Semi-Supervised Semantic Segmentation with Pixel-Level Contrastive Learning from a Class-wise Memory Bank

TL;DR

This paper introduces a semi-supervised semantic segmentation method using pixel-level contrastive learning with a class-wise memory bank, significantly improving performance especially with limited labeled data.

Contribution

It proposes a novel contrastive learning module with a class-wise memory bank to enhance semi-supervised segmentation accuracy.

Findings

Outperforms state-of-the-art semi-supervised segmentation methods.

Achieves larger improvements with less labeled data.

Effective in semi-supervised domain adaptation scenarios.

Abstract

This work presents a novel approach for semi-supervised semantic segmentation. The key element of this approach is our contrastive learning module that enforces the segmentation network to yield similar pixel-level feature representations for same-class samples across the whole dataset. To achieve this, we maintain a memory bank continuously updated with relevant and high-quality feature vectors from labeled data. In an end-to-end training, the features from both labeled and unlabeled data are optimized to be similar to same-class samples from the memory bank. Our approach outperforms the current state-of-the-art for semi-supervised semantic segmentation and semi-supervised domain adaptation on well-known public benchmarks, with larger improvements on the most challenging scenarios, i.e., less available labeled data. https://github.com/Shathe/SemiSeg-Contrastive