Scalable Object-Oriented Sequential Generative Models

10/06/2019 ∙ by Jindong Jiang, et al. ∙ 34

The main limitation of previous approaches to unsupervised sequential object-oriented representation learning is in scalability. Most of the previous models have been shown to work only on scenes with a few objects. In this paper, we propose SCALOR, a generative model for SCALable sequential Object-oriented Representation. With the proposed spatially-parallel attention and proposal-rejection mechanism, SCALOR can deal with orders of magnitude more number of objects compared to the current state-of-the-art models. Besides, we introduce the background model so that SCALOR can model complex background along with many foreground objects. We demonstrate that SCALOR can deal with crowded scenes containing nearly a hundred objects while modeling complex background as well. Importantly, SCALOR is the first unsupervised model demonstrating its working in natural scenes containing several tens of moving objects.



There are no comments yet.


page 7

page 8

page 9

page 14

page 15

page 16

page 17

page 18

This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.