Semi-Supervised Semantic Segmentation with Cross Teacher Training

TL;DR

This paper introduces a cross-teacher training framework for semi-supervised semantic segmentation, combining multiple modules to enhance learning from limited labeled data and outperform existing methods.

Contribution

It proposes a novel cross-teacher training framework with contrastive modules that reduces error propagation and improves segmentation performance.

Findings

Significant performance improvement over traditional semi-supervised methods

Outperforms state-of-the-art on benchmark datasets

Framework effectively transfers knowledge from labeled to unlabeled data

Abstract

Convolutional neural networks can achieve remarkable performance in semantic segmentation tasks. However, such neural network approaches heavily rely on costly pixel-level annotation. Semi-supervised learning is a promising resolution to tackle this issue, but its performance still far falls behind the fully supervised counterpart. This work proposes a cross-teacher training framework with three modules that significantly improves traditional semi-supervised learning approaches. The core is a cross-teacher module, which could simultaneously reduce the coupling among peer networks and the error accumulation between teacher and student networks. In addition, we propose two complementary contrastive learning modules. The high-level module can transfer high-quality knowledge from labeled data to unlabeled ones and promote separation between classes in feature space. The low-level module can encourage low-quality features learning from the high-quality features among peer networks. In experiments, the cross-teacher module significantly improves the performance of traditional student-teacher approaches, and our framework outperforms stateof-the-art methods on benchmark datasets. Our source code of CTT will be released.