The identification of objects under-water presents a formidable challenge because of the light absorption and scattering in water, which may alter the color and visual attributes of objects. GAN-based underwater object detection is a promising new approach for improving the performance of object detection algorithms on underwater images. Generative Adversarial Networks (GANs) represent a class of machine learning models capable of producing synthetic data that closely resembles real data. GAN-based color correction methods can generate color-corrected underwater images that are more amenable to object detection. This capability has the potential to enhance the precision of object detection algorithms. Several successful GAN-based underwater object detection systems have been developed in recent years [5]. For example, one study showed that GAN-based color correction improved the accuracy of an object detection algorithm on underwater images by up to 10%. Another study developed a GAN-based object detection system that was able to detect objects in underwater images with high accuracy, even in low-visibility and noisy conditions. The deep learning associated Generated Adversarial Networks (GANs) have presented remarkable outcomes on image segmentation [3]. In the future, GAN-based underwater object detection is expected to play an important role in a variety of applications, such as underwater surveillance, exploration, robotics, and marine biology research.