SCALOR: Generative World Models with Scalable Object RepresentationsDownload PDF

Published: 20 Dec 2019, Last Modified: 22 Oct 2023ICLR 2020 Conference Blind SubmissionReaders: Everyone
Abstract: Scalability in terms of object density in a scene is a primary challenge in unsupervised sequential object-oriented representation learning. Most of the previous models have been shown to work only on scenes with a few objects. In this paper, we propose SCALOR, a probabilistic generative world model for learning SCALable Object-oriented Representation of a video. With the proposed spatially parallel attention and proposal-rejection mechanisms, SCALOR can deal with orders of magnitude larger numbers of objects compared to the previous state-of-the-art models. Additionally, we introduce a background module that allows SCALOR to model complex dynamic backgrounds as well as many foreground objects in the scene. We demonstrate that SCALOR can deal with crowded scenes containing up to a hundred objects while jointly modeling complex dynamic backgrounds. Importantly, SCALOR is the first unsupervised object representation model shown to work for natural scenes containing several tens of moving objects.
Code: [![Papers with Code](/images/pwc_icon.svg) 2 community implementations](
Community Implementations: [![CatalyzeX](/images/catalyzex_icon.svg) 2 code implementations](
Original Pdf: pdf
11 Replies