Semi-Supervised Semantic Segmentation with Cross Pseudo Supervision

TL;DR

This paper introduces a novel semi-supervised semantic segmentation method called cross pseudo supervision (CPS), which uses two networks to generate pseudo labels for each other, improving segmentation accuracy with limited labeled data.

Contribution

The paper proposes a new consistency regularization technique, CPS, that leverages two perturbed networks to enhance semi-supervised segmentation performance.

Findings

Achieves state-of-the-art results on Cityscapes and PASCAL VOC 2012 datasets.

Effectively utilizes unlabeled data to improve segmentation accuracy.

Demonstrates the effectiveness of dual-network pseudo supervision.

Abstract

In this paper, we study the semi-supervised semantic segmentation problem via exploring both labeled data and extra unlabeled data. We propose a novel consistency regularization approach, called cross pseudo supervision (CPS). Our approach imposes the consistency on two segmentation networks perturbed with different initialization for the same input image. The pseudo one-hot label map, output from one perturbed segmentation network, is used to supervise the other segmentation network with the standard cross-entropy loss, and vice versa. The CPS consistency has two roles: encourage high similarity between the predictions of two perturbed networks for the same input image, and expand training data by using the unlabeled data with pseudo labels. Experiment results show that our approach achieves the state-of-the-art semi-supervised segmentation performance on Cityscapes and PASCAL VOC 2012. Code is available at https://git.io/CPS.