Expensive bounding-box annotations have limited the development of object detection task. Thus, it is necessary to focus on more challenging task of few-shot object detection. It requires the detector to recognize objects of novel classes with only a few training samples. Nowadays, many existing popular methods adopting training way similar to meta-learning have achieved promising performance, such as Meta R-CNN series. However, support data is only used as the class attention to guide the detecting of query images each time. Their relevance to each other remains unexploited. Moreover, a lot of recent works treat the support data and query images as independent branch without considering the relationship between them. To address this issue, we propose a dynamic relevance learning model, which utilizes the relationship between all support images and Region of Interest (RoI) on the query images to construct a dynamic graph convolutional network (GCN). By adjusting the prediction distribution of the base detector using the output of this GCN, the proposed model serves as a hard auxiliary classification task, which guides the detector to improve the class representation implicitly. Comprehensive experiments have been conducted on Pascal VOC and MS-COCO dataset. The proposed model achieves the best overall performance, which shows its effectiveness of learning more generalized features. Our code is available at https://github.com/liuweijie19980216/DRL-for-FSOD.
翻译:----
昂贵的边界框注释限制了目标检测任务的发展。因此,有必要关注更具挑战性的小样本目标检测任务。它要求检测器仅使用少量训练样本即可识别新类别的对象。目前,许多采用类似于元学习的训练方式的流行方法已经取得了有前途的性能,例如Meta R-CNN系列。然而,每次仅将支持数据用作类别关注以指导查询图像的检测。它们之间的相关性仍未被充分利用。此外,许多最近的工作将支持数据和查询图像视为独立的分支,而不考虑它们之间的关系。为解决这个问题,我们提出了一种动态相关性学习模型,它利用所有支持图像和查询图像上感兴趣区域(RoI)之间的关系构建动态图卷积网络(GCN)。通过使用该GCN的输出调整基础探测器的预测分布,所提出的模型充当硬辅助分类任务,隐式地指导检测器改进类别表征。在Pascal VOC和MS-COCO数据集上进行了全面的实验。所提出的模型实现了最佳的整体性能,表明其有效地学习了更通用的特征。我们的代码可在 https://github.com/liuweijie19980216/DRL-for-FSOD 找到。