LGM-Net: Learning to Generate Matching Networks for Few-Shot Learning | |
Huaiyu Li; Weiming Dong; Xing Mei; Chongyang Ma; Feiyue Huang; Bao-Gang Hu | |
2019-06 | |
会议日期 | 2019-6 |
会议地点 | Long Beach, CA, USA |
页码 | 3825-3834 |
英文摘要 | 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. |
会议录 | International Conference on Machine Learning |
内容类型 | 会议论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/23908] |
专题 | 多媒体计算与图形学团队 |
作者单位 | 1.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 |
推荐引用方式 GB/T 7714 | Huaiyu Li,Weiming Dong,Xing Mei,et al. LGM-Net: Learning to Generate Matching Networks for Few-Shot Learning[C]. 见:. Long Beach, CA, USA. 2019-6. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论