Compositional Factorization of Visual Scenes with Convolutional Sparse Coding and Resonator Networks

TL;DR

This paper introduces a novel visual scene analysis system combining convolutional sparse coding with resonator networks, enabling efficient and accurate scene parsing through high-dimensional feature representations.

Contribution

It presents a new integrated approach that leverages convolutional sparse coding and resonator networks for improved scene content parsing and factorization.

Findings

Resonator networks enable fast, accurate vector factorization.

Sparse coding enhances the capacity of distributed representations.

A confidence metric improves convergence tracking.

Abstract

We propose a system for visual scene analysis and recognition based on encoding the sparse, latent feature-representation of an image into a high-dimensional vector that is subsequently factorized to parse scene content. The sparse feature representation is learned from image statistics via convolutional sparse coding, while scene parsing is performed by a resonator network. The integration of sparse coding with the resonator network increases the capacity of distributed representations and reduces collisions in the combinatorial search space during factorization. We find that for this problem the resonator network is capable of fast and accurate vector factorization, and we develop a confidence-based metric that assists in tracking the convergence of the resonator network.