Flatten Long-Range Loss Landscapes for Cross-Domain Few-Shot Learning

arXiv:2403.00567v1 Announce Type: new
Abstract: Cross-domain few-shot learning (CDFSL) aims to acquire knowledge from limited training data in the target domain by leveraging prior knowledge transferred from source domains with abundant training samples. CDFSL faces challenges in transferring knowledge across dissimilar domains and fine-tuning models with limited training data. To address these challenges, we initially extend the analysis of loss landscapes from the parameter space to the representation space, which allows us to simultaneously interpret the transferring and fine-tuning difficulties …

abstract arxiv challenges cs.ai cs.cv data domain domains few-shot few-shot learning fine-tuning flatten knowledge loss prior samples training training data type