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

2022/04/28 by Jianrong Zhang, Zhang, Jianrong, Tianyi Wu +7 · 1 citation
Computer Science · #Advanced Neural Network Applications #Domain Adaptation and Few-Shot Learning #Multimodal Machine Learning Applications

paper · pdf · doi:10.48550/arxiv.2204.13314

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_num²). To address the issues, we propose a novel region-level contrastive and consistency learning framework (RC²L) 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 (RC²L) for semi-supervised semantic segmentation, and evaluate our RC²L on two challenging benchmarks (PASCAL VOC 2012 and Cityscapes), outperforming the state-of-the-art.

Cited by

• ClusterStyle: Modeling Intra-Style Diversity with Prototypical Clustering for Stylized Motion Generation

Related

• Pixel Contrastive-Consistent Semi-Supervised Semantic Segmentation
• Structured Consistency Loss for semi-supervised semantic segmentation
• Semi-supervised Semantic Segmentation with Prototype-based Consistency Regularization
• Bootstrapping Semantic Segmentation with Regional Contrast
• Semi-supervised Semantic Segmentation Meets Masked Modeling:Fine-grained Locality Learning Matters in Consistency Regularization