부산대학교 도서관

Most existing deep learning-based methods for logo detection require a large amount of object-level annotated training data. However, it takes a lot of time and effort to create a good object-level annotated logo detection dataset. Many researchers have tried to utilize synthesized images with automatically generated annotations for training to deal with data annotation problem. However, in real applications, model trained using synthesized images suffer from performance loss due to domain shift between synthesized and real-world images. To this end, in this paper, we propose an adversarial learning-based unsupervised domain adaptation method for logo detection. We only use labeled synthesized logo images for model training and adapt target domain knowledge using unlabeled real-world logo images. We propose entropy minimization of mid-level output feature maps in order to effectively align the domain gap between synthetic and real images for the logo detection task. Additionally, we have generated coherent synthesized logo images with automatically constructed bounding box annotations for different datasets to perform unsupervised training for the experiments. Our experiments show that the proposed method improves performance on different logo datasets compared to direct transfer from source to target domain (synthetic-to-real images) without any labeling cost and increasing network parameters.