BG-YOLO: A Bidirectional-Guided Method for Underwater Object Detection

TL;DR

BG-YOLO introduces a bidirectional-guided approach with parallel enhancement and detection branches, improving underwater object detection accuracy in degraded images without additional computational costs.

Contribution

The paper presents a novel bidirectional-guided framework that optimizes image enhancement specifically for detection tasks, outperforming existing methods in underwater object detection.

Findings

Significant improvement in detection accuracy in degraded underwater scenes

Maintains high detection speed without extra computational cost

Effective guidance from detection subnet enhances image enhancement quality

Abstract

Degraded underwater images decrease the accuracy of underwater object detection. However, existing methods for underwater image enhancement mainly focus on improving the indicators in visual aspects, which may not benefit the tasks of underwater image detection, and may lead to serious degradation in performance. To alleviate this problem, we proposed a bidirectional-guided method for underwater object detection, referred to as BG-YOLO. In the proposed method, network is organized by constructing an enhancement branch and a detection branch in a parallel way. The enhancement branch consists of a cascade of an image enhancement subnet and an object detection subnet. And the detection branch only consists of a detection subnet. A feature guided module connects the shallow convolution layer of the two branches. When training the enhancement branch, the object detection subnet in the enhancement branch guides the image enhancement subnet to be optimized towards the direction that is most conducive to the detection task. The shallow feature map of the trained enhancement branch will be output to the feature guided module, constraining the optimization of detection branch through consistency loss and prompting detection branch to learn more detailed information of the objects. And hence the detection performance will be refined. During the detection tasks, only detection branch will be reserved so that no additional cost of computation will be introduced. Extensive experiments demonstrate that the proposed method shows significant improvement in performance of the detector in severely degraded underwater scenes while maintaining a remarkable detection speed.