We present a novel confidence refinement scheme that enhances pseudo labels in semi-supervised semantic segmentation. Unlike existing methods, which filter pixels with low-confidence predictions in isolation, our approach leverages the spatial correlation of labels in segmentation maps by grouping neighboring pixels and considering their pseudo labels collectively. With this contextual information, our method, named S4MC, increases the amount of unlabeled data used during training while maintaining the quality of the pseudo labels, all with negligible computational overhead. Through extensive experiments on standard benchmarks, we demonstrate that S4MC outperforms existing state-of-the-art semi-supervised learning approaches, offering a promising solution for reducing the cost of acquiring dense annotations. For example, S4MC achieves a 1.39 mIoU improvement over the prior art on PASCAL VOC 12 with 366 annotated images. The code to reproduce our experiments is available at https://s4mcontext.github.io/

翻译：我们提出了一种新颖的置信度优化方案，用于增强半监督语义分割中的伪标签。与现有方法孤立地过滤低置信度预测像素不同，我们的方法通过将相邻像素分组并集体考虑其伪标签，利用了分割图中标签的空间相关性。借助这种上下文信息，我们的方法（命名为S4MC）在保持伪标签质量的同时，增加了训练期间使用的未标记数据量，且计算开销可忽略不计。通过在标准基准上进行大量实验，我们证明S4MC优于现有的最先进半监督学习方法，为降低密集标注获取成本提供了一个有前景的解决方案。例如，在PASCAL VOC 12数据集上仅使用366张标注图像时，S4MC相较于先前最佳方法实现了1.39 mIoU的提升。重现我们实验的代码可在 https://s4mcontext.github.io/ 获取。