BMPCN: A Bigraph Mutual Prototype Calibration Net for few-shot classification

Jing Zhang, Mingzhe Chen, Yunzuo Hu, Xinzhou Zhang, Zhe Wang

Abstract: Highlights•A bigraph mutual prototype calibration net is proposed for few-shot classification.•A bigraph interactive augmentation module is proposed to realize mutual guidance.•A proto-level similarity with task-specific information is proposed.•An instance-level similarity with potential correlations is proposed.