branch occlusion attention mechanism. J Mar Sci Eng, 2024, 12: 2291

[17] Lin TY, Dollár P, Girshick R, He KM, Hariharan B, Belongie S (2017) Feature pyramid networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, pp 936–944. https://doi.org/10.1109/CVPR.2017.106

[18] Liu K, Peng L, Tang SR. Underwater object detection using TC-YOLO with attention mechanisms. Sensors, 2023, 23: 2567

[19] Liu S, Qi L, Qin HF, Shi JP, Jia JY (2018) Path aggregation network for instance segmentation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. IEEE, pp 8759–8768

[20] Liu W, Anguelov D, Erhan D, Szegedy C, Reed S, Fu CY et al (2016) SSD: single shot MultiBox detector. In: Computer Vision–ECCV 2016: 14th European Conference. Springer, Amsterdam, pp 21–37. https://doi.org/10.1007/978-3-319-46448-0_2

[21] Lu YY, Zhang JJ, Chen QL, Xu CJ, Irfan M, Chen Z. AquaYOLO: enhancing YOLOv8 for accurate underwater object detection for sonar images. J Mar Sci Eng, 2025, 13: 73

[22] Misra D, Nalamada T, Arasanipalai AU, Hou QB (2021) Rotate to attend: convolutional triplet attention module. In: 2021 IEEE Winter Conference on Applications of Computer Vision, WACV 2021. IEEE, pp 3138–3147. https://doi.org/10.1109/WACV48630.2021.00318

[23] Praveen RVS, Maindola M, Anandhi RJ, Thandra N, Bansal S, Sharma V (2025) Deep learning techniques for object detection in underwater environments. In: 2025 International Conference on Computational, Communication and Information Technology (ICCCIT). IEEE, pp 595–600. https://doi.org/10.1109/ICCCIT62592.2025.10928054

[24] Priyadharshini G, Judie Dolly DR (2023) Comparative investigations on tomato leaf disease detection and classification using CNN, R-CNN, fast R-CNN and faster R-CNN. In: 2023 9th International Conference on Advanced Computing and Communication Systems (ICACCS). IEEE, pp 1540–1545. https://doi.org/10.1109/ICACCS57279.2023.10112860

[25] Qin P, Cai YL, Liu J, Fan PR, Sun MH. Multilayer feature extraction network for military ship detection from high-resolution optical remote sensing images. IEEE J Sel Top Appl Earth Obs Remote Sens, 2021, 14: 11058-11069

[26] Redmon J, Divvala S, Girshick R, Farhadi A (2016) You only look once: unified, real-time object detection. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. IEEE, pp 779–788. https://doi.org/10.1109/CVPR.2016.91

[27] Redmon J, Farhadi A (2018) YOLOv3: an incremental improvement. Preprint at arXiv:1804.02767

[28] Ren PZ, Xiao Y, Chang XJ, Huang PY, Li ZH, Chen XJ, et al.. A comprehensive survey of neural architecture search: challenges and solutions. ACM Comput Surv, 2021, 54: 76

[29] Selvaraju RR, Cogswell M, Das A, Vedantam R, Parikh D, Batra D (2017) Grad-CAM: visual explanations from deep networks via gradient-based localization. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV). IEEE, pp 618–626. https://doi.org/10.1109/ICCV.2017.74

[30] Sun K, Zheng YJ, Yang XB, Chen XY, Jia WK. Semi-supervised breast cancer pathology image segmentation based on fine-grained classification guidance. Med Biol Eng Comput, 2024, 62: 901-912

[31] Tan MX, Pang RM, Le QV (2020) EfficientDet: scalable and efficient object detection. In: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, pp 10778–10787. https://doi.org/10.1109/CVPR42600.2020.01079

[32] Terven J, Córdova-Esparaza DM, Romero-González JA. A comprehensive review of YOLO: from YOLOv1 to YOLOv8 and YOLO-NAS. Mach Learn Knowl Extr, 2023, 5: 1680-1716

[33] Tong ZJ, Chen YH, Xu ZW, Yu R (2023) Wise-IoU: bounding box regression loss with dynamic focusing mechanism. Preprint at arXiv:2301.10051

[34] Viola P, Jones M (2001) Rapid object detection using a boosted cascade of simple features. In: IEEE Conference on Computer Vision and Pattern Recognition. IEEE, pp I-511–I-518. https://doi.org/10.1109/CVPR.2001.990517

[35] Wei YF, Tao J, Wu WJ, Yuan DH, Hou SZ. RHS-YOLOv8: a lightweight underwater small object detection algorithm based on improved YOLOv8. Appl Sci, 2025, 15: 3778

[36] Wu CM, Sun YQ, Wang TJ, Liu YL. Underwater trash detection algorithm based on improved YOLOv5s. J Real-Time Image Process, 2022, 19: 911-920

[37] Wu QQ, Cen LH, Kan SC, Zhai YP, Chen XF, Zhang H. Real-time underwater target detection based on improved YOLOv7. J Real-Time Image Process, 2025, 22: 43

[38] Xiao ZH, Li ZP, Li HH, Li MT, Liu XY, Kong YY. Multi-scale feature fusion enhancement for underwater object detection. Sensors, 2024, 24: 7201

[39] Yan PP, Qi XM, Jiang L. LI-YOLOv8: lightweight small target detection algorithm for remote sensing images that combines GSConv and PConv. PLoS ONE, 2025, 20: e0321026

[40] Yang L, Noh T. YOLOv8-UW: innovative real-time algorithm for underwater object detection. Signal Image Video Process, 2025, 19: 539

[41] Yang Q, Meng HJ, Gao YC, Gao DX. A real-time object detection method for underwater complex environments based on FasterNet-YOLOv7. J Real-Time Image Process, 2024, 21: 8

[42] Yi DW, Ahmedov HB, Jiang SY, Li YR, Flinn SJ, Fernandes PG. Coordinate-aware mask R-CNN with group normalization: a underwater marine animal instance segmentation framework. Neurocomputing, 2024, 583: 127488

[43] Zeng LC, Sun B, Zhu DQ. Underwater target detection based on Faster R-CNN and adversarial occlusion network. Eng Appl Artif Intell, 2021, 100: 104190

[44] Zhang DH, Wang DC, Yu CC, Hao XY, Liang LL. EB-Net: an efficient balanced network for accuracy and speed of remote sensing detection. Int J Remote Sens, 2024, 45: 3201-3230

[45] Zhang H, Xu C, Zhang S (2023a) Inner-IoU: more effective intersection over union loss with auxiliary bounding box. Preprint at arXiv:2311.02877

[46] Zhang X, Liu C, Song TT, Yang DG, Ye YC, Li K et al (2023b) RFAConv: receptive-field attention convolution for improving convolutional neural networks. Preprint at arXiv:2304.03198

[47] Zheng Z, Wang P, Liu W, Li J, Ye R, Ren D (2020) Distance-IoU loss: faster and better learning for bounding box regression. In: Proceedings of the AAAI Conference on Artificial Intelligence. AAAI, pp 12993–13000. https://doi.org/10.1609/aaai.v34i07.6999

[48] Zou ZX, Chen KY, Shi ZW, Guo YH, Ye JP. Object detection in 20 years: a survey. Proc IEEE, 2023, 111: 257-276

RIGHTS & PERMISSIONS

The Author(s)