mlsanityData to 7 Oct 2026

DeepSphere: a graph-based spherical CNN

arXiv 2012.15000 ↗First posted 30 Dec 2020cs.LG cs.CV stat.MLcited by 65

Not on the map. Why?

Abstract (arXiv)

Designing a convolution for a spherical neural network requires a delicate tradeoff between efficiency and rotation equivariance. DeepSphere, a method based on a graph representation of the sampled sphere, strikes a controllable balance between these two desiderata. This contribution is twofold. First, we study both theoretically and empirically how equivariance is affected by the underlying graph with respect to the number of vertices and neighbors. Second, we evaluate DeepSphere on relevant problems. Experiments show state-of-the-art performance and demonstrates the efficiency and flexibility of this formulation. Perhaps surprisingly, comparison with previous work suggests that anisotropic filters might be an unnecessary price to pay. Our code is available at https://github.com/deepsphere

Key facts. Cited by 65 papers in the map (data through 7 Oct 2026). First posted on arXiv 30 Dec 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 15; 2022: 10; 2023: 19; 2024: 9; 2025: 6; 2026: 6.

65 papers.

Sort:

By area:

  1. 2021Hyperbolic Deep Neural Networks: A Surveycited by 138
  2. 2021CKConv: Continuous Kernel Convolution For Sequential Datacited by 117
  3. 2021Graph-Based Deep Learning for Medical Diagnosis and Analysis: Past, Present and Futurecited by 67
  4. 2021Geometric Deep Learning and Equivariant Neural Networkscited by 64
  5. 2022When Physics Meets Machine Learning: A Survey of Physics-Informed Machine Learningcited by 64
  6. 2023Towards Stability of Autoregressive Neural Operatorscited by 54
  7. 2022Deep Learning for Omnidirectional Vision: A Survey and New Perspectivescited by 38
  8. 2021Conditional Local Convolution for Spatio-temporal Meteorological Forecastingcited by 30
  9. 2022SurfGen: Adversarial 3D Shape Synthesis with Explicit Surface Discriminatorscited by 26
  10. 2022Surface Vision Transformers: Attention-Based Modelling applied to Cortical Analysiscited by 25
  11. 2021Symmetric Spaces for Graph Embeddings: A Finsler-Riemannian Approachcited by 23
  12. 2025A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Visioncited by 23
38 more
  1. 2021PDO-eS2CNNs: Partial Differential Operator Based Equivariant Spherical CNNscited by 19
  2. 2023Weather2K: A Multivariate Spatio-Temporal Benchmark Dataset for Meteorological Forecasting Based on Real-Time Observation Data from Ground Weather Stationscited by 18
  3. 2023HEAL-SWIN: A Vision Transformer On The Spherecited by 18
  4. 2023PanoSwin: a Pano-style Swin Transformer for Panorama Understandingcited by 18
  5. 2022A PAC-Bayesian Generalization Bound for Equivariant Networkscited by 17
  6. 2021Equivariant Networks for Pixelized Spherescited by 16
  7. 2023Curve Your Attention: Mixed-Curvature Transformers for Graph Representation Learningcited by 15
  8. 2025Position: Beyond Euclidean -- Foundation Models Should Embrace Non-Euclidean Geometriescited by 15
  9. 2024SphereUFormer: A U-Shaped Transformer for Spherical 360 Perceptioncited by 12
  10. 2022Spherical Transformercited by 11
  11. 2023Connectivity Optimized Nested Graph Networks for Crystal Structurescited by 11
  12. 20243D Scene Geometry Estimation from 360^circ Imagery: A Surveycited by 11
  13. 2023Modeling Graphs Beyond Hyperbolic: Graph Neural Networks in Symmetric Positive Definite Matricescited by 10
  14. 2023360VOT: A New Benchmark Dataset for Omnidirectional Visual Object Trackingcited by 10
  15. 2025Attention on the Spherecited by 9
  16. 2024360VOTS: Visual Object Tracking and Segmentation in Omnidirectional Videoscited by 8
  17. 2021Deformation Robust Roto-Scale-Translation Equivariant CNNscited by 7
  18. 20233D reconstruction from spherical images: A review of techniques, applications, and prospectscited by 7
  19. 2021Equivariant Wavelets: Fast Rotation and Translation Invariant Wavelet Scattering Transformscited by 6
  20. 2021Inferring dark matter substructure with astrometric lensing beyond the power spectrumcited by 4
  21. 2023SINCERE: Sequential Interaction Networks representation learning on Co-Evolving RiEmannian manifoldscited by 4
  22. 20243D Equivariant Pose Regression via Direct Wigner-D Harmonics Predictioncited by 4
  23. 2025Breaking the Discretization Barrier of Continuous Physics Simulation Learningcited by 4
  24. 2021The Earth Mover's Pinball Loss: Quantiles for Histogram-Valued Regressioncited by 3
  25. 2022Rigidity Preserving Image Transformations and Equivariance in Perspectivecited by 3
  26. 2022Direction of Arrival Estimation of Sound Sources Using Icosahedral CNNscited by 3
  27. 2024Contrastive Sequential Interaction Network Learning on Co-Evolving Riemannian Spacescited by 3
  28. 2024Hybrid Neural Representations for Spherical Datacited by 3
  29. 2021Concentric Spherical GNN for 3D Representation Learningcited by 2
  30. 2023Deep Neural Networks with Efficient Guaranteed Invariancescited by 2
  31. 2023HAiVA: Hybrid AI-assisted Visual Analysis Framework to Study the Effects of Cloud Properties on Climate Patternscited by 2
  32. 2023Higher Order Gauge Equivariant CNNs on Riemannian Manifolds and Applicationscited by 2
  33. 2023Normed Spaces for Graph Embeddingcited by 2
  34. 2024Equivariant Manifold Neural ODEs and Differential Invariantscited by 2
  35. 2024Current Symmetry Group Equivariant Convolution Frameworks for Representation Learningcited by 2
  36. 2021ChebLieNet: Invariant Spectral Graph NNs Turned Equivariant by Riemannian Geometry on Lie Groupscited by 1
  37. 2022Hierarchical Spherical CNNs with Lifting-based Adaptive Wavelets for Pooling and Unpoolingcited by 1
  38. 2022Neurodevelopmental Phenotype Prediction: A State-of-the-Art Deep Learning Modelcited by 1

50 most cited of 65 All 65 (JSON)