Timezone: »
Poster
Unified Fourier-based Kernel and Nonlinearity Design for Equivariant Networks on Homogeneous Spaces
Yinshuang Xu · Jiahui Lei · Edgar Dobriban · Kostas Daniilidis
We introduce a unified framework for group equivariant networks on homogeneous spaces derived from a Fourier perspective. We consider tensor-valued feature fields, before and after a convolutional layer. We present a unified derivation of kernels via the Fourier domain by leveraging the sparsity of Fourier coefficients of the lifted feature fields. The sparsity emerges when the stabilizer subgroup of the homogeneous space is a compact Lie group. We further introduce a nonlinear activation, via an elementwise nonlinearity on the regular representation after lifting and projecting back to the field through an equivariant convolution. We show that other methods treating features as the Fourier coefficients in the stabilizer subgroup are special cases of our activation. Experiments on $SO(3)$ and $SE(3)$ show state-of-the-art performance in spherical vector field regression, point cloud classification, and molecular completion.
Author Information
Yinshuang Xu (University of Pennsylvania)
Jiahui Lei (University of Pennsylvania)
Edgar Dobriban (University of Pennsylvania)
Kostas Daniilidis (University of Pennsylvania)
Related Events (a corresponding poster, oral, or spotlight)
-
2022 Spotlight: Unified Fourier-based Kernel and Nonlinearity Design for Equivariant Networks on Homogeneous Spaces »
Tue. Jul 19th 03:35 -- 03:40 PM Room Ballroom 3 & 4
More from the Same Authors
-
2021 : Discovering and Achieving Goals with World Models »
Russell Mendonca · Oleh Rybkin · Kostas Daniilidis · Danijar Hafner · Deepak Pathak -
2023 Poster: Demystifying Disagreement-on-the-Line in High Dimensions »
Donghwan Lee · Behrad Moniri · Xinmeng Huang · Edgar Dobriban · Hamed Hassani -
2021 Poster: Simple and Effective VAE Training with Calibrated Decoders »
Oleh Rybkin · Kostas Daniilidis · Sergey Levine -
2021 Spotlight: Simple and Effective VAE Training with Calibrated Decoders »
Oleh Rybkin · Kostas Daniilidis · Sergey Levine -
2021 Poster: Model-Based Reinforcement Learning via Latent-Space Collocation »
Oleh Rybkin · Chuning Zhu · Anusha Nagabandi · Kostas Daniilidis · Igor Mordatch · Sergey Levine -
2021 Spotlight: Model-Based Reinforcement Learning via Latent-Space Collocation »
Oleh Rybkin · Chuning Zhu · Anusha Nagabandi · Kostas Daniilidis · Igor Mordatch · Sergey Levine -
2020 Poster: The Implicit Regularization of Stochastic Gradient Flow for Least Squares »
Alnur Ali · Edgar Dobriban · Ryan Tibshirani -
2020 Poster: One-shot Distributed Ridge Regression in High Dimensions »
Yue Sheng · Edgar Dobriban -
2020 Poster: Planning to Explore via Self-Supervised World Models »
Ramanan Sekar · Oleh Rybkin · Kostas Daniilidis · Pieter Abbeel · Danijar Hafner · Deepak Pathak -
2020 Poster: DeltaGrad: Rapid retraining of machine learning models »
Yinjun Wu · Edgar Dobriban · Susan B Davidson -
2019 Poster: Cross-Domain 3D Equivariant Image Embeddings »
Carlos Esteves · Avneesh Sud · Zhengyi Luo · Kostas Daniilidis · Ameesh Makadia -
2019 Oral: Cross-Domain 3D Equivariant Image Embeddings »
Carlos Esteves · Avneesh Sud · Zhengyi Luo · Kostas Daniilidis · Ameesh Makadia