UCC: Uncertainty guided Cross-head Cotraining for Semi-Supervised Semantic Segmentation

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 Cotraining (UCC) for semi-supervised semantic segmentation. Our framework introduces weak and strong augmentations within a shared encoder to achieve cotraining, 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.