Bi-Level Meta-Learning for Few-Shot Domain Generalization

no code implementations • CVPR 2023 • Xiaorong Qin, Xinhang Song, Shuqiang Jiang

We address FSDG problem by meta-learning two levels of meta-knowledge, where the lower-level meta-knowledge are domain-specific embedding spaces as subspaces of a base space for intra-domain generalization, and the upper-level meta-knowledge is the base space and a prior subspace over domain-specific spaces for inter-domain generalization.

Domain Generalization Few-Shot Learning