论文标题
Centermask：单次实例分割带有点表示
CenterMask: single shot instance segmentation with point representation
论文作者
论文摘要
在本文中，我们提出了一种单次实例分割方法，该方法简单，快速和准确。一阶段实例细分面临两个主要挑战：对象实例分化和像素功能对齐。因此，我们将实例分割分解为两个并行子任务：局部形状预测，即使在重叠的条件下也将实例分开，以及以像素到像素的方式将整个图像分割的全球显着性生成。组装两个分支的输出以形成最终实例掩码。要意识到这一点，局部形状信息是从对象中心点的表示中采用的。拟议的Centermask完全从头开始训练，没有任何铃铛和哨子，以12.3 fps的速度实现了34.5个掩码AP，使用单型型号，对充满挑战的可可数据集进行单尺度训练/测试。该精度高于所有其他一阶段实例分割方法，但张紧张术慢了5倍，这显示了CenterMask的有效性。此外，我们的方法可以很容易地嵌入到其他单阶段对象检测器（例如FCO）上，并且表现良好，显示了CenterMask的概括。
In this paper, we propose a single-shot instance segmentation method, which is simple, fast and accurate. There are two main challenges for one-stage instance segmentation: object instances differentiation and pixel-wise feature alignment. Accordingly, we decompose the instance segmentation into two parallel subtasks: Local Shape prediction that separates instances even in overlapping conditions, and Global Saliency generation that segments the whole image in a pixel-to-pixel manner. The outputs of the two branches are assembled to form the final instance masks. To realize that, the local shape information is adopted from the representation of object center points. Totally trained from scratch and without any bells and whistles, the proposed CenterMask achieves 34.5 mask AP with a speed of 12.3 fps, using a single-model with single-scale training/testing on the challenging COCO dataset. The accuracy is higher than all other one-stage instance segmentation methods except the 5 times slower TensorMask, which shows the effectiveness of CenterMask. Besides, our method can be easily embedded to other one-stage object detectors such as FCOS and performs well, showing the generalization of CenterMask.
