English

Polite Teacher: Semi-Supervised Instance Segmentation with Mutual Learning and Pseudo-Label Thresholding

Computer Vision and Pattern Recognition 2022-11-09 v1 Artificial Intelligence Machine Learning

Abstract

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.

Keywords

Cite

@article{arxiv.2211.03850,
  title  = {Polite Teacher: Semi-Supervised Instance Segmentation with Mutual Learning and Pseudo-Label Thresholding},
  author = {Dominik Filipiak and Andrzej Zapała and Piotr Tempczyk and Anna Fensel and Marek Cygan},
  journal= {arXiv preprint arXiv:2211.03850},
  year   = {2022}
}
R2 v1 2026-06-28T05:22:04.643Z