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

TL;DR

Polite Teacher introduces a semi-supervised instance segmentation method using mutual learning and pseudo-label filtering, significantly improving performance on COCO dataset with an anchor-free detector.

Contribution

It is one of the first semi-supervised instance segmentation methods employing mutual learning and confidence-based pseudo-label filtering with an anchor-free detector.

Findings

Achieves approximately +8 percentage points in mask AP over baseline.

Effective in different supervision regimes.

First to address semi-supervised instance segmentation with anchor-free detectors.

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.