Discriminative Sample-Guided and Parameter-Efficient Feature Space Adaptation for Cross-Domain Few-Shot Learning

arXiv:2403.04492v1 Announce Type: new
Abstract: In this paper, we look at cross-domain few-shot classification which presents the challenging task of learning new classes in unseen domains with few labelled examples. Existing methods, though somewhat effective, encounter several limitations, which we address in this work through two significant improvements. First, to address overfitting associated with fine-tuning a large number of parameters on small datasets, we introduce a lightweight parameter-efficient adaptation strategy. This strategy employs a linear transformation of pre-trained features, significantly …

arxiv cs.cv domain feature few-shot few-shot learning sample space type