Skip to main content
placeholder image

Asymmetric distribution measure for few-shot learning

Conference Paper


Abstract


  • The core idea of metric-based few-shot image classification is to directly measure the relations between query images and support classes to learn transferable feature embeddings. Previous work mainly focuses on image-level feature representations, which actually cannot effectively estimate a class's distribution due to the scarcity of samples. Some recent work shows that local descriptor based representations can achieve richer representations than image-level based representations. However, such works are still based on a less effective instance-level metric, especially a symmetric metric, to measure the relation between a query image and a support class. Given the natural asymmetric relation between a query image and a support class, we argue that an asymmetric measure is more suitable for metric-based few-shot learning. To that end, we propose a novel Asymmetric Distribution Measure (ADM) network for few-shot learning by calculating a joint local and global asymmetric measure between two multivariate local distributions of a query and a class. Moreover, a task-aware Contrastive Measure Strategy (CMS) is proposed to further enhance the measure function. On popular miniImageNet and tieredImageNet, ADM can achieve the state-of-the-art results, validating our innovative design of asymmetric distribution measures for few-shot learning. The source code can be downloaded from https://github.com/WenbinLee/ADM.git.

Publication Date


  • 2020

Citation


  • Li, W., Wang, L., Huo, J., Shi, Y., Gao, Y., & Luo, J. (2020). Asymmetric distribution measure for few-shot learning. In IJCAI International Joint Conference on Artificial Intelligence Vol. 2021-January (pp. 2957-2963).

Scopus Eid


  • 2-s2.0-85097349228

Web Of Science Accession Number


Start Page


  • 2957

End Page


  • 2963

Volume


  • 2021-January

Abstract


  • The core idea of metric-based few-shot image classification is to directly measure the relations between query images and support classes to learn transferable feature embeddings. Previous work mainly focuses on image-level feature representations, which actually cannot effectively estimate a class's distribution due to the scarcity of samples. Some recent work shows that local descriptor based representations can achieve richer representations than image-level based representations. However, such works are still based on a less effective instance-level metric, especially a symmetric metric, to measure the relation between a query image and a support class. Given the natural asymmetric relation between a query image and a support class, we argue that an asymmetric measure is more suitable for metric-based few-shot learning. To that end, we propose a novel Asymmetric Distribution Measure (ADM) network for few-shot learning by calculating a joint local and global asymmetric measure between two multivariate local distributions of a query and a class. Moreover, a task-aware Contrastive Measure Strategy (CMS) is proposed to further enhance the measure function. On popular miniImageNet and tieredImageNet, ADM can achieve the state-of-the-art results, validating our innovative design of asymmetric distribution measures for few-shot learning. The source code can be downloaded from https://github.com/WenbinLee/ADM.git.

Publication Date


  • 2020

Citation


  • Li, W., Wang, L., Huo, J., Shi, Y., Gao, Y., & Luo, J. (2020). Asymmetric distribution measure for few-shot learning. In IJCAI International Joint Conference on Artificial Intelligence Vol. 2021-January (pp. 2957-2963).

Scopus Eid


  • 2-s2.0-85097349228

Web Of Science Accession Number


Start Page


  • 2957

End Page


  • 2963

Volume


  • 2021-January