Accuracy Improvement of Semi-Supervised Segmentation Using Supervised ClassMix and Sup-Unsup Feature Discriminator

TL;DR

This paper enhances semi-supervised semantic segmentation by combining class label pasting from labeled images onto unlabeled ones with a feature discriminator to improve prediction consistency, leading to better performance.

Contribution

It introduces a novel method that integrates class label pasting and a feature discriminator to address label accuracy and data quality gaps in semi-supervised segmentation.

Findings

Achieved an average 2.07% mIoU improvement on Chase and COVID-19 datasets.

Demonstrated effectiveness of the combined approach over conventional semi-supervised methods.

Abstract

In semantic segmentation, the creation of pixel-level labels for training data incurs significant costs. To address this problem, semi-supervised learning, which utilizes a small number of labeled images alongside unlabeled images to enhance the performance, has gained attention. A conventional semi-supervised learning method, ClassMix, pastes class labels predicted from unlabeled images onto other images. However, since ClassMix performs operations using pseudo-labels obtained from unlabeled images, there is a risk of handling inaccurate labels. Additionally, there is a gap in data quality between labeled and unlabeled images, which can impact the feature maps. This study addresses these two issues. First, we propose a method where class labels from labeled images, along with the corresponding image regions, are pasted onto unlabeled images and their pseudo-labeled images. Second, we introduce a method that trains the model to make predictions on unlabeled images more similar to those on labeled images. Experiments on the Chase and COVID-19 datasets demonstrated an average improvement of 2.07% in mIoU compared to conventional semi-supervised learning methods.