Albeit the highest accuracy of object detection is generally acquired by multi-stage detectors, like R-CNN and its extension approaches, the single-stage object detectors also achieve remarkable performance with faster execution and higher scalability. Inspired by this, we propose a single-stage framework to tackle the instance segmentation task. Building on a single-stage object detection network in hand, our model outputs the detected bounding box of each instance, the semantic segmentation result, and the pixel affinity simultaneously. After that, we generate the final instance masks via a fast post-processing method with the help of the three outputs above. As far as we know, it is the first attempt to segment instances in a single-stage pipeline on challenging datasets. Extensive experiments demonstrate the efficiency of our post-processing method, and the proposed framework obtains competitive results as a single-stage instance segmentation method. We achieve 32.5 box AP and 26.0 mask AP on the COCO validation set with 500 pixels input scale and 22.9 mask AP on the Cityscapes test set.

中文翻译：

---

单阶段实例分割

尽管目标检测的最高精度通常由多级检测器（如 R-CNN 及其扩展方法）获得，但单级目标检测器也以更快的执行速度和更高的可扩展性实现了卓越的性能。受此启发，我们提出了一个单阶段框架来解决实例分割任务。我们的模型基于现有的单阶段目标检测网络，同时输出检测到的每个实例的边界框、语义分割结果和像素亲和力。之后，我们借助上述三个输出通过快速后处理方法生成最终实例掩码。据我们所知，这是第一次尝试在具有挑战性的数据集的单阶段管道中分割实例。大量实验证明了我们的后处理方法的效率，并且所提出的框架作为单阶段实例分割方法获得了有竞争力的结果。我们在输入比例为 500 像素的 COCO 验证集上实现了 32.5 box AP 和 26.0 mask AP，在 Cityscapes 测试集上实现了 22.9 mask AP。