Underwater target detection is widely used in various applications such as underwater search and rescue, underwater environment monitoring, and marine resource surveying. However, the complex underwater environment, including factors such as light changes and background noise, poses a significant challenge to target detection. We propose an improved underwater target detection algorithm based on YOLOv8n to overcome these problems. Our algorithm focuses on three aspects. Firstly, we replace the original C2f module with Deformable Convnets v2 to enhance the adaptive ability of the target region in the convolution check feature map and extract the target region’s features more accurately. Secondly, we introduce SimAm, a non-parametric attention mechanism, which can deduce and assign three-dimensional attention weights without adding network parameters. Lastly, we optimize the loss function by replacing the CIoU loss function with the Wise-IoU loss function. We named our new algorithm DSW-YOLOv8n, which is an acronym of Deformable Convnets v2, SimAm, and Wise-IoU of the improved YOLOv8n(DSW-YOLOv8n). To conduct our experiments, we created our own dataset of underwater target detection for experimentation. Meanwhile, we also utilized the Pascal VOC dataset to evaluate our approach. The mAP@0.5 and mAP@0.5:0.95 of the original YOLOv8n algorithm on underwater target detection were 88.6% and 51.8%, respectively, and the DSW-YOLOv8n algorithm mAP@0.5 and mAP@0.5:0.95 can reach 91.8% and 55.9%. The original YOLOv8n algorithm was 62.2% and 45.9% mAP@0.5 and mAP@0.5:0.95 on the Pascal VOC dataset, respectively. The DSW-YOLOv8n algorithm mAP@0.5 and mAP@0.5:0.95 were 65.7% and 48.3%, respectively. The number of parameters of the model is reduced by about 6%. The above experimental results prove the effectiveness of our method.

Underwater target detection is widely used in various applications such as underwater search and rescue, underwater environment monitoring, and Marine resources survey. However, the visibility of the underwater environment and the accuracy of target detection can be affected by complex underwater light changes and unpredictable background noise. To address these issues, we propose an improved underwater target detection algorithm based on YOLOv8n. Our algorithm focuses on three aspects. Firstly, we replace the original C2f module with Deformable Convnets v2 to enhance the adaptive ability of the target region in the convolution check feature map and extract the target region's features more accurately. Secondly, we introduce SimAm, a non-parametric attention mechanism, which can deduce and assign three-dimensional attention weights without adding network parameters. Lastly, we optimize the loss function by replacing the CIOU loss function with the Wise-IOU loss function. To conduct our experiments, we create our own dataset of underwater target detection for experimentation. Meanwhile, we also utilized the Pascal VOC dataset to evaluate our approach. The mAP@0.5 and mAP@0.5:0.95 of the original YOLOv8n algorithm on the underwater target detection were 88.6% and 51.8%, respectively, and the improved algorithm mAP@0.5 and mAP@0.5:0.95 can reach 91.8% and 55.9%. The original YOLOV8n algorithm was 62.2% and 45.9% mAP@0.5 and mAP@0.5:0.95 on the Pascal VOC dataset, respectively. The improved YOLOV8n algorithm mAP@0.5 and mAP@0.5:0.95 were 65.7% and 48.3%, respectively. The floating-point computation volume of the model is reduced by about 6%. The above experimental results prove the effectiveness of our method.

The recently proposed DEtection TRansformer (DETR) removes hand-designed components and has become a new paradigm for object detection. However, the application of DETR is limited due to its expensive inference cost. While edge devices provide a solution for more challenging scenarios, they are unable to accommodate the expensive inference cost of DETR. To address this issue, we propose a Lightweight, Efficient, and Decoupled DETR, called LED-DETR. We divide DETR into two parts: the feature extractor and the object querier. In the feature extractor, we introduce lightweight convolutional neural networks as the backbone and efficient attention mechanisms as the self-attention mechanism for more lightweight. In the object querier, we incorporate the conditional spatial query for more performant. Compared with the original DETR, LED-DETR achieves a good trade-off between compute, memory footprint, and performance.