IPixMatch: Boost Semi-supervised Semantic Segmentation with Inter-Pixel Relation

arXiv:2404.18891v1 Announce Type: cross
Abstract: The scarcity of labeled data in real-world scenarios is a critical bottleneck of deep learning's effectiveness. Semi-supervised semantic segmentation has been a typical solution to achieve a desirable tradeoff between annotation cost and segmentation performance. However, previous approaches, whether based on consistency regularization or self-training, tend to neglect the contextual knowledge embedded within inter-pixel relations. This negligence leads to suboptimal performance and limited generalization. In this paper, we propose a novel approach IPixMatch designed to …

abstract annotation arxiv boost cost cs.ai cs.cv cs.lg data deep learning however performance pixel regularization segmentation self-training semantic semi-supervised solution training type world