Blessing few-shot segmentation via semi-supervised learning with noisy support images

Runtong Zhang, Hongyuan Zhu, Hanwang Zhang, Chen Gong, Joey Tianyi Zhou, Fanman Meng

Abstract: Highlights•Incorporating semi-supervised learning into few-shot task to tackle data scarcity.•A ranking algorithm to identify and remove noisy samples in pseudo labels.•Explaining the algorithm using a Structural Causal Model to reduce confounding bias.