ABSTRACT Detecting and monitoring structural damage is crucial to prevent significant damage to ship structures caused by corrosion. This study aims to measure the performance of corrosion detection using Convolutional Neural Networks (CNN) by comparing YOLOv8 and Detectron2 models analyzed at various data augmentation settings. The results show that Detectron2 with the ResNet101 backbone performs better than Detectron2 ResNet50 and YOLOv8 models. The result found that applied augmentation data settings, such as vertical & horizontal flip, rotation, and increasing & decreasing colour saturation, highlight their importance in training robust corrosion detection models. These findings contribute to developing corrosion detection methods, showing that the Detectron2 model with instance segmentation can overcome the complexity and variety of corrosion shapes more effectively than YOLOv8 model. The instance segmentation model has proven to be the more effective CNN model for detecting abstract objects, such as corrosion damage in ship hulls.