Early Visual Concept Learning with Unsupervised Deep Learning

06/17/2016
by   Irina Higgins, et al.
0

Automated discovery of early visual concepts from raw image data is a major open challenge in AI research. Addressing this problem, we propose an unsupervised approach for learning disentangled representations of the underlying factors of variation. We draw inspiration from neuroscience, and show how this can be achieved in an unsupervised generative model by applying the same learning pressures as have been suggested to act in the ventral visual stream in the brain. By enforcing redundancy reduction, encouraging statistical independence, and exposure to data with transform continuities analogous to those to which human infants are exposed, we obtain a variational autoencoder (VAE) framework capable of learning disentangled factors. Our approach makes few assumptions and works well across a wide variety of datasets. Furthermore, our solution has useful emergent properties, such as zero-shot inference and an intuitive understanding of "objectness".

READ FULL TEXT

page 2

page 4

page 5

page 6

page 7

page 8

research
02/23/2023

Causally Disentangled Generative Variational AutoEncoder

We propose a new supervised learning method for Variational AutoEncoder ...
research
12/11/2019

A Closer Look at Disentangling in β-VAE

In many data analysis tasks, it is beneficial to learn representations w...
research
07/26/2023

Learning Disentangled Discrete Representations

Recent successes in image generation, model-based reinforcement learning...
research
03/31/2018

Joint-VAE: Learning Disentangled Joint Continuous and Discrete Representations

We present a framework for learning disentangled and interpretable joint...
research
02/16/2018

Disentangling by Factorising

We define and address the problem of unsupervised learning of disentangl...
research
06/01/2022

Top-down inference in an early visual cortex inspired hierarchical Variational Autoencoder

Interpreting computations in the visual cortex as learning and inference...

Please sign up or login with your details

Forgot password? Click here to reset