Deep Meta-Learning: Learning to Learn in the Concept Space

02/10/2018
by   Fengwei Zhou, et al.
0

Few-shot learning remains challenging for meta-learning that learns a learning algorithm (meta-learner) from many related tasks. In this work, we argue that this is due to the lack of a good representation for meta-learning, and propose deep meta-learning to integrate the representation power of deep learning into meta-learning. The framework is composed of three modules, a concept generator, a meta-learner, and a concept discriminator, which are learned jointly. The concept generator, e.g. a deep residual net, extracts a representation for each instance that captures its high-level concept, on which the meta-learner performs few-shot learning, and the concept discriminator recognizes the concepts. By learning to learn in the concept space rather than in the complicated instance space, deep meta-learning can substantially improve vanilla meta-learning, which is demonstrated on various few-shot image recognition problems. For example, on 5-way-1-shot image recognition on CIFAR-100 and CUB-200, it improves Matching Nets from 50.53 58.18 and improves Meta-SGD from 53.83 respectively.

READ FULL TEXT
research
07/05/2020

MetaConcept: Learn to Abstract via Concept Graph for Weakly-Supervised Few-Shot Learning

Meta-learning has been proved to be an effective framework to address fe...
research
07/14/2020

Concept Learners for Generalizable Few-Shot Learning

Developing algorithms that are able to generalize to a novel task given ...
research
09/09/2021

Bootstrapped Meta-Learning

Meta-learning empowers artificial intelligence to increase its efficienc...
research
01/13/2021

Learning to Focus: Cascaded Feature Matching Network for Few-shot Image Recognition

Deep networks can learn to accurately recognize objects of a category by...
research
06/15/2021

Contextualizing Multiple Tasks via Learning to Decompose

One single instance could possess multiple portraits and reveal diverse ...
research
01/19/2023

Concept Discovery for Fast Adapatation

The advances in deep learning have enabled machine learning methods to o...
research
05/12/2023

Meta Omnium: A Benchmark for General-Purpose Learning-to-Learn

Meta-learning and other approaches to few-shot learning are widely studi...

Please sign up or login with your details

Forgot password? Click here to reset