Region-level Contrastive and Consistency Learning for Semi-Supervised Semantic Segmentation

TL;DR

This paper introduces RC^2L, a novel region-level contrastive and consistency learning framework that improves semi-supervised semantic segmentation by addressing pixel-level noise sensitivity and computational costs.

Contribution

The paper proposes a new region-level contrastive and consistency learning framework with specific losses, outperforming existing methods on benchmark datasets.

Findings

Outperforms state-of-the-art on PASCAL VOC 2012

Outperforms state-of-the-art on Cityscapes

Addresses pixel-level noise and computational issues

Abstract

Current semi-supervised semantic segmentation methods mainly focus on designing pixel-level consistency and contrastive regularization. However, pixel-level regularization is sensitive to noise from pixels with incorrect predictions, and pixel-level contrastive regularization has memory and computational cost with O(pixel_num^2). To address the issues, we propose a novel region-level contrastive and consistency learning framework (RC^2L) for semi-supervised semantic segmentation. Specifically, we first propose a Region Mask Contrastive (RMC) loss and a Region Feature Contrastive (RFC) loss to accomplish region-level contrastive property. Furthermore, Region Class Consistency (RCC) loss and Semantic Mask Consistency (SMC) loss are proposed for achieving region-level consistency. Based on the proposed region-level contrastive and consistency regularization, we develop a region-level contrastive and consistency learning framework (RC^2L) for semi-supervised semantic segmentation, and evaluate our RC$^2$L on two challenging benchmarks (PASCAL VOC 2012 and Cityscapes), outperforming the state-of-the-art.