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

Abstract

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-weig