Polite Teacher: Semi-Supervised Instance Segmentation with Mutual Learning and Pseudo-Label Thresholding
This work addresses semi-supervised instance segmentation, a problem for computer vision researchers, and is incremental as it adapts existing teacher-student frameworks to a new task.
The paper tackles semi-supervised instance segmentation by proposing Polite Teacher, a method using mutual learning and pseudo-label thresholding, which improves mask AP by approximately 8 percentage points over the baseline on the COCO 2017 val dataset.
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.