Breaking the Symmetry: Resolving Symmetry Ambiguities in Equivariant Neural Networks
Abstract/Contents
- Abstract
- Equivariant neural networks have been adopted in a variety of 3-D learning areas. In this paper, we identify and address a fundamental problem of equivariant networks: their ambiguity to symmetries. For a left-right symmetric input, like an airplane, these networks cannot complete symmetry-dependent tasks like segmenting the object into its left and right sides. We tackle this problem by adding components that resolve symmetry ambiguities while preserving rotational equivariance. We present OAVNN: Orientation Aware Vector Neuron Network, an extension of the Vector Neuron Network. OAVNN is a rotation equivariant network that is robust to planar symmetric inputs. Our network consists of three key components. First, we introduce an algorithm to calculate features for detecting symmetries. Second, we create an orientation aware linear layer that is sensitive to symmetries. Finally, we construct an attention mechanism that relates directional information across points. We evaluate the network using left-right segmentation and find that the network quickly obtains accurate segmentations. We hope this work motivates investigations on the expressivity of equivariant networks to symmetric objects.
Description
Type of resource | text |
---|---|
Date modified | May 26, 2022; December 5, 2022 |
Publication date | May 26, 2022; May 2022 |
Creators/Contributors
Author | Balachandar, Sidhika |
---|---|
Thesis advisor | Poulenard, Adrien |
Thesis advisor | Guibas, Leonidas |
Thesis advisor | Dror, Ron |
Thesis advisor | Deng, Congyue |
Degree granting institution | Stanford University |
Department | Department of Computer Science |
Subjects
Subject | Equivariance |
---|---|
Subject | Machine learning |
Subject | Symmetry groups |
Genre | Text |
Genre | Thesis |
Bibliographic information
Access conditions
- Use and reproduction
- User agrees that, where applicable, content will not be used to identify or to otherwise infringe the privacy or confidentiality rights of individuals. Content distributed via the Stanford Digital Repository may be subject to additional license and use restrictions applied by the depositor.
- License
- This work is licensed under a Creative Commons Attribution Non Commercial 4.0 International license (CC BY-NC).
Preferred citation
- Preferred citation
- Balachandar, S. (2022). Breaking the Symmetry: Resolving Symmetry Ambiguities in Equivariant Neural Networks. Stanford Digital Repository. Available at https://purl.stanford.edu/tn463rr9524
Collection
Undergraduate Theses, School of Engineering
View other items in this collection in SearchWorksContact information
- Contact
- sidhikabalachandar@gmail.com
Also listed in
Loading usage metrics...