Unsupervised Meta-Learning through Latent-Space Interpolation in Generative Models

06/18/2020
by   Siavash Khodadadeh, et al.
63

Unsupervised meta-learning approaches rely on synthetic meta-tasks that are created using techniques such as random selection, clustering and/or augmentation. Unfortunately, clustering and augmentation are domain-dependent, and thus they require either manual tweaking or expensive learning. In this work, we describe an approach that generates meta-tasks using generative models. A critical component is a novel approach of sampling from the latent space that generates objects grouped into synthetic classes forming the training and validation data of a meta-task. We find that the proposed approach, LAtent Space Interpolation Unsupervised Meta-learning (LASIUM), outperforms or is competitive with current unsupervised learning baselines on few-shot classification tasks on the most widely used benchmark datasets. In addition, the approach promises to be applicable without manual tweaking over a wider range of domains than previous approaches.

READ FULL TEXT

page 4

page 5

page 9

research
05/20/2022

Set-based Meta-Interpolation for Few-Task Meta-Learning

Meta-learning approaches enable machine learning systems to adapt to new...
research
11/28/2018

Unsupervised Meta-Learning For Few-Shot Image and Video Classification

Few-shot or one-shot learning of classifiers for images or videos is an ...
research
03/03/2021

Meta-Learning with Variational Bayes

The field of meta-learning seeks to improve the ability of today's machi...
research
02/09/2021

Transfer learning based few-shot classification using optimal transport mapping from preprocessed latent space of backbone neural network

MetaDL Challenge 2020 focused on image classification tasks in few-shot ...
research
12/22/2016

Set2Model Networks: Learning Discriminatively To Learn Generative Models

We present a new "learning-to-learn"-type approach that enables rapid le...
research
09/16/2020

Using Sensory Time-cue to enable Unsupervised Multimodal Meta-learning

As data from IoT (Internet of Things) sensors become ubiquitous, state-o...
research
09/14/2016

Sampling Generative Networks

We introduce several techniques for sampling and visualizing the latent ...

Please sign up or login with your details

Forgot password? Click here to reset