Semi-supervised vehicle classification via fusing affinity matrices

Maojin Sun, Shijie Hao, Guangcan Liu

Abstract: Highlights • Address the label insufficiency issue in classifying vehicle type by using GSSL. • Make the affinity more reliable by using graph fusion. • Achieve over 70% accuracy by only using 5% labeled instances. Abstract Vehicle classification plays a fundamental role in various intelligent transportation systems. With the rapid development of traffic surveillance, the amount of visual vehicle data has been increasing tremendously, and can be easily collected. However, it is labor-intensive to manually annotate the semantic labels for these data, posing the challenge of label insufficiency to the vehicle classification tasks. In this context, we use a semi-supervised learning model to classify vehicle types, which only needs a small number of pre-labeled data and propagates these labels to the rest data at hand. In our model, we combine multiple features via fusing their affinity matrices to enhance the classification accuracy. We conduct several experiments to validate our method on a public vehicle dataset. Experimental results support the effectiveness of our method.