Semi-Supervised Confidence-Level-based Contrastive Discrimination for Class-Imbalanced Semantic Segmentation

TL;DR

This paper introduces a semi-supervised contrastive learning framework with confidence-level discrimination, a data imbalance loss, and a multi-stage fusion network to improve class-imbalanced semantic segmentation, especially with limited labeled data.

Contribution

It presents a novel semi-supervised contrastive learning approach with confidence-level discrimination, a data imbalance loss, and a multi-stage fusion network for improved class-imbalanced segmentation.

Findings

Achieves high segmentation accuracy with only 3.5% labeled data.

Outperforms existing methods on crack and road segmentation tasks.

Demonstrates effectiveness through extensive industrial experiments.

Abstract

To overcome the data-hungry challenge, we have proposed a semi-supervised contrastive learning framework for the task of class-imbalanced semantic segmentation. First and foremost, to make the model operate in a semi-supervised manner, we proposed the confidence-level-based contrastive learning to achieve instance discrimination in an explicit manner, and make the low-confidence low-quality features align with the high-confidence counterparts. Moreover, to tackle the problem of class imbalance in crack segmentation and road components extraction, we proposed the data imbalance loss to replace the traditional cross entropy loss in pixel-level semantic segmentation. Finally, we have also proposed an effective multi-stage fusion network architecture to improve semantic segmentation performance. Extensive experiments on the real industrial crack segmentation and the road segmentation demonstrate the superior effectiveness of the proposed framework. Our proposed method can provide satisfactory segmentation results with even merely 3.5% labeled data.