Cross-Domain Cross-Set Few-Shot Learning via Learning Compact and Aligned Representations
This addresses domain adaptation challenges in few-shot learning for AI systems, but it is incremental as it builds on existing cross-domain FSL work.
The paper tackles the problem of domain shift in few-shot learning by introducing a new cross-domain cross-set scenario, where models must adapt to new domains and maintain consistency across domains within each novel class, and proposes an approach that improves 5-shot accuracy by 6.0 points on average on DomainNet.
Few-shot learning (FSL) aims to recognize novel queries with only a few support samples through leveraging prior knowledge from a base dataset. In this paper, we consider the domain shift problem in FSL and aim to address the domain gap between the support set and the query set. Different from previous cross-domain FSL work (CD-FSL) that considers the domain shift between base and novel classes, the new problem, termed cross-domain cross-set FSL (CDSC-FSL), requires few-shot learners not only to adapt to the new domain, but also to be consistent between different domains within each novel class. To this end, we propose a novel approach, namely stabPA, to learn prototypical compact and cross-domain aligned representations, so that the domain shift and few-shot learning can be addressed simultaneously. We evaluate our approach on two new CDCS-FSL benchmarks built from the DomainNet and Office-Home datasets respectively. Remarkably, our approach outperforms multiple elaborated baselines by a large margin, e.g., improving 5-shot accuracy by 6.0 points on average on DomainNet. Code is available at https://github.com/WentaoChen0813/CDCS-FSL