Generative Data Augmentation for Vehicle Detection in Aerial Images

Scarcity of training data is one the prominent problems for deep networks which require large amounts data. Data augmentation a widely used method to increase number samples and their variations. In this paper, we focus on improving vehicle detection performance in aerial images propose generative does not need any extra supervision than bounding box annotations objects dataset. The proposed increases by allowing detectors be trained with higher instances, especially when there are limited instances. generic sense that it can integrated different generators. experiments show Average Precision up 25.2% 25.7% Pluralistic DeepFill respectively.