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.

READ FULL TEXT

page 7

page 8

page 9

page 14

page 15

page 16

page 17

page 18

research
01/08/2020

SPACE: Unsupervised Object-Oriented Scene Representation via Spatial Attention and Decomposition

The ability to decompose complex multi-object scenes into meaningful abs...
research
10/13/2021

Unsupervised Object Learning via Common Fate

Learning generative object models from unlabelled videos is a long stand...
research
01/23/2013

SPOOK: A System for Probabilistic Object-Oriented Knowledge Representation

In previous work, we pointed out the limitations of standard Bayesian ne...
research
09/25/2019

Guided Attention Network for Object Detection and Counting on Drones

Object detection and counting are related but challenging problems, espe...
research
04/04/2019

A Learned Representation for Scalable Vector Graphics

Dramatic advances in generative models have resulted in near photographi...
research
09/25/2019

LAVAE: Disentangling Location and Appearance

We propose a probabilistic generative model for unsupervised learning of...
research
08/19/2022

Background Invariance Testing According to Semantic Proximity

In many applications, machine learned (ML) models are required to hold s...

Please sign up or login with your details

Forgot password? Click here to reset