论文标题
用于对象检测，实例分割和姿势估计的点锚锚
Point-Set Anchors for Object Detection, Instance Segmentation and Pose Estimation
论文作者
论文摘要
对象检测和人类姿势估计的最新方法是从对象或人的中心点回归边界框或人类关键点。尽管此中心点回归是简单有效的，但我们认为，由于对象变形和比例/方向变化，在中心点提取的图像特征包含有限的信息，以预测遥远的关键点或边界框边界。为了促进推论，我们建议从位于更有利位置的一组点进行回归。该点集的安排是为了反映给定任务的良好初始化，例如训练数据中的姿势估计模式，姿势估算的模式比中心点更接近地面真理，并为回归提供了更有信息的功能。由于点集的效用取决于其比例，纵横比和旋转与目标匹配的效果，因此我们采用了对这些转换进行采样的锚点技术来生成其他点集候选者。我们将此提出的框架（称为点锚锚）应用于对象检测，实例分割和人体姿势估计。我们的结果表明，这种通用方法可以使用这些任务中的每个任务来实现绩效竞争。代码可在\ url {https://github.com/fangyunwei/pointsetanchor}中获得。
A recent approach for object detection and human pose estimation is to regress bounding boxes or human keypoints from a central point on the object or person. While this center-point regression is simple and efficient, we argue that the image features extracted at a central point contain limited information for predicting distant keypoints or bounding box boundaries, due to object deformation and scale/orientation variation. To facilitate inference, we propose to instead perform regression from a set of points placed at more advantageous positions. This point set is arranged to reflect a good initialization for the given task, such as modes in the training data for pose estimation, which lie closer to the ground truth than the central point and provide more informative features for regression. As the utility of a point set depends on how well its scale, aspect ratio and rotation matches the target, we adopt the anchor box technique of sampling these transformations to generate additional point-set candidates. We apply this proposed framework, called Point-Set Anchors, to object detection, instance segmentation, and human pose estimation. Our results show that this general-purpose approach can achieve performance competitive with state-of-the-art methods for each of these tasks. Code is available at \url{https://github.com/FangyunWei/PointSetAnchor}
