LGM-Net: Learning to Generate Matching Networks for Few-Shot Learning

Abstract

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.

arXiv commentTo appear in ICML2019

Cited by in corpus (16)

• BSNet: Bi-Similarity Network for Few-shot Fine-grained Image Classification
• An Ensemble of Epoch-wise Empirical Bayes for Few-shot Learning
• Learning to Warm Up Cold Item Embeddings for Cold-start Recommendation with Meta Scaling and Shifting Networks
• Interventional Few-Shot Learning
• Sparse Spatial Transformers for Few-Shot Learning
• Transforming task representations to perform novel tasks
• MCML: A Novel Memory-based Contrastive Meta-Learning Method for Few Shot Slot Tagging
• A Concise Review of Recent Few-shot Meta-learning Methods
• On the Importance of Firth Bias Reduction in Few-Shot Classification
• Revisiting Metric Learning for Few-Shot Image Classification
• Parameter Prediction for Unseen Deep Architectures
• Few-Shot Learning with Intra-Class Knowledge Transfer
• Task-Adaptive Clustering for Semi-Supervised Few-Shot Classification
• Zero-shot task adaptation by homoiconic meta-mapping
• Trainable Class Prototypes for Few-Shot Learning
• A Transductive Maximum Margin Classifier for Few-Shot Learning