Please use this identifier to cite or link to this item:
Title: Meta-Transfer Learning for Few-Shot Learning
Authors: Qianru Sun 
Yaoyao Liu
Tat-Seng Chua 
Bernt Schiele
Keywords: Categorization
Deep Learning
Recognition: Detection
Issue Date: 16-Jun-2019
Publisher: IEEE Computer Society
Citation: Qianru Sun, Yaoyao Liu, Tat-Seng Chua, Bernt Schiele (2019-06-16). Meta-Transfer Learning for Few-Shot Learning. CVPR 2019 : 403-412. ScholarBank@NUS Repository.
Abstract: Meta-learning has been proposed as a framework to address the challenging few-shot learning setting. The key idea is to leverage a large number of similar few-shot tasks in order to learn how to adapt a base-learner to a new task for which only a few labeled samples are available. As deep neural networks (DNNs) tend to overfit using a few samples only, meta-learning typically uses shallow neural networks (SNNs), thus limiting its effectiveness. In this paper we propose a novel few-shot learning method called meta-transfer learning (MTL) which learns to adapt a deep NN for few shot learning tasks. Specifically, 'meta' refers to training multiple tasks, and 'transfer' is achieved by learning scaling and shifting functions of DNN weights for each task. In addition, we introduce the hard task (HT) meta-batch scheme as an effective learning curriculum for MTL. We conduct experiments using (5-class, 1-shot) and (5-class, 5-shot) recognition tasks on two challenging few-shot learning benchmarks: miniImageNet and Fewshot-CIFAR100. Extensive comparisons to related works validate that our meta-transfer learning approach trained with the proposed HT meta-batch scheme achieves top performance. An ablation study also shows that both components contribute to fast convergence and high accuracy. © 2019 IEEE.
Source Title: CVPR 2019
DOI: 10.1109/CVPR.2019.00049
Appears in Collections:Elements
Staff Publications

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
Sun_Meta-Transfer_Learning_for_Few-Shot_Learning_CVPR_2019_paper.pdf1.01 MBAdobe PDF




checked on Sep 21, 2020

Page view(s)

checked on Sep 24, 2020

Google ScholarTM



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.