针对水下检测的图像增强模型，提升目标识别精度与速度。
AquaFeat: A Features-Based Image Enhancement Model for Underwater Object Detection
- 基于任务驱动的多尺度特征增强，端到端优化检测相关特征。
- 在复杂水下数据集上实现0.877精确率和0.624召回率，领先现有方法。
- 轻量高效，46.5帧/秒，适合海洋监测等实时场景应用。
水下环境严重图像退化影响目标检测性能，传统增强方法未针对下游任务优化。为此，我们提出AquaFeat，一种即插即用的任务驱动特征增强模块。该方法将多尺度特征增强网络与检测器损失函数联合训练，使增强过程显式聚焦于检测关键特征。集成到YOLOv8m后，在挑战性水下数据集上达到0.877的精确率（Precision）和0.624的召回率（Recall），并取得0.677（[email protected]）和0.421（mAP@[0.5:0.95]）的优异指标。模型保持46.5帧/秒的实际处理速度，为海洋生态监测与基础设施巡检等实际应用提供高效可靠的解决方案。
原文摘要 · Abstract (English)
The severe image degradation in underwater environments impairs object detection models, as traditional image enhancement methods are often not optimized for such downstream tasks. To address this, we propose AquaFeat, a novel, plug-and-play module that performs task-driven feature enhancement. Our approach integrates a multi-scale feature enhancement network trained end-to-end with the detector's loss function, ensuring the enhancement process is explicitly guided to refine features most relevant to the detection task. When integrated with YOLOv8m on challenging underwater datasets, AquaFeat achieves state-of-the-art Precision (0.877) and Recall (0.624), along with competitive mAP scores ([email protected] of 0.677 and mAP@[0.5:0.95] of 0.421). By delivering these accuracy gains while maintaining a practical processing speed of 46.5 FPS, our model provides an effective and computationally efficient solution for real-world applications, such as marine ecosystem monitoring and infrastructure inspection.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。