Semi-Supervised Semantic Segmentation via Derivative Label Propagation

TL;DR

This paper introduces DerProp, a semi-supervised semantic segmentation framework that enhances pseudo-label reliability through derivative label propagation, improving segmentation accuracy with limited labeled data.

Contribution

The paper proposes a novel derivative label propagation method that regularizes similarity metrics, effectively improving pseudo-label quality in semi-supervised segmentation.

Findings

Demonstrates superior performance over existing methods

Validates the effectiveness of derivative label regularization

Achieves improved segmentation accuracy with limited labels

Abstract

Semi-supervised semantic segmentation, which leverages a limited set of labeled images, helps to relieve the heavy annotation burden. While pseudo-labeling strategies yield promising results, there is still room for enhancing the reliability of pseudo-labels. Hence, we develop a semi-supervised framework, namely DerProp, equipped with a novel derivative label propagation to rectify imperfect pseudo-labels. Our label propagation method imposes discrete derivative operations on pixel-wise feature vectors as additional regularization, thereby generating strictly regularized similarity metrics. Doing so effectively alleviates the ill-posed problem that identical similarities correspond to different features, through constraining the solution space. Extensive experiments are conducted to verify the rationality of our design, and demonstrate our superiority over other methods. Codes are available at https://github.com/ForawardStar/DerProp/.