CASIA OpenIR  > 模式识别国家重点实验室  > 三维可视计算
LGM-Net: Learning to Generate Matching Networks for Few-Shot Learning
Huaiyu Li; Weiming Dong; Xing Mei; Chongyang Ma; Feiyue Huang; Bao-Gang Hu
Conference Name36th International Conference on Machine Learning (ICML)
Source PublicationInternational Conference on Machine Learning
Conference Date2019-6
Conference PlaceLong Beach, CA, USA

In this work, we propose a novel meta-learning approach for few-shot classification, which learns transferable prior knowledge across tasks and directly produces network parameters for similar unseen tasks with training samples. Our approach, called LGM-Net, includes two key modules, namely, TargetNet and MetaNet. The TargetNet module is a neural network for solving a specific task and the MetaNet module aims at learning to generate functional weights for TargetNet by observing training samples. We also present an intertask normalization strategy for the training process to leverage common information shared across different tasks. The experimental results on Omniglot and miniImageNet datasets demonstrate that LGM-Net can effectively adapt to similar unseen tasks and achieve competitive performance, and the results on synthetic datasets show that transferable prior knowledge is learned by the MetaNet module via mapping training data to functional weights. LGM-Net enables fast learning and adaptation since no further tuning steps are required compared to other metalearning approaches.

Indexed ByEI
Document Type会议论文
Affiliation1.National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences
2.University of Chinese Academy of Sciences
3.Snap Inc.
4.Kwai Inc.
5.Youtu Lab, Tencent
Recommended Citation
GB/T 7714
Huaiyu Li,Weiming Dong,Xing Mei,et al. LGM-Net: Learning to Generate Matching Networks for Few-Shot Learning[C],2019:3825-3834.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Huaiyu Li]'s Articles
[Weiming Dong]'s Articles
[Xing Mei]'s Articles
Baidu academic
Similar articles in Baidu academic
[Huaiyu Li]'s Articles
[Weiming Dong]'s Articles
[Xing Mei]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Huaiyu Li]'s Articles
[Weiming Dong]'s Articles
[Xing Mei]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.

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