Proceedings

Few-Shot Learning with Part Discovery and Augmentation from Unlabeled Images

Wentao Chen, Chenyang Si, Wei Wang, Liang Wang, Zilei Wang, Tieniu Tan

Download BibTeX Cite

Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence. Main Track. Pages 2271-2277.

https://doi.org/10.24963/ijcai.2021/313

Keywords

  • Machine Learning: Classification
  • Machine Learning: Deep Learning
  • Machine Learning: Unsupervised Learning

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.

Wentao Chen, Chenyang Si, Wei Wang, Liang Wang, Zilei Wang, and Tieniu Tan. 2021. Few-Shot Learning with Part Discovery and Augmentation from Unlabeled Images. In Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, IJCAI-21. IJCAI, 2271–2277. https://doi.org/10.24963/ijcai.2021/313
Welcome Future Conferences AI Journal Division IJCAI Proceedings About IJCAI IJCAI Awards