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 reducing the trainable parameter count. Second, we replace the traditional nearest centroid classifier with a variance-aware loss function, enhancing the model's sensitivity to the inter- and intra-class variances within the training set for improved clustering in feature space. Empirical evaluations on the Meta-Dataset benchmark showcase that our approach not only improves accuracy up to 7.7% and 5.3% on seen and unseen datasets respectively but also achieves this performance while being at least ~3x more parameter-efficient than existing methods, establishing a new state-of-the-art in cross-domain few-shot learning. Our code can be found at https://github.com/rashindrie/DIPA.

翻译：本文研究跨域小样本分类问题，该问题要求在未见领域中使用少量标注样本学习新类别。现有方法虽有一定效果，但存在若干局限，本研究通过两项重要改进加以解决。首先，针对小数据集微调大量参数导致的过拟合现象，我们提出轻量级参数高效适配策略，该方法通过对预训练特征进行线性变换，显著减少可训练参数数量。其次，我们采用方差感知损失函数替代传统最近质心分类器，增强模型对训练集内类间/类内方差的敏感性，从而提升特征空间中的聚类效果。在Meta-Dataset基准上的实验表明，本方法在已见和未见数据集上分别最高提升7.7%和5.3%的准确率，同时实现至少约3倍于现有方法的参数效率，确立了跨域小样本学习领域的最新最佳性能。相关代码已开源至https://github.com/rashindrie/DIPA。