Cross-Domain Few-Shot Classification via Inter-Source Stylization
This addresses the problem of few-shot classification across different domains for machine learning practitioners, offering an incremental improvement by leveraging unlabeled data without extra labeling costs.
The paper tackles cross-domain few-shot classification by proposing an Inter-Source Stylization Network (ISSNet) that uses one labeled and multiple unlabeled source domains to enrich data distribution, improving generalization; experiments on 8 target datasets show it significantly reduces domain gap impact compared to baselines.
The goal of Cross-Domain Few-Shot Classification (CDFSC) is to accurately classify a target dataset with limited labelled data by exploiting the knowledge of a richly labelled auxiliary dataset, despite the differences between the domains of the two datasets. Some existing approaches require labelled samples from multiple domains for model training. However, these methods fail when the sample labels are scarce. To overcome this challenge, this paper proposes a solution that makes use of multiple source domains without the need for additional labeling costs. Specifically, one of the source domains is completely tagged, while the others are untagged. An Inter-Source Stylization Network (ISSNet) is then introduced to enhance stylisation across multiple source domains, enriching data distribution and model's generalization capabilities. Experiments on 8 target datasets show that ISSNet leverages unlabelled data from multiple source data and significantly reduces the negative impact of domain gaps on classification performance compared to several baseline methods.