Recently, significant progress has been made on semantic segmentation. However, the success of supervised semantic segmentation typically relies on a large amount of labelled data, which is time-consuming and costly to obtain. Inspired by the success of semi-supervised learning methods in image classification, here we propose a simple yet effective semi-supervised learning framework for semantic segmentation. We demonstrate that the devil is in the details: a set of simple design and training techniques can collectively improve the performance of semi-supervised semantic segmentation significantly. Previous works [3, 27] fail to employ strong augmentation in pseudo label learning efficiently, as the large distribution change caused by strong augmentation harms the batch normalisation statistics. We design a new batch normalisation, namely distribution-specific batch normalisation (DSBN) to address this problem and demonstrate the importance of strong augmentation for semantic segmentation. Moreover, we design a self correction loss which is effective in noise resistance. We conduct a series of ablation studies to show the effectiveness of each component. Our method achieves state-of-the-art results in the semi-supervised settings on the Cityscapes and Pascal VOC datasets.
翻译:最近,在语义分解方面取得了显著进展。然而,受监督语义分解的成功通常依赖于大量贴标签的数据,这些数据耗时费时费钱。受半受监督的图像分类学习方法的成功启发,我们在此提出一个简单而有效的半受监督的语义分解学习框架。我们证明魔鬼在细节中:一套简单的设计和培训技术能够集体改善半受监督的语义分解的性能。以前的作品[3,27]未能在假名学习中有效地运用强大的增益,因为强劲增长造成的大规模分布变化损害了批次正常化统计。我们设计了新的批次正常化,即分批正常化(DSBN),以解决这一问题,并表明大力增强语义分解的重要性。此外,我们设计了一种自我纠正损失的方法,以有效抵抗噪音。我们进行了一系列的反动研究,以显示每个组成部分的有效性。我们的方法在半受监督的城市和动画图中取得了最新结果。