TransLine: transfer learning for accurate and explainable power line anomaly detection with insufficient data

 Accurate and automatic power line anomaly detection is critical to the smart grid. However, effective solutions are yet available due to the insufficiency of anomaly data. In this paper, we first collect a dataset from various sources consisting of both normal and abnormal power line images. With this dataset, anomaly detection becomes feasible though with limited accuracy due to the limited size of the dataset. As such, we propose TransLine, an approach based on transfer learning to apply the existing knowledge extracted from large-scale datasets to complement the data insufficiency of power line anomaly detection. TransLine customizes and optimizes the knowledge to automate the power line anomaly detection with high accuracy. The experiment results show that TransLine can achieve an average accuracy of 96.1% and up to 98.1% accuracy given only a hundred abnormal images for model training. TransLine also incorporates an explainability module to explain the detection results and enhance its understandability, trustworthiness, and practicalness. TransLine can be a key enabler of the smart grid for great stability and efficiency and can inspire other industrial applications facing data insufficiency issues.