Slot-VAE: Object-Centric Scene Generation with Slot Attention

Yanbo Wang*, Letao Liu, Justin Dauwels

*Corresponding author for this work

Research output: Contribution to journalConference articleScientificpeer-review

18 Downloads (Pure)

Abstract

Slot attention has shown remarkable object-centric representation learning performance in computer vision tasks without requiring any supervision. Despite its object-centric binding ability brought by compositional modelling, as a deterministic module, slot attention lacks the ability to generate novel scenes. In this paper, we propose the Slot-VAE, a generative model that integrates slot attention with the hierarchical VAE framework for object-centric structured scene generation. For each image, the model simultaneously infers a global scene representation to capture high-level scene structure and object-centric slot representations to embed individual object components. During generation, slot representations are generated from the global scene representation to ensure coherent scene structures. Our extensive evaluation of the scene generation ability indicates that Slot-VAE outperforms slot representation-based generative baselines in terms of sample quality and scene structure accuracy.

Original languageEnglish
Pages (from-to)36020-36035
Number of pages16
JournalProceedings of Machine Learning Research
Volume202
Publication statusPublished - 2023
Event40th International Conference on Machine Learning, ICML 2023 - Honolulu, United States
Duration: 23 Jul 202329 Jul 2023

Fingerprint

Dive into the research topics of 'Slot-VAE: Object-Centric Scene Generation with Slot Attention'. Together they form a unique fingerprint.

Cite this