论文标题
礼貌的老师：半监督实例分割，相互学习和伪标签阈值
Polite Teacher: Semi-Supervised Instance Segmentation with Mutual Learning and Pseudo-Label Thresholding
论文作者
论文摘要
我们提出了礼貌的老师，这是一种简单而有效的方法，用于半监督实例细分的任务。拟议的架构依赖于教师的相互学习框架。为了滤除嘈杂的伪标签，我们使用置信度阈值来边界框和面罩评分。该方法已使用CenterMask（单阶段的无锚检测器）进行了测试。在Coco 2017 Val数据集上进行了测试，我们的体系结构显着（大约+8 pp。在Mask AP中）优于不同监督制度的基线。据我们所知，这是解决半监督实例细分问题的第一件作品之一，也是第一个专门用于无锚探测器的问题。
We present Polite Teacher, a simple yet effective method for the task of semi-supervised instance segmentation. The proposed architecture relies on the Teacher-Student mutual learning framework. To filter out noisy pseudo-labels, we use confidence thresholding for bounding boxes and mask scoring for masks. The approach has been tested with CenterMask, a single-stage anchor-free detector. Tested on the COCO 2017 val dataset, our architecture significantly (approx. +8 pp. in mask AP) outperforms the baseline at different supervision regimes. To the best of our knowledge, this is one of the first works tackling the problem of semi-supervised instance segmentation and the first one devoted to an anchor-free detector.
