Feature Transformation for Few-Shot Learning

The goal of few-shot learning is to classify new classes of samples with a few labeled training samples. State-ofthe-art few-shot learners train a backbone on sufficient datasets and use its extracted features for classification. However, biased data distributions can lead to severe overfitting in few-shot learning. In this paper, we propose a novel feature transformation method that utilizes the statistical characteristics of sufficient data to perform feature transformation on few-shot data to alleviate overfitting caused by biased data distributions. We show an interesting phenomenon that removing the component along the mean feature of the base classes in meta-testing improves the performance for few-shot learning. Our method can be used on off-the-shelf pretrained feature extractors without extra parameters. We show that our method achieves the new state-ofthe-art accuracy in the prototype-based method and comparable accuracy with state-of-the-art accuracy in the optimization-based method.