핵심 개념
Flattening long-range loss landscapes in the representation space enhances transferability and fine-tuning in cross-domain few-shot learning.
통계
Cross-domain few-shot learning (CDFSL) aims to acquire knowledge from limited training data in the target domain.
Experimental results on 8 datasets demonstrate that the approach outperforms state-of-the-art methods in terms of average accuracy.
인용구
"Our contribution is the first to extend the analysis of loss landscapes from the parameter space to the representation space for the CDFSL task."
"Experimental results on 8 datasets demonstrate that our approach outperforms state-of-the-art methods in terms of average accuracy."