Multi-Scale Fusion for Object Representation

TL;DR

This paper introduces Multi-Scale Fusion, a novel method that improves object-centric learning by leveraging multi-scale image representations and fusion techniques to better handle objects of varying sizes.

Contribution

It proposes a multi-scale fusion approach that enhances VAE guidance in object-centric learning, addressing scale variability in object representations.

Findings

Improves performance of existing OCL methods on standard benchmarks.

Enhances scale-invariance and variance in object super-pixels.

Outperforms state-of-the-art diffusion-based methods.

Abstract

Representing images or videos as object-level feature vectors, rather than pixel-level feature maps, facilitates advanced visual tasks. Object-Centric Learning (OCL) primarily achieves this by reconstructing the input under the guidance of Variational Autoencoder (VAE) intermediate representation to drive so-called \textit{slots} to aggregate as much object information as possible. However, existing VAE guidance does not explicitly address that objects can vary in pixel sizes while models typically excel at specific pattern scales. We propose \textit{Multi-Scale Fusion} (MSF) to enhance VAE guidance for OCL training. To ensure objects of all sizes fall within VAE's comfort zone, we adopt the \textit{image pyramid}, which produces intermediate representations at multiple scales; To foster scale-invariance/variance in object super-pixels, we devise \textit{inter}/\textit{intra-scale fusion}, which augments low-quality object super-pixels of one scale with corresponding high-quality super-pixels from another scale. On standard OCL benchmarks, our technique improves mainstream methods, including state-of-the-art diffusion-based ones. The source code is available on https://github.com/Genera1Z/MultiScaleFusion.