论文标题
WQT和DG-YOLO：朝着水下对象检测中的域泛化
WQT and DG-YOLO: towards domain generalization in underwater object detection
论文作者
论文摘要
一般的水下对象探测器（GUOD）应在大多数水下情况下表现良好。但是，由于水下数据集有限，常规对象检测方法遭受了域的严重转移。本文旨在建造一个具有小型水下数据集的鸟类，其水质类型有限。首先，我们提出了一个数据增强方法水质转移（WQT），以增加原始小数据集的域多样性。其次，为了从WQT生成的数据中挖掘语义信息，提出了DG-Yolo，其中包括三个部分：Yolov3，DIM和IRM惩罚。最后，对原始和合成URPC2019数据集进行的实验证明，WQT+DG-Yolo在水下对象检测中实现了有希望的域概括性能。
A General Underwater Object Detector (GUOD) should perform well on most of underwater circumstances. However, with limited underwater dataset, conventional object detection methods suffer from domain shift severely. This paper aims to build a GUOD with small underwater dataset with limited types of water quality. First, we propose a data augmentation method Water Quality Transfer (WQT) to increase domain diversity of the original small dataset. Second, for mining the semantic information from data generated by WQT, DG-YOLO is proposed, which consists of three parts: YOLOv3, DIM and IRM penalty. Finally, experiments on original and synthetic URPC2019 dataset prove that WQT+DG-YOLO achieves promising performance of domain generalization in underwater object detection.
