Alleviating the Sample Selection Bias in Few-shot Learning by Removing Projection to the CentroidDownload PDF

Published: 31 Oct 2022, 18:00, Last Modified: 12 Oct 2022, 08:46NeurIPS 2022 AcceptReaders: Everyone
Keywords: Few-shot learning, metric learning, image classification
TL;DR: This paper reveals that the linear classification boundary would be very sensitive to the position of support samples if they are in the vicinity of the task centroid and proposes a simple feature transformation to alleviate the sampling bias.
Abstract: Few-shot learning (FSL) targets at generalization of vision models towards unseen tasks without sufficient annotations. Despite the emergence of a number of few-shot learning methods, the sample selection bias problem, i.e., the sensitivity to the limited amount of support data, has not been well understood. In this paper, we find that this problem usually occurs when the positions of support samples are in the vicinity of task centroid—the mean of all class centroids in the task. This motivates us to propose an extremely simple feature transformation to alleviate this problem, dubbed Task Centroid Projection Removing (TCPR). TCPR is applied directly to all image features in a given task, aiming at removing the dimension of features along the direction of the task centroid. While the exact task centoid cannot be accurately obtained from limited data, we estimate it using base features that are each similar to one of the support features. Our method effectively prevents features from being too close to the task centroid. Extensive experiments over ten datasets from different domains show that TCPR can reliably improve classification accuracy across various feature extractors, training algorithms and datasets. The code has been made available at
Supplementary Material: zip
21 Replies