In this paper, we present a simple but performant semi-supervised semantic segmentation approach, termed CorrMatch. Our goal is to mine more high-quality regions from the unlabeled images to leverage the unlabeled data more efficiently via consistency regularization. The key contributions of our CorrMatch are two novel and complementary strategies. First, we introduce an adaptive threshold updating strategy with a relaxed initialization to expand the high-quality regions. Furthermore, we propose to propagate high-confidence predictions through measuring the pairwise similarities between pixels. Despite its simplicity, we show that CorrMatch achieves great performance on popular semi-supervised semantic segmentation benchmarks. Taking the DeepLabV3+ framework with ResNet-101 backbone as our segmentation model, we receive a 76%+ mIoU score on the Pascal VOC 2012 segmentation benchmark with only 92 annotated images provided. We also achieve a consistent improvement over previous semi-supervised semantic segmentation models. Code will be made publicly available.

翻译：本文提出一种简单而高效的半监督语义分割方法，名为CorrMatch。我们的目标是通过一致性正则化从无标签图像中挖掘更多高质量区域，从而更有效地利用无标签数据。CorrMatch的核心贡献在于两种新颖且互补的策略：首先，我们引入一种带有松弛初始化的自适应阈值更新策略，以扩展高质量区域；其次，我们提出通过测量像素间的成对相似性来传播高置信度预测。尽管方法简洁，但实验表明CorrMatch在主流半监督语义分割基准上取得了优异性能。以采用ResNet-101骨干网络的DeepLabV3+框架作为分割模型，在仅提供92张标注图像的Pascal VOC 2012分割基准上，我们获得了76%+的mIoU分数。此外，我们相较于先前半监督语义分割模型实现了持续改进。代码将公开发布。