Existing logo detection methods mostly rely on supervised learning with a large quantity of labelled training data in limited classes. This restricts their scalability to a large number of logo classes subject to limited labelling budget. In this work, we consider a more scalable open logo detection problem where only a fraction of logo classes are fully labelled whilst the remaining classes are only annotated with a clean icon image (e.g. 1-shot icon supervised). To generalise and transfer knowledge of fully supervised logo classes to other 1-shot icon supervised classes, we propose a Multi-Perspective Cross-Class (MPCC) domain adaptation method. In a data augmentation principle, MPCC conducts feature distribution alignment in two perspectives. Specifically, we align the feature distribution between synthetic logo images of 1-shot icon supervised classes and genuine logo images of fully supervised classes, and that between logo images and non-logo images, concurrently. This allows for mitigating the domain shift problem between model training and testing on 1-shot icon supervised logo classes, simultaneously reducing the model overfitting towards fully labelled logo classes. Extensive comparative experiments show the advantage of MPCC over existing state-of-the-art competitors on the challenging QMUL-OpenLogo benchmark (Su et al., 2018).

现有的徽标检测方法大多依赖于有限级别的大量标签培训数据的监督学习。在有限的标签预算下，这将它们的可扩展性限制为大量徽标类。在这项工作中，我们考虑了更具可扩展性的开放徽标检测问题，其中只有一小部分徽标类别被完全标记，而其余类别仅使用干净的图标图像进行注释（例如，监督一击式图标）。为了将完全受监管的徽标类别的知识概括并转移到其他一击式图标受监管的类别，我们提出了多视角交叉类别（MPCC）域自适应方法。在数据增强原则中，MPCC从两个角度进行特征分布对齐。具体而言，我们同时调整了1次图标监管类的合成徽标图像和完全监管类的真实徽标图像之间的特征分布，以及徽标图像和非徽标图像之间的特征分布。这样可以减轻模型训练和在1发图标监督的徽标类上进行测试之间的域转换问题，同时减少模型对完全标记的徽标类的过度拟合。广泛的比较实验表明，在具有挑战性的QMUL-OpenLogo基准测试中，MPCC优于现有的最新竞争对手（Su等人，2018）。