Can I read TransMatch: A Transfer-Learning Scheme for Semi-Supervised Few-Shot Learning on EtoBox?

TransMatch: A Transfer-Learning Scheme for Semi-Supervised Few-Shot Learning by Yu, Zhongjie; Chen, Lin; Cheng, Zhongwei; Luo, Jiebo is a scholarly article available to read on EtoBox.

What is TransMatch: A Transfer-Learning Scheme for Semi-Supervised Few-Shot Learning about?

The successful application of deep learning to many visual recognition tasks relies heavily on the availability of a large amount of labeled data which is usually expensive to obtain. The few-shot learning problem has attracted increasing attention from researchers for building a robust model upon only a few labeled samples. Most existing works tackle this problem under the meta-learning framework by mimicking the few-shot learning task with an episodic training strategy. In this paper, we propose a new transfer-learning framework for semi-supervised few-shot learning to fully utilize the auxiliary information from labeled base-class data and unlabeled novel-class data. The framework consists of three components: 1) pre-training a feature extractor on base-class data; 2) using the feature extractor to initialize the classifier weights for the novel classes; and 3) further updating the model with a semi-supervised learning method. Under the proposed framework, we develop a novel method for semi-supervised few-shot learning called TransMatch by instantiating the three components with Imprinting and MixMatch. Extensive experiments on two popular benchmark datasets for few-shot learnin

Author

Yu, Zhongjie; Chen, Lin; Cheng, Zhongwei; Luo, Jiebo

Published

2019

Language

EN