Dominik Filipiak, Andrzej Zapała, Piotr Tempczyk, Anna Fensel, Marek Cygan
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.
| Task | Dataset | Metric | Value | Model |
|---|---|---|---|---|
| Semi-Supervised Instance Segmentation | COCO 1% labeled data | mask AP | 18.33 | Polite Teacher (ResNet50) |
| Semi-Supervised Instance Segmentation | COCO 10% labeled data | mask AP | 30.08 | Polite Teacher (ResNet50) |
| Semi-Supervised Instance Segmentation | COCO 5% labeled data | mask AP | 26.46 | Polite Teacher (ResNet50) |
| Semi-Supervised Instance Segmentation | COCO 2% labeled data | mask AP | 22.28 | Polite Teacher (ResNet50) |