Structuring Autoencoders

08/07/2019
by   Marco Rudolph, et al.
10

In this paper we propose Structuring AutoEncoders (SAE). SAEs are neural networks which learn a low dimensional representation of data which are additionally enriched with a desired structure in this low dimensional space. While traditional Autoencoders have proven to structure data naturally they fail to discover semantic structure that is hard to recognize in the raw data. The SAE solves the problem by enhancing a traditional Autoencoder using weak supervision to form a structured latent space. In the experiments we demonstrate, that the structured latent space allows for a much more efficient data representation for further tasks such as classification for sparsely labeled data, an efficient choice of data to label, and morphing between classes. To demonstrate the general applicability of our method, we show experiments on the benchmark image datasets MNIST, Fashion-MNIST, DeepFashion2 and on a dataset of 3D human shapes.

READ FULL TEXT

page 6

page 8

research
12/05/2019

Representing Closed Transformation Paths in Encoded Network Latent Space

Deep generative networks have been widely used for learning mappings fro...
research
05/11/2023

Revealing Patterns of Symptomatology in Parkinson's Disease: A Latent Space Analysis with 3D Convolutional Autoencoders

This work proposes the use of 3D convolutional variational autoencoders ...
research
10/03/2018

Deep processing of structured data

We construct a general unified framework for learning representation of ...
research
06/30/2023

Geometric Autoencoders – What You See is What You Decode

Visualization is a crucial step in exploratory data analysis. One possib...
research
02/12/2020

Variational Autoencoders with Riemannian Brownian Motion Priors

Variational Autoencoders (VAEs) represent the given data in a low-dimens...
research
01/16/2023

Simplex Autoencoders

Synthetic data generation is increasingly important due to privacy conce...

Please sign up or login with your details

Forgot password? Click here to reset