AISTATS 2024poster0 citations

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

Marzi Heidari, Abdullah Alchihabi, Qing En, Yuhong Guo

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 to many state-of-the-art cross-domain few-shot learning methods.

BibTeX
@InProceedings{pmlr-v238-heidari24a,
  title = 	 {Adaptive Parametric Prototype Learning for Cross-Domain Few-Shot Classification},
  author =       {Heidari, Marzi and Alchihabi, Abdullah and En, Qing and Guo, Yuhong},
  booktitle = 	 {Proceedings of The 27th International Conference on Artificial Intelligence and Statistics},
  pages = 	 {1369--1377},
  year = 	 {2024},
  editor = 	 {Dasgupta, Sanjoy and Mandt, Stephan and Li, Yingzhen},
  volume = 	 {238},
  series = 	 {Proceedings of Machine Learning Research},
  month = 	 {02--04 May},
  publisher =    {PMLR},
  pdf = 	 {https://proceedings.mlr.press/v238/heidari24a/heidari24a.pdf},
  url = 	 {https://proceedings.mlr.press/v238/heidari24a.html},
  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 to many state-of-the-art cross-domain few-shot learning methods.}
}