Semi-supervised Semantic Segmentation with Mutual Knowledge Distillation

TL;DR

This paper introduces a mutual knowledge distillation framework for semi-supervised semantic segmentation, leveraging auxiliary models and diverse augmentations to improve performance over existing methods.

Contribution

The paper proposes a novel mutual knowledge distillation approach with auxiliary mean-teacher models and multiple augmentation strategies for semi-supervised segmentation.

Findings

Outperforms previous state-of-the-art methods on public benchmarks.

Effectively utilizes data and feature augmentation to enhance training diversity.

Demonstrates significant performance gains in various semi-supervised settings.

Abstract

Consistency regularization has been widely studied in recent semisupervised semantic segmentation methods, and promising performance has been achieved. In this work, we propose a new consistency regularization framework, termed mutual knowledge distillation (MKD), combined with data and feature augmentation. We introduce two auxiliary mean-teacher models based on consistency regularization. More specifically, we use the pseudo-labels generated by a mean teacher to supervise the student network to achieve a mutual knowledge distillation between the two branches. In addition to using image-level strong and weak augmentation, we also discuss feature augmentation. This involves considering various sources of knowledge to distill the student network. Thus, we can significantly increase the diversity of the training samples. Experiments on public benchmarks show that our framework outperforms previous state-of-the-art (SOTA) methods under various semi-supervised settings. Code is available at semi-mmseg.