Küçük ölçekli verilerde araç tespiti için üretken metodlarla veri artırma

Scarcity of training data is one of the prominent problems for deep neural networks, which commonly require high amounts of data to display their potential. Data augmentation techniques are frequently applied during the pre-training and training phases of deep neural networks to overcome the problem of having insufficient data for training. These techniques aim to increase a neural network's generalization performance on unseen data by increasing the number of training samples and provide a more representative distribution to the system during training. In this work, we focus on improving vehicle detection in aerial images by proposing a data augmentation method that does not need any extra supervision than the bounding box annotations of the vehicle instances in the training data. The methods we used are based on a conditional Generative Adversarial Network (cGAN). The proposed method is not exclusive and can be used in association with classical augmentation techniques to further improve object detection performance. We showed that the proposed data augmentation method increases the Average Precision by up to 25.2%, 32.7%, and 25.7% when integrated with Pluralistic, PSGAN, and DeepFill respectively.