Confusable Learning for Large-Class Few-Shot Classification
Abstract
Few-shot image classification is challenging due to the lack of ample samples in each class. Such a challenge becomes even tougher when the number of classes is very large, i.e., the large-class few-shot scenario. In this novel scenario, existing approaches do not perform well because they ignore confusable classes, namely similar classes that are difficult to distinguish from each other. These classes carry more information. In this paper, we propose a biased learning paradigm called Confusable Learning, which focuses more on confusable classes. Our method can be applied to mainstream meta-learning algorithms. Specifically, our method maintains a dynamically updating confusion matrix, which analyzes confusable classes in the dataset. Such a confusion matrix helps meta learners to emphasize on confusable classes. Comprehensive experiments on Omniglot, Fungi, and ImageNet demonstrate the efficacy of our method over state-of-the-art baselines.
Cite
Text
Li et al. "Confusable Learning for Large-Class Few-Shot Classification." European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2020. doi:10.1007/978-3-030-67661-2_42Markdown
[Li et al. "Confusable Learning for Large-Class Few-Shot Classification." European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2020.](https://mlanthology.org/ecmlpkdd/2020/li2020ecmlpkdd-confusable/) doi:10.1007/978-3-030-67661-2_42BibTeX
@inproceedings{li2020ecmlpkdd-confusable,
title = {{Confusable Learning for Large-Class Few-Shot Classification}},
author = {Li, Bingcong and Han, Bo and Wang, Zhuowei and Jiang, Jing and Long, Guodong},
booktitle = {European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases},
year = {2020},
pages = {707-723},
doi = {10.1007/978-3-030-67661-2_42},
url = {https://mlanthology.org/ecmlpkdd/2020/li2020ecmlpkdd-confusable/}
}