BFRA: A Bi-level Feature Relation Alignment Method for Cross-Domain Few-Shot Learning

While existing Few-Shot Learning (FSL) techniques demonstrate strong performance on uniform datasets, they encounter domain shift challenges when presented with domainagnostic queries in real-world scenarios. So we investigate it in Cross-Domain Few-Shot Learning (CD-FSL) and propose to learn more universal feature representations to enhance generalization on unseen domains. Toward this issue, we pinpoint two issues in current multi-model fusion approaches: 1) the entanglement of domain and class information, and 2) feature overlap across distinct domains. To address these challenges, we introduce a Bi-level Feature Relation Alignment method, BFRA, which facilitates the acquisition of more versatile features by decoupling domain-class relationships and aligning feature relations. Through the segregation of domain and class feature learning, we devise a smoothing layer prior for domain feature alignment to mitigate inter-domain discrepancies. This approach enables our model to acquire domain-consistent features, diminishing interference in subsequent class feature alignment procedures. During the class feature alignment, we notice that class feature representations from various in-domain models may intersect, leading to a diminished distinction between classes. To address this, we adopt a topological perspective to train our target model, by aligning feature relations instead of features between our target model and multiple in-domain models. The integration of these components results in the establishment of a bi-level feature relation alignment framework aimed at acquiring more universal features. Furthermore, we partially fine-tune the plug-in layer-wise affine adapter on domain-agnostic queries to expedite adaptation without impacting the known domains. Experiments of 21 datasets on meta-dataset and BSCD-FSL benchmark demonstrate the effectiveness of our method. The code are made publicly available at https://github.com/leaves162/BFRA.