DeepAI AI Chat
Log In Sign Up

Semi-unsupervised Learning of Human Activity using Deep Generative Models

by   Matthew Willetts, et al.

Here we demonstrate a new deep generative model for classification. We introduce `semi-unsupervised learning', a problem regime related to transfer learning and zero/few shot learning where, in the training data, some classes are sparsely labelled and others entirely unlabelled. Models able to learn from training data of this type are potentially of great use, as many medical datasets are `semi-unsupervised'. Our model demonstrates superior semi-unsupervised classification performance on MNIST to model M2 from Kingma and Welling (2014). We apply the model to human accelerometer data, performing activity classification and structure discovery on windows of time series data.


Semi-Unsupervised Learning with Deep Generative Models: Clustering and Classifying using Ultra-Sparse Labels

We introduce semi-unsupervised learning, an extreme case of semi-supervi...

DGPose: Disentangled Semi-supervised Deep Generative Models for Human Body Analysis

Deep generative modelling for robust human body analysis is an emerging ...

Semi-unsupervised Learning for Time Series Classification

Time series are ubiquitous and therefore inherently hard to analyze and ...

Unsupervised Learning of 3D Structure from Images

A key goal of computer vision is to recover the underlying 3D structure ...

Learning Neural Random Fields with Inclusive Auxiliary Generators

In this paper we develop Neural Random Field learning with Inclusive-div...

A Non-generative Framework and Convex Relaxations for Unsupervised Learning

We give a novel formal theoretical framework for unsupervised learning w...

Semi-Generative Modelling: Domain Adaptation with Cause and Effect Features

This paper presents a novel, causally-inspired approach to domain adapta...