2019/05/15 by Huaiyu Li, Weiming Dong, Li, Huaiyu +9 · 1 citation
Computer Science · Mathematics · #Advanced Neural Network Applications #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Multimodal Machine Learning Applications #cs.LG #stat.ML
paper · pdf · doi:10.48550/arxiv.1905.06331
To appear in ICML2019
arxiv created 2019/05/15 · openalex publication_date 2019/05/15 · arxiv updated 2019/05/17 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
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 meta-learning approaches.