2019/12/19 by Zhongjie Yu, Yu, Zhongjie, Lin Chen +5 · 7 citations
Biochemistry, Genetics and Molecular Biology · Computer Science · Mathematics · #Artificial intelligence #Artificial neural network #Benchmark (surveying) #Cancer-related molecular mechanisms research #Class (philosophy) #Classifier (UML) #Computer Vision and Pattern Recognition (cs.CV) #Computer science #Domain Adaptation and Few-Shot Learning #Extractor #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Machine learning #Multi-task learning #Multimodal Machine Learning Applications #Pattern recognition (psychology) #Semi-supervised learning #Supervised learning #Task (project management) #Transfer of learning #cs.CV #cs.LG #stat.ML
paper · pdf · doi:10.48550/arxiv.1912.09033
published in arXiv (Cornell University) (Cornell University) · Accepted at CVPR2020
openalex publication_date 2019/12/19 · openalex created_date 2019/12/26 · arxiv created 2020/03/09 · arxiv updated 2020/03/11 · openalex updated_date 2026/08/05
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 learning, CUB-200-2011 and miniImageNet, demonstrate that our proposed method can effectively utilize the auxiliary information from labeled base-class data and unlabeled novel-class data to significantly improve the accuracy of few-shot learning task.