Adaptive Enhancement and Dual-Pooling Sequential Attention for Lightweight Underwater Object Detection with YOLOv10

Md. Mushibur Rahman; Umme Fawzia Rahim; Enam Ahmed Taufik

cs.CVMar 4, 2026

Adaptive Enhancement and Dual-Pooling Sequential Attention for Lightweight Underwater Object Detection with YOLOv10

Authors: Md. Mushibur Rahman, Umme Fawzia Rahim, Enam Ahmed Taufik

Organizations: Department of Computer Science and Engineering, Dhaka University of Engineering & Technology Gazipur, 1707, Bangladesh · Department of Computer Science and Engineering, BRAC University Dhaka, Bangladesh

Abstract

Underwater object detection constitutes a pivotal endeavor within the realms of marine surveillance and autonomous underwater systems; however, it presents significant challenges due to pronounced visual impairments arising from phenomena such as light absorption, scattering, and diminished contrast. In response to these formidable challenges, this manuscript introduces a streamlined yet robust framework for underwater object detection, grounded in the YOLOv10 architecture. The proposed method integrates a Multi-Stage Adaptive Enhancement module to improve image quality, a Dual-Pooling Sequential Attention (DPSA) mechanism embedded into the backbone to strengthen multi-scale feature representation, and a Focal Generalized IoU Objectness (FGIoU) loss to jointly improve localization accuracy and objectness prediction under class imbalance. Comprehensive experimental evaluations conducted on the RUOD and DUO benchmark datasets substantiate that the proposed DPSA_FGIoU_YOLOv10n attains exceptional performance, achieving mean Average Precision (mAP) scores of 88.9% and 88.0% at IoU threshold 0.5, respectively. In comparison to the baseline YOLOv10n, this represents enhancements of 6.7% for RUOD and 6.2% for DUO, all while preserving a compact model architecture comprising merely 2.8M parameters. These findings validate that the proposed framework establishes an efficacious equilibrium among accuracy, robustness, and real-time operational efficiency, making it suitable for deployment in resource-constrained underwater settings.

Figures & tables

Fig. 1: Distribution of samples across object categories in the datasets: (a) RUOD dataset and (b) DUO dataset.

Fig. 2: Structure of MAE-UVP enhancement module.

Fig. 3: Proposed YOLOv10 architecture with SPPF replaced by DPSA_SPPF in the backbone and modified detection head.

Dataset	Method	DPSA_SPPF	FGIoU Loss	mAP50 (%)	mAP50:95 (%)
RUOD	YOLOv10n	–	–	82.2	58.8
	YOLOv10n	Yes	–	88.3 (+6.1)	65.1 (+6.3)
	YOLOv10n	–	Yes	88.0 (+5.8)	64.9 (+6.1)
	YOLOv10n	Yes	Yes	88.9 (+6.7)	66.5 (+7.7)
DUO	YOLOv10n	–	–	81.8	63.5
	YOLOv10n	Yes	–	85.7 (+3.9)	66.4 (+2.9)

TABLE I: Experimental comparison with the baseline model.

Model	RUOD Dataset				DUO Dataset				Parameters
	Prec. %	Rec. %	[email protected] %	[email protected]–0.95 %	Prec. %	Rec. %	[email protected] %	[email protected]–0.95 %
YOLOv8n	83.8	75.0	82.6	58.4	81.9	75.7	82.7	64.1	3.1M
YOLOv8s	85.7	78.5	85.6	61.4	86.5	76.7	83.4	67.0	11.1M
YOLOv8m	85.6	77.9	85.8	62.1	85.7	76.8	83.4	68.4	25.8M
YOLOv9t	84.1	75.1	82.4	59.0	86.5	77.6	85.5	66.4	2.01M
YOLOv10n	82.3	76.0	82.2	58.8	88.3	68.4	81.8	63.5	2.7M

TABLE II: Comparison of the improved YOLOv10n variants with state-of-the-art methods for underwater object detection on the RUOD and DUO datasets

Fig. 4: Comparison of mAP@0.5 Metrics Across (a) RUOD, and (b) DUO dataset. — Fig. 4: Comparison of [email protected] Metrics Across (a) RUOD, and (b) DUO dataset.

Object Detection

Object detection locates and classifies objects in images or video, balancing localization accuracy, robustness, and inference speed.

See all 611 papers

Feb 26, 2026

SPMamba-YOLO: An Underwater Object Detection Network Based on Multi-Scale Feature Enhancement and Global Context Modeling

Underwater object detection is a critical yet challenging research problem owing to severe light attenuation, color distortion, background clutter, and the small scale of underwater targets. To address these challenges, we propose SPMamba-YOLO, a novel underwater object detection network that integrates multi-scale feature enhancement with global context modeling. Specifically, a Spatial Pyramid Pooling Enhanced Layer Aggregation Network (SPPELAN) module is introduced to strengthen multi-scale feature aggregation and expand the receptive field, while a Pyramid Split Attention (PSA) mechanism enhances feature discrimination by emphasizing informative regions and suppressing background interference. In addition, a Mamba-based state space modeling module is incorporated to efficiently capture long-range dependencies and global contextual information, thereby improving detection robustness in complex underwater environments. Extensive experiments on the URPC2022 dataset demonstrate that SPMamba-YOLO outperforms the YOLOv8n baseline by more than 4.9% in [email protected], particularly for small and densely distributed underwater objects, while maintaining a favorable balance between detection accuracy and computational cost.

Guanghao Liao, Zhen Liu, Liyuan Cao +2

School of Electronic and Information Engineering, University of Science and Technology Liaoning, Anshan, 114051, China

Underwater Object Detection Efficient Object Detection Small Object Detection

Ask PDF

Jun 14, 2026

A Dual-Branch Collaborative Framework for Joint Optimization of Underwater Image Enhancement and Object Detection

Due to wavelength dependent light absorption and scattering, underwater images usually suffer from color distortion and blurred details, which limits underwater object detection performance. Existing underwater image enhancement methods mainly focus on visual quality improvement, while it is still difficult to balance enhancement quality, processing efficiency, and downstream detection performance. Therefore, this paper proposes an efficient dual-branch underwater image enhancement framework for object detection. The detail enhancement branch improves brightness and local contrast to recover texture details in dark regions. The color restoration branch uses adaptive compensation to reduce color distortion and improve color gradation. By combining the complementary outputs of the two branches, the proposed framework provides clearer and more informative images for object detection. On the UIEB and EUVP datasets, the proposed method achieves UIQM scores of 2.249 and 2.576. When applied to the YOLOv8 detection task on the URPC dataset, the proposed method improves mAP50 by 2.1% compared with the baseline. Extensive experiments show that our method improves object detection in complex underwater scenes, while balancing enhancement quality and processing efficiency.

Liyuan Cao, Zheng Liu, Guanghao Liao +2

School of Electronic and Information Engineering, University of Science and Technology Liaoning, No.189 Qianshan Middle Road, Lishan District, Anshan, 114051, Liaoning, China

Underwater Image Enhancement Underwater Imaging Underwater Object Detection

Ask PDF

Apr 23, 2026

A Probabilistic Framework for Improving Dense Object Detection in Underwater Image Data via Annealing-Based Data Augmentation

Object detection models typically perform well on images captured in controlled environments with stable lighting, water clarity, and viewpoint, but their performance degrades substantially in real-world underwater settings characterized by high variability and frequent occlusions. In this work, we address these challenges by introducing a novel data augmentation framework designed to improve robustness in dense and unconstrained underwater scenes. Using the DeepFish dataset, which contains images of fish in natural environments, we first generate bounding box annotations from provided segmentation masks to construct a custom detection dataset. We then propose a pseudo-simulated annealing-based augmentation algorithm, inspired by the copy-paste strategy of Deng et al. [1], to synthesize realistic crowded fish scenarios. Our approach improves spatial diversity and object density during training, enabling better generalization to complex scenes. Experimental results show that our method significantly outperforms a baseline YOLOv10 model, particularly on a challenging test set of manually annotated images collected from live-stream footage in the Florida Keys. These results demonstrate the effectiveness of our augmentation strategy for improving detection performance in dense, real-world underwater environments.

Eleanor Wiesler, Trace Baxley

Harvard Department of Mathematics. · Harvard Department of Computer Science.

Synthetic Data Augmentation Data Augmentation Object Detection Underwater Object Detection

Ask PDF

Abstract

Object Detection

Explore similar work

SPMamba-YOLO: An Underwater Object Detection Network Based on Multi-Scale Feature Enhancement and Global Context Modeling

A Dual-Branch Collaborative Framework for Joint Optimization of Underwater Image Enhancement and Object Detection

A Probabilistic Framework for Improving Dense Object Detection in Underwater Image Data via Annealing-Based Data Augmentation