Skip to main content
placeholder image

Distribution consistency based covariance metric networks for few-shot learning

Conference Paper


Abstract


  • Few-shot learning aims to recognize new concepts from very few examples. However, most of the existing few-shot learning methods mainly concentrate on the first-order statistic of concept representation or a fixed metric on the relation between a sample and a concept. In this work, we propose a novel end-to-end deep architecture, named Covariance Metric Networks (CovaMNet). The CovaMNet is designed to exploit both the covariance representation and covariance metric based on the distribution consistency for the few-shot classification tasks. Specifically, we construct an embedded local covariance representation to extract the second-order statistic information of each concept and describe the underlying distribution of this concept. Upon the covariance representation, we further define a new deep covariance metric to measure the consistency of distributions between query samples and new concepts. Furthermore, we employ the episodic training mechanism to train the entire network in an end-to-end manner from scratch. Extensive experiments in two tasks, generic few-shot image classification and fine-grained few-shot image classification, demonstrate the superiority of the proposed CovaMNet. The source code can be available from https://github.com/WenbinLee/CovaMNet.git.

Publication Date


  • 2019

Citation


  • Li, W., Xu, J., Huo, J., Wang, L., Gao, Y., & Luo, J. (2019). Distribution consistency based covariance metric networks for few-shot learning. In 33rd AAAI Conference on Artificial Intelligence, AAAI 2019, 31st Innovative Applications of Artificial Intelligence Conference, IAAI 2019 and the 9th AAAI Symposium on Educational Advances in Artificial Intelligence, EAAI 2019 (pp. 8642-8649).

Scopus Eid


  • 2-s2.0-85089434248

Start Page


  • 8642

End Page


  • 8649

Abstract


  • Few-shot learning aims to recognize new concepts from very few examples. However, most of the existing few-shot learning methods mainly concentrate on the first-order statistic of concept representation or a fixed metric on the relation between a sample and a concept. In this work, we propose a novel end-to-end deep architecture, named Covariance Metric Networks (CovaMNet). The CovaMNet is designed to exploit both the covariance representation and covariance metric based on the distribution consistency for the few-shot classification tasks. Specifically, we construct an embedded local covariance representation to extract the second-order statistic information of each concept and describe the underlying distribution of this concept. Upon the covariance representation, we further define a new deep covariance metric to measure the consistency of distributions between query samples and new concepts. Furthermore, we employ the episodic training mechanism to train the entire network in an end-to-end manner from scratch. Extensive experiments in two tasks, generic few-shot image classification and fine-grained few-shot image classification, demonstrate the superiority of the proposed CovaMNet. The source code can be available from https://github.com/WenbinLee/CovaMNet.git.

Publication Date


  • 2019

Citation


  • Li, W., Xu, J., Huo, J., Wang, L., Gao, Y., & Luo, J. (2019). Distribution consistency based covariance metric networks for few-shot learning. In 33rd AAAI Conference on Artificial Intelligence, AAAI 2019, 31st Innovative Applications of Artificial Intelligence Conference, IAAI 2019 and the 9th AAAI Symposium on Educational Advances in Artificial Intelligence, EAAI 2019 (pp. 8642-8649).

Scopus Eid


  • 2-s2.0-85089434248

Start Page


  • 8642

End Page


  • 8649