Looking back to lower-level information in few-shot learning

by   Zhongjie Yu, et al.
University of Wisconsin-Madison

Humans are capable of learning new concepts from small numbers of examples. In contrast, supervised deep learning models usually lack the ability to extract reliable predictive rules from limited data scenarios when attempting to classify new examples. This challenging scenario is commonly known as few-shot learning. Few-shot learning has garnered increased attention in recent years due to its significance for many real-world problems. Recently, new methods relying on meta-learning paradigms combined with graph-based structures, which model the relationship between examples, have shown promising results on a variety of few-shot classification tasks. However, existing work on few-shot learning is only focused on the feature embeddings produced by the last layer of the neural network. In this work, we propose the utilization of lower-level, supporting information, namely the feature embeddings of the hidden neural network layers, to improve classifier accuracy. Based on a graph-based meta-learning framework, we develop a method called Looking-Back, where such lower-level information is used to construct additional graphs for label propagation in limited data settings. Our experiments on two popular few-shot learning datasets, miniImageNet and tieredImageNet, show that our method can utilize the lower-level information in the network to improve state-of-the-art classification performance.


page 1

page 2

page 3

page 4


A New Meta-Baseline for Few-Shot Learning

Meta-learning has become a popular framework for few-shot learning in re...

Few-shot Learning for Decoding Brain Signals

Few-shot learning consists in addressing data-thrifty (inductive few-sho...

Transductive Propagation Network for Few-shot Learning

Few-shot learning aims to build a learner that quickly generalizes to no...

Model-Agnostic Graph Regularization for Few-Shot Learning

In many domains, relationships between categories are encoded in the kno...

Multi-Domain Few-Shot Learning and Dataset for Agricultural Applications

Automatic classification of pests and plants (both healthy and diseased)...

Few-Shot Learning with Graph Neural Networks

We propose to study the problem of few-shot learning with the prism of i...

EASY: Ensemble Augmented-Shot Y-shaped Learning: State-Of-The-Art Few-Shot Classification with Simple Ingredients

Few-shot learning aims at leveraging knowledge learned by one or more de...

Please sign up or login with your details

Forgot password? Click here to reset