Few-Shot Learning with Part Discovery and Augmentation from Unlabeled Images
Abstract
Few-shot learning is a challenging task since only few instances are given for recognizing an unseen class. One way to alleviate this problem is to acquire a strong inductive bias via meta-learning on similar tasks. In this paper, we show that such inductive bias can be learned from a flat collection of unlabeled images, and instantiated as transferable representations among seen and unseen classes. Specifically, we propose a novel part-based self-supervised representation learning scheme to learn transferable representations by maximizing the similarity of an image to its discriminative part. To mitigate the overfitting in few-shot classification caused by data scarcity, we further propose a part augmentation strategy by retrieving extra images from a base dataset. We conduct systematic studies on miniImageNet and tieredImageNet benchmarks. Remarkably, our method yields impressive results, outperforming the previous best unsupervised methods by 7.74% and 9.24% under 5-way 1-shot and 5-way 5-shot settings, which are comparable with state-of-the-art supervised methods.
Keywords
Cite
@article{arxiv.2105.11874,
title = {Few-Shot Learning with Part Discovery and Augmentation from Unlabeled Images},
author = {Wentao Chen and Chenyang Si and Wei Wang and Liang Wang and Zilei Wang and Tieniu Tan},
journal= {arXiv preprint arXiv:2105.11874},
year = {2021}
}
Comments
Accepted by IJCAI 2021