Labeling objects with pixel-wise segmentation requires a huge amount of human labor compared to bounding boxes. Most existing methods for weakly supervised instance segmentation focus on designing heuristic losses with priors from bounding boxes. While, we find that box-supervised methods can produce some fine segmentation masks and we wonder whether the detectors could learn from these fine masks while ignoring low-quality masks. To answer this question, we present BoxTeacher, an efficient and end-to-end training framework for high-performance weakly supervised instance segmentation, which leverages a sophisticated teacher to generate high-quality masks as pseudo labels. Considering the massive noisy masks hurt the training, we present a mask-aware confidence score to estimate the quality of pseudo masks, and propose the noise-aware pixel loss and noise-reduced affinity loss to adaptively optimize the student with pseudo masks. Extensive experiments can demonstrate effectiveness of the proposed BoxTeacher. Without bells and whistles, BoxTeacher remarkably achieves $34.4$ mask AP and $35.4$ mask AP with ResNet-50 and ResNet-101 respectively on the challenging MS-COCO dataset, which outperforms the previous state-of-the-art methods by a significant margin. The code and models are available at https://github.com/hustvl/BoxTeacher.

BoxTeacher是一个高效End-to-End的训练框架，可以实现使用Bounding Box产生高质量的Mask标签的弱监督实例分割，BoxTeacher使用一个复杂的教师网络产生高质量的Mask标签，然后通过noise-aware pixel loss和noise-reduced affinity loss调整学生网络，这种方法在COCO数据集上具有很高的标记AP表现。

BoxTeacher：探索高质量的弱监督实例分割伪标签