Cross-Domain Few-Shot Classification via Inter-Source Stylization

TL;DR

This paper introduces ISSNet, a method that uses unlabelled data from multiple source domains to improve cross-domain few-shot classification, effectively reducing domain gap impacts without extra labeling.

Contribution

The paper proposes a novel Inter-Source Stylization Network (ISSNet) that enhances data distribution and generalization using unlabelled source data in cross-domain few-shot learning.

Findings

ISSNet outperforms baseline methods on 8 datasets.

Utilizes unlabelled source data effectively.

Reduces negative effects of domain gaps.

Abstract

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.