论文标题
CentRipetalnet：追求高质量的关键点对以进行对象检测
CentripetalNet: Pursuing High-quality Keypoint Pairs for Object Detection
论文作者
论文摘要
基于Kepoint的检测器已取得了相当孔的性能。但是，不正确的关键点匹配仍然是广泛的，并且会极大地影响检测器的性能。在本文中，我们提出了使用Centripetal Shift的Centripetalnet，以配对同一实例的角关键点。 Centripetalnet预测角点的位置和中心移动，并匹配其偏移结果的角落。结合位置信息，我们的方法比常规嵌入方法更准确地匹配角点。角池在边界框中提取到边框上的信息。为了使这些信息在角落更加了解，我们设计了一个跨星形变形卷积网络以进行功能适应。此外，我们通过将Centripetalnet配备掩码预测模块来探索无锚探测器上的实例分割。在MS-Coco Test-DEV上，我们的CentRipetAlnet不仅优于AP为48.0％的所有现有的无锚探测器，而且还能实现与最新的实例分段方法相当的性能，并具有40.2％的MaskAp。代码将在https://github.com/kiveedong/centripetalnet上找到。
Keypoint-based detectors have achieved pretty-well performance. However, incorrect keypoint matching is still widespread and greatly affects the performance of the detector. In this paper, we propose CentripetalNet which uses centripetal shift to pair corner keypoints from the same instance. CentripetalNet predicts the position and the centripetal shift of the corner points and matches corners whose shifted results are aligned. Combining position information, our approach matches corner points more accurately than the conventional embedding approaches do. Corner pooling extracts information inside the bounding boxes onto the border. To make this information more aware at the corners, we design a cross-star deformable convolution network to conduct feature adaption. Furthermore, we explore instance segmentation on anchor-free detectors by equipping our CentripetalNet with a mask prediction module. On MS-COCO test-dev, our CentripetalNet not only outperforms all existing anchor-free detectors with an AP of 48.0% but also achieves comparable performance to the state-of-the-art instance segmentation approaches with a 40.2% MaskAP. Code will be available at https://github.com/KiveeDong/CentripetalNet.
