Unsupervised Object-Based Transition Models for 3D Partially Observable Environments

03/08/2021
by   Antonia Creswell, et al.
2

We present a slot-wise, object-based transition model that decomposes a scene into objects, aligns them (with respect to a slot-wise object memory) to maintain a consistent order across time, and predicts how those objects evolve over successive frames. The model is trained end-to-end without supervision using losses at the level of the object-structured representation rather than pixels. Thanks to its alignment module, the model deals properly with two issues that are not handled satisfactorily by other transition models, namely object persistence and object identity. We show that the combination of an object-level loss and correct object alignment over time enables the model to outperform a state-of-the-art baseline, and allows it to deal well with object occlusion and re-appearance in partially observable environments.

READ FULL TEXT

page 2

page 6

page 7

page 8

page 12

page 13

research
06/11/2020

Learning to Infer 3D Object Models from Images

A crucial ability of human intelligence is to build up models of individ...
research
12/22/2019

End-Point Detection with State Transition Model based on Chunk-Wise Classification

A state transition model (STM) based on chunk-wise classification was pr...
research
02/16/2023

Object-centric Learning with Cyclic Walks between Parts and Whole

Learning object-centric representations from complex natural environment...
research
08/02/2016

Context Discovery for Model Learning in Partially Observable Environments

The ability to learn a model is essential for the success of autonomous ...
research
12/04/2020

Spatial Language Understanding for Object Search in Partially Observed Cityscale Environments

We present a system that enables robots to interpret spatial language as...
research
07/17/2020

AlignNet: Unsupervised Entity Alignment

Recently developed deep learning models are able to learn to segment sce...

Please sign up or login with your details

Forgot password? Click here to reset