Many object detection models struggle with several problematic aspects of small object detection including the low number of samples, lack of diversity and low features representation. Taking into account that GANs belong to generative models class, their initial objective is to learn to mimic any data distribution. Using the proper GAN model would enable augmenting low precision data increasing their amount and diversity. This solution could potentially result in improved object detection results. Additionally, incorporating GAN-based architecture inside deep learning model can increase accuracy of small objects recognition. In this work the GAN-based method with augmentation is presented to improve small object detection on VOC Pascal dataset. The method is compared with different popular augmentation strategies like object rotations, shifts etc. The experiments are based on FasterRCNN model.
翻译:许多天体探测模型与小型天体探测的几个有问题的方面挣扎,包括样本数量少、缺乏多样性和特征代表性低。考虑到GAN属于基因模型类,它们最初的目标是学习模仿任何数据分布。使用适当的GAN模型可以增加低精度数据,增加其数量和多样性。这一解决方案可能会改进天体探测结果。此外,在深层学习模型中采用GAN结构可以提高小天体识别的准确性。在这项工作中,以GAN为基础的扩增法用来改进VOC Pascal数据集的小天体探测。这种方法与物体旋转、转移等不同的流行增强战略进行比较。实验以SeappleRCNN模型为基础。