论文标题
OS2D：通过匹配锚点功能，一阶段的单次对象检测
OS2D: One-Stage One-Shot Object Detection by Matching Anchor Features
论文作者
论文摘要
在本文中，我们考虑了单发对象检测的任务，该任务包括检测由单个演示定义的对象。与标准对象检测不同，用于训练和测试的对象类别不会重叠。我们构建了共同执行本地化和认可的单阶段系统。我们使用学到的本地特征的密集相关匹配来查找对应关系，一种馈送前线几何变换模型来对齐特征和相关张量的双线性重新采样，以计算对齐特征的检测得分。所有组件都是可区分的，可以端到端培训。对几个具有挑战性的领域（零售产品，3D对象，建筑物和徽标）的实验评估表明，我们的方法可以检测到看不见的类别（例如，在杂货训练时牙膏），并以明显的边距胜过几个基线。我们的代码可在线提供：https：//github.com/aosokin/os2d。
In this paper, we consider the task of one-shot object detection, which consists in detecting objects defined by a single demonstration. Differently from the standard object detection, the classes of objects used for training and testing do not overlap. We build the one-stage system that performs localization and recognition jointly. We use dense correlation matching of learned local features to find correspondences, a feed-forward geometric transformation model to align features and bilinear resampling of the correlation tensor to compute the detection score of the aligned features. All the components are differentiable, which allows end-to-end training. Experimental evaluation on several challenging domains (retail products, 3D objects, buildings and logos) shows that our method can detect unseen classes (e.g., toothpaste when trained on groceries) and outperforms several baselines by a significant margin. Our code is available online: https://github.com/aosokin/os2d .
