In semi-supervised semantic segmentation, the Mean Teacher- and co-training-based approaches are employed to mitigate confirmation bias and coupling problems. However, despite their high performance, these approaches frequently involve complex training pipelines and a substantial computational burden, limiting the scalability and compatibility of these methods. In this paper, we propose a PrevMatch framework that effectively mitigates the aforementioned limitations by maximizing the utilization of the temporal knowledge obtained during the training process. The PrevMatch framework relies on two core strategies: (1) we reconsider the use of temporal knowledge and thus directly utilize previous models obtained during training to generate additional pseudo-label guidance, referred to as previous guidance. (2) we design a highly randomized ensemble strategy to maximize the effectiveness of the previous guidance. Experimental results on four benchmark semantic segmentation datasets confirm that the proposed method consistently outperforms existing methods across various evaluation protocols. In particular, with DeepLabV3+ and ResNet-101 network settings, PrevMatch outperforms the existing state-of-the-art method, Diverse Co-training, by +1.6 mIoU on Pascal VOC with only 92 annotated images, while achieving 2.4 times faster training. Furthermore, the results indicate that PrevMatch induces stable optimization, particularly in benefiting classes that exhibit poor performance. Code is available at https://github.com/wooseok-shin/PrevMatch

提出了一种PrevMatch框架，通过最大化利用训练过程中获得的时间知识，有效地缓解了复杂的训练流程和计算负担所带来的限制，同时在各种评估协议上始终优于现有方法，特别是在DeepLabV3+和ResNet-101网络设置下，在只有92个标注图像的Pascal VOC数据集上，与现有最先进方法Diverse Co-training相比，mIoU提升了1.6，同时训练速度增快了2.4倍，并且结果表明PrevMatch能够稳定地优化，特别适用于性能较差的类别。

半监督语义分割中的时态知识重访与最大化