基于网格切分的单阶段实例分割方法

近年来，与二阶段实例分割方法相比，单阶段实例分割方法由于实时性强，已在实际应用中取得了初步进展，但目前仍然存在以下两个主要缺点.（1）精度较低：单阶段方法缺少多轮优化环节，因此其精度离实际应用仍存在差距；（2）不够灵活：目前大多数单阶段方法是独立设计的，难以兼容实际应用中不同类型的物体检测框架，因此适用范围相对有限.提出了一种精确且灵活的单阶段实例分割框架——网格实例分割方法（GridMask），其中两个关键步骤如下：（1）为了提高实例分割精度，提出了一种网格切分二值化算法，将物体边界框内的区域划分为多个独立的网格，然后在每个网格上进行实例分割.该步骤将物体分割任务简化成了多个网格切片的分割，有效降低了特征表示的复杂程度，进而提高了实例分割的精度；（2）为了兼容不同的物体检测方法，设计了一个可以即插即用的子网络模块.该模块可以无缝地接入到目前大多数主流物体检测框架中，以增强这些方法的分割性能.所提方法在公共数据集MS COCO上取得了出色的性能，优于现有的大部分单阶段方法，甚至一些二阶段方法.

Grid Dividing for Single-stage Instance Segmentation

In recent years, single-stage instance segmentation methods have made preliminary progress in real-world applications due to their high efficiency, but there are still two drawbacks compared to two-stage counterparts. (1) Low accuracy: the single-stage method does not have multiple rounds of refinement, so its accuracy is some distance away from real-world applications; (2) Low flexibility: most existing single-stage methods are specifically designed models, which are not compatible with object detectors. This study presents an accurate and flexible framework for single-stage instance segmentation, which contains the following two key designs. (1) To improve the accuracy of instance segmentation, a grid dividing binarization algorithm is proposed, where the bounding box region is firstly divided into several grid cells and then instance segmentation is performed on each grid cell. In this way, the original full-object segmentation task is simplified into the sub-tasks of grid cells, which significantly reduces the complexity of feature representation and further improves the instance segmentation accuracy; (2) To be compatible with object detectors, a plug-and-play module is designed, which can be seamlessly plugged into most existing object detection methods, thus enabling them to perform instance segmentation. The proposed method achieves excellent performance on the public dataset, such as MS COCO. It outperforms most existing single-stage methods and even some two-stage methods.