Few-Shot Learning with Part Discovery and Augmentation from Unlabeled Images
Few-Shot Learning with Part Discovery and Augmentation from Unlabeled Images
Wentao Chen, Chenyang Si, Wei Wang, Liang Wang, Zilei Wang, Tieniu Tan
Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence
Main Track. Pages 2271-2277.
https://doi.org/10.24963/ijcai.2021/313
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:
Machine Learning: Unsupervised Learning
Machine Learning: Classification
Machine Learning: Deep Learning