English

Adaptive Parametric Prototype Learning for Cross-Domain Few-Shot Classification

Computer Vision and Pattern Recognition 2023-09-06 v1 Machine Learning

Abstract

Cross-domain few-shot classification induces a much more challenging problem than its in-domain counterpart due to the existence of domain shifts between the training and test tasks. In this paper, we develop a novel Adaptive Parametric Prototype Learning (APPL) method under the meta-learning convention for cross-domain few-shot classification. Different from existing prototypical few-shot methods that use the averages of support instances to calculate the class prototypes, we propose to learn class prototypes from the concatenated features of the support set in a parametric fashion and meta-learn the model by enforcing prototype-based regularization on the query set. In addition, we fine-tune the model in the target domain in a transductive manner using a weighted-moving-average self-training approach on the query instances. We conduct experiments on multiple cross-domain few-shot benchmark datasets. The empirical results demonstrate that APPL yields superior performance than many state-of-the-art cross-domain few-shot learning methods.

Keywords

Cite

@article{arxiv.2309.01342,
  title  = {Adaptive Parametric Prototype Learning for Cross-Domain Few-Shot Classification},
  author = {Marzi Heidari and Abdullah Alchihabi and Qing En and Yuhong Guo},
  journal= {arXiv preprint arXiv:2309.01342},
  year   = {2023}
}
R2 v1 2026-06-28T12:11:47.536Z