Binding via Reconstruction Clustering

TL;DR

This paper introduces an unsupervised clustering algorithm using denoising autoencoders to address the binding problem in complex data, enabling the separation and representation of multiple objects in a single input.

Contribution

It presents a novel probabilistic framework and an EM-like algorithm that dynamically binds features in multi-object inputs, improving representation learning.

Findings

Successfully binds multiple objects in artificial binary image datasets

Generalizes to unseen objects during training

Demonstrates effectiveness of the clustering approach

Abstract

Disentangled distributed representations of data are desirable for machine learning, since they are more expressive and can generalize from fewer examples. However, for complex data, the distributed representations of multiple objects present in the same input can interfere and lead to ambiguities, which is commonly referred to as the binding problem. We argue for the importance of the binding problem to the field of representation learning, and develop a probabilistic framework that explicitly models inputs as a composition of multiple objects. We propose an unsupervised algorithm that uses denoising autoencoders to dynamically bind features together in multi-object inputs through an Expectation-Maximization-like clustering process. The effectiveness of this method is demonstrated on artificially generated datasets of binary images, showing that it can even generalize to bind together new objects never seen by the autoencoder during training.