E(2) Equivariant Self-Attention for Radio Astronomy
arXiv:2111.04742
Abstract
In this work we introduce group-equivariant self-attention models to address the problem of explainable radio galaxy classification in astronomy. We evaluate various orders of both cyclic and dihedral equivariance, and show that including equivariance as a prior both reduces the number of epochs required to fit the data and results in improved performance. We highlight the benefits of equivariance when using self-attention as an explainable model and illustrate how equivariant models statistically attend the same features in their classifications as human astronomers.
Accepted in: Fourth Workshop on Machine Learning and the Physical Sciences (35th Conference on Neural Information Processing Systems; NeurIPS2021); final version; 7 pages, 3 figures
References in corpus (6)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Rotation-invariant convolutional neural networks for galaxy morphology prediction
- The MeerKAT International GHz Tiered Extragalactic Exploration (MIGHTEE) Survey
- Fanaroff-Riley classification of radio galaxies using group-equivariant convolutional neural networks
- Attention-gating for improved radio galaxy classification
- Rapid sorting of radio galaxy morphology using Haralick features