Semi-supervised medical image classification via Cross-Training and Dual-Teacher fusion model

Yanyuan Chen, Dexuan Xu, Yiwei Lou, Hang Li, Weiping Ding, Yu Huang

Abstract: Highlights•A robust semi-supervised learning paradigm to unleash the potential of unlabeled data for better medical image classification.•Mitigate the issue of error accumulation in self-learning method through incorporating distinct models.•Fuse complementary knowledge from diverged teachers to alleviate confirmation biases.•Extensive experiments on two public benchmark medical image dataset to validate the effectiveness of proposed method.

External IDs:dblp:journals/inffus/ChenXLLDH25