Multi-Scale Fusion for Object Representation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhao, Rongzhen, Wang, Vivienne, Kannala, Juho, Pajarinen, Joni
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908636987523072
author Zhao, Rongzhen
Wang, Vivienne
Kannala, Juho
Pajarinen, Joni
author_facet Zhao, Rongzhen
Wang, Vivienne
Kannala, Juho
Pajarinen, Joni
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2410_01539
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Multi-Scale Fusion for Object Representation
Zhao, Rongzhen
Wang, Vivienne
Kannala, Juho
Pajarinen, Joni
Computer Vision and Pattern Recognition
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.
title Multi-Scale Fusion for Object Representation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2410.01539