Few-Shot Learning with Graph Neural Networks

10 Nov 2017Victor GarciaJoan Bruna

We propose to study the problem of few-shot learning with the prism of inference on a partially observed graphical model, constructed from a collection of input images whose label can be either observed or not. By assimilating generic message-passing inference algorithms with their neural-network counterparts, we define a graph neural network architecture that generalizes several of the recently proposed few-shot learning models... (read more)

PDF Abstract

Results from the Paper


  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.

Results from Other Papers


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK SOURCE PAPER COMPARE
Few-Shot Image Classification Stanford Cars 5-way (1-shot) GNN++ Accuracy 55.85 # 2
Few-Shot Image Classification Stanford Cars 5-way (5-shot) GNN++ Accuracy 71.25 # 2
Few-Shot Image Classification Stanford Dogs 5-way (5-shot) GNN++ Accuracy 62.27 # 2