We improved an existing end-to-end polyp detection model with better average precision validated by different data sets with trivial cost on detection speed. Previous work on detecting polyps within colonoscopy \cite{Chen2018} provided an efficient end-to-end solution to alleviate doctor's examination overhead. However, our later experiments found this framework is not as robust as before as the condition of polyp capturing varies. In this work, we conducted several studies on data set, identifying main issues that causes low precision rate in the task of polyp detection. We used an optimized anchor generation methods to get better anchor box shape and more boxes are used for detection as we believe this is necessary for small object detection. A alternative backbone is used to compensate the heavy time cost introduced by dense anchor box regression. With use of the attention gate module, our model can achieve state-of-the-art polyp detection performance while still maintain real-time detection speed.

翻译：我们改进了现有的端到端聚苯乙烯检测模型,提高了平均精确度,得到了不同数据集的验证,探测速度费用低廉。以前在结肠镜检查中检测聚苯乙烯的工作提供了有效的端到端解决方案,以减轻医生检查管理费用。然而,我们后来的实验发现,这一框架不像聚苯乙烯捕获条件不同那样坚固。在这项工作中,我们进行了数项关于数据集的研究,查明了造成聚苯乙烯检测任务低精确率的主要问题。我们使用了优化锚生成方法,以获得更好的锚箱形状,并使用更多的盒子进行检测,因为我们认为小型物体探测需要这种方式。使用了替代的骨干来补偿密度锚盒回归带来的沉重时间成本。使用注意门模块,我们的模型可以在保持实时检测速度的同时实现最先进的聚苯检测功能。