In this paper, we propose an instance segmentation method uses a single-stage detector. Compared to the two-stage method, the single-stage method is simpler and easier to train. Not rely on the traditional region proposal, it directly uses pixels, which reduces the complexity of the network and significantly increases the speed. Our segmentation method is based on anchor boxes, which performs multi-scale detection by setting anchors of different sizes on multi-scale feature maps. We add a new branch to the prediction head to generate prototype masks and mask coefficients, then linearly combine them to generate mask. In our experiments, the proposed model had better performance, we got 35.12 fps on a single NVIDIA GEFORCE GTX 2080 GPU, which proves that our method is simple, effective, and faster.

在本文中，我们提出了一种使用单级检测器的实例分割方法。与两阶段方法相比，单阶段方法更简单，更容易训练。不依赖于传统的region proposal，直接使用像素，降低了网络的复杂度，显着提高了速度。我们的分割方法基于锚框，通过在多尺度特征图上设置不同大小的锚来执行多尺度检测。我们向预测头添加一个新分支以生成原型掩码和掩码系数，然后将它们线性组合以生成掩码。在我们的实验中，所提出的模型具有更好的性能，我们在单个 NVIDIA GEFORCE GTX 2080 GPU 上获得了 35.12 fps，这证明我们的方法简单、有效且速度更快。