Improving Semi-Supervised Semantic Segmentation with Dual-Level Siamese Structure Network

arXiv:2307.13938v2 Announce Type: replace
Abstract: Semi-supervised semantic segmentation (SSS) is an important task that utilizes both labeled and unlabeled data to reduce expenses on labeling training examples. However, the effectiveness of SSS algorithms is limited by the difficulty of fully exploiting the potential of unlabeled data. To address this, we propose a dual-level Siamese structure network (DSSN) for pixel-wise contrastive learning. By aligning positive pairs with a pixel-wise contrastive loss using strong augmented views in both low-level image space and …

arxiv cs.cv cs.lg improving network segmentation semantic semi-supervised type