Object-Centric Representation Learning

This paper introduces several advancements for continuous and distributed object-centric representations, scaling them from simple toy to real-world data.

We learn object-centric representations in an unsupervised manner by differentiably parameterizing and solving a min-cut problem to partition the image. Published at ICLR 2023.

We perform unsupervised object-centric representation learning by exploiting complex-valued activations in an unconstrained autoencoder architecture.