Deep neural networks (DNNs) have witnessed great successes in semantic segmentation, which requires a large number of labeled data for training. We present a novel learning framework called Uncertainty guided Cross-head Co-training (UCC) for semi-supervised semantic segmentation. Our framework introduces weak and strong augmentations within a shared encoder to achieve co-training, which naturally combines the benefits of consistency and self-training. Every segmentation head interacts with its peers and, the weak augmentation result is used for supervising the strong. The consistency training samples' diversity can be boosted by Dynamic Cross-Set Copy-Paste (DCSCP), which also alleviates the distribution mismatch and class imbalance problems. Moreover, our proposed Uncertainty Guided Re-weight Module (UGRM) enhances the self-training pseudo labels by suppressing the effect of the low-quality pseudo labels from its peer via modeling uncertainty. Extensive experiments on Cityscapes and PASCAL VOC 2012 demonstrate the effectiveness of our UCC. Our approach significantly outperforms other state-of-the-art semi-supervised semantic segmentation methods. It achieves 77.17$\%$, 76.49$\%$ mIoU on Cityscapes and PASCAL VOC 2012 datasets respectively under 1/16 protocols, which are +10.1$\%$, +7.91$\%$ better than the supervised baseline.

翻译：深度神经网络在需要大量标注数据进行训练的语义分割任务中取得了显著成功。我们提出了一种名为不确定性引导的交叉头协同训练（UCC）的新型学习框架用于半监督语义分割。该框架在共享编码器内引入弱增强与强增强实现协同训练，自然融合了一致性训练和自训练的优势。每个分割头部与其对应部分相互交互，弱增强结果用于监督强增强训练。通过动态跨集复制粘贴（DCSCP）增强一致性训练样本多样性，同时缓解分布不匹配和类别不平衡问题。此外，我们提出的不确定性引导加权模块（UGRM）通过对齐头部间的建模不确定性来抑制低质量伪标签的影响，从而提升自训练伪标签质量。在Cityscapes和PASCAL VOC 2012数据集上的大量实验证明了UCC的有效性。我们的方法在半监督语义分割任务中显著优于其他最先进方法。在1/16标注协议下，它在Cityscapes和PASCAL VOC 2012数据集上分别达到77.17%、76.49%的平均交并比（mIoU），比监督基线提升了+10.1%、+7.91%。