ZooKT: Task-adaptive knowledge transfer of Model Zoo for few-shot learning

Baoquan Zhang, Bingqi Shan, Aoxue Li, Chuyao Luo, Yunming Ye, Zhenguo Li

Abstract: Highlights•We formulate a new FSL setting, i.e., Model-Zoo-based FSL (MZFSL).•We propose a novel FSL framework, i.e., ZooKT, which amalgamates knowledge of model zoo to learn to extract transferable visual features.•Experimental results on multiple datasets show that our method achieves superior performance.