← Search

Liang Lv

2 accepted papers

2025

ScaleMatch: Multi-scale Consistency Enhancement for Semi-supervised Semantic Segmentation

AAAI 2025technical

Semi-supervised learning improves semantic segmentation performance by leveraging unlabeled data, thereby significantly reducing labeling costs. Previous semi-supervised semantic segmentation (S4) methods explored perturbations at the image level but neglected to adequately utilize multi-scale infor…