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

• URL: http://arxiv.org/abs/2103.04693v1
• Date: Mon, 8 Mar 2021 12:10:02 GMT
• Title: Unsupervised Object-Based Transition Models for 3D Partially Observable Environments
• Authors: Antonia Creswell, Rishabh Kabra, Chris Burgess, Murray Shanahan
• Abstract summary: The model is trained end-to-end without supervision using losses at the level of the object-structured representation rather than pixels. 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.
• Score: 13.598250346370467
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

Err

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.