Skip to yearly menu bar Skip to main content


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

Marzi Heidari · Abdullah Alchihabi · Qing En · Yuhong Guo

MR1 & MR2 - Number 40
[ ]
Thu 2 May 8 a.m. PDT — 8:30 a.m. PDT


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.

Live content is unavailable. Log in and register to view live content