Complex-Valued Autoencoders for Object Discovery

04/05/2022
by   Sindy Löwe, et al.
7

Object-centric representations form the basis of human perception and enable us to reason about the world and to systematically generalize to new settings. Currently, most machine learning work on unsupervised object discovery focuses on slot-based approaches, which explicitly separate the latent representations of individual objects. While the result is easily interpretable, it usually requires the design of involved architectures. In contrast to this, we propose a distributed approach to object-centric representations: the Complex AutoEncoder. Following a coding scheme theorized to underlie object representations in biological neurons, its complex-valued activations represent two messages: their magnitudes express the presence of a feature, while the relative phase differences between neurons express which features should be bound together to create joint object representations. We show that this simple and efficient approach achieves better reconstruction performance than an equivalent real-valued autoencoder on simple multi-object datasets. Additionally, we show that it achieves competitive unsupervised object discovery performance to a SlotAttention model on two datasets, and manages to disentangle objects in a third dataset where SlotAttention fails - all while being 7-70 times faster to train.

READ FULL TEXT

page 6

page 8

page 18

page 19

page 20

research
06/01/2023

Rotating Features for Object Discovery

The binding problem in human cognition, concerning how the brain represe...
research
05/24/2023

Contrastive Training of Complex-Valued Autoencoders for Object Discovery

Current state-of-the-art object-centric models use slots and attention-b...
research
11/19/2015

Binding via Reconstruction Clustering

Disentangled distributed representations of data are desirable for machi...
research
10/17/2022

Unsupervised Object-Centric Learning with Bi-Level Optimized Query Slot Attention

The ability to decompose complex natural scenes into meaningful object-c...
research
09/29/2022

Bridging the Gap to Real-World Object-Centric Learning

Humans naturally decompose their environment into entities at the approp...
research
10/07/2021

Unsupervised Image Decomposition with Phase-Correlation Networks

The ability to decompose scenes into their object components is a desire...
research
05/11/2020

SCAT: Second Chance Autoencoder for Textual Data

We present a k-competitive learning approach for textual autoencoders na...

Please sign up or login with your details

Forgot password? Click here to reset