mlsanityData to 7 Oct 2026

E(2) Equivariant Neural Networks for Robust Galaxy Morphology Classification

arXiv 2311.01500 ↗First posted 2 Nov 2023astro-ph.GA cs.LGcited by 6

Not on the map. Why?

Abstract (arXiv)

We propose the use of group convolutional neural network architectures (GCNNs) equivariant to the 2D Euclidean group, E(2), for the task of galaxy morphology classification by utilizing symmetries of the data present in galaxy images as an inductive bias in the architecture. We conduct robustness studies by introducing artificial perturbations via Poisson noise insertion and one-pixel adversarial attacks to simulate the effects of limited observational capabilities. We train, validate, and test GCNNs equivariant to discrete subgroups of E(2) - the cyclic and dihedral groups of order N - on the Galaxy10 DECals dataset and find that GCNNs achieve higher classification accuracy and are consistently more robust than their non-equivariant counterparts, with an architecture equivariant to the group D16 achieving a 95.52 ± 0.18% test-set accuracy. We also find that the model loses <6% accuracy on a 50%-noise dataset and all GCNNs are less susceptible to one-pixel perturbations than an identically constructed CNN. Our code is publicly available at https://github.com/snehjp2/GCNNMorphology.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 19 of its 35 references that are in the map. First posted on arXiv 2 Nov 2023.

Builds on

19 of 35 references.

References · 19

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  3. 2015Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)cited by 1,061
  4. 2017One pixel attack for fooling deep neural networkscited by 579
  5. 2018Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Surveycited by 459
  6. 2019General E(2)-Equivariant Steerable CNNscited by 441
  7. 2017Adversarial Examples: Attacks and Defenses for Deep Learningcited by 350
  8. 2016Steerable CNNscited by 298
  9. 2017Towards Robust Neural Networks via Random Self-ensemblecited by 158
  10. 2022Approximately Equivariant Networks for Imperfectly Symmetric Dynamicscited by 95
  11. 2016Exploiting Cyclic Symmetry in Convolutional Neural Networkscited by 91
  12. 2015Rotation-invariant convolutional neural networks for galaxy morphology predictioncited by 83
7 more
  1. 2021Residual Pathway Priors for Soft Equivariance Constraintscited by 74
  2. 2021Galaxy Zoo DECaLS: Detailed Visual Morphology Measurements from Volunteers and Deep Learning for 314,000 Galaxiescited by 40
  3. 2021DeepAdversaries: Examining the Robustness of Deep Learning Models for Galaxy Morphology Classificationcited by 10
  4. 2020Can we have it all? On the Trade-off between Spatial and Adversarial Robustness of Neural Networkscited by 9
  5. 2018Robustness of Rotation-Equivariant Networks to Adversarial Perturbationscited by 6
  6. 2021Robustness of deep learning algorithms in astronomy -- galaxy morphology studiescited by 4
  7. 2021Nonlinearities in Steerable SO(2)-Equivariant CNNscited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 4; 2026: 2.

6 papers.

  1. 2025SIDDA: SInkhorn Dynamic Domain Adaptation for Image Classification with Equivariant Neural Networkscited by 2
  2. 2026Interpreting "Interpretability" and Explaining "Explainability" in Machine Learning in Physicscited by 2
  3. 2025Galaxy Morphology Classification with Counterfactual Explanationcited by 1
  4. 2025On Uncertainty Calibration for Equivariant Functionscited by 1
  5. 2025From Simulations to Surveys: Domain Adaptation for Galaxy Observationscited by 0
  6. 2026Deep learning from the crowd Fundamentals of morphological galaxy classificationcited by 0