Scattering Networks on the Sphere for Scalable and Rotationally Equivariant Spherical CNNs

• URL: http://arxiv.org/abs/2102.02828v1
• Date: Thu, 4 Feb 2021 19:00:01 GMT
• Title: Scattering Networks on the Sphere for Scalable and Rotationally Equivariant Spherical CNNs
• Authors: Jason D. McEwen, Christopher G. R. Wallis, Augustine N. Mavor-Parker
• Abstract summary: We develop scattering networks constructed on the sphere that provide a powerful representational space for spherical data. By integrating scattering networks as an additional type of layer in the generalized spherical CNN framework, we show how they can be leveraged to scale spherical CNNs to the high resolution data typical of many practical applications.
• Score: 2.453627017761322
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Convolutional neural networks (CNNs) constructed natively on the sphere have been developed recently and shown to be highly effective for the analysis of spherical data. While an efficient framework has been formulated, spherical CNNs are nevertheless highly computationally demanding; typically they cannot scale beyond spherical signals of thousands of pixels. We develop scattering networks constructed natively on the sphere that provide a powerful representational space for spherical data. Spherical scattering networks are computationally scalable and exhibit rotational equivariance, while their representational space is invariant to isometries and provides efficient and stable signal representations. By integrating scattering networks as an additional type of layer in the generalized spherical CNN framework, we show how they can be leveraged to scale spherical CNNs to the high resolution data typical of many practical applications, with spherical signals of many tens of megapixels and beyond.

Related papers

• Herglotz-NET: Implicit Neural Representation of Spherical Data with Harmonic Positional Encoding [4.2412715094420665]
  Implicit neural representations (INRs) have emerged as a promising alternative for high-fidelity data representation. Herglotz-NET (HNET) is a novel INR architecture that employs a harmonic positional encoding based on complex Herglotz mappings. Our results establish HNET as a scalable and flexible framework for accurate modeling of spherical data.
  arXiv  Detail & Related papers  (2025-02-19T14:40:02Z)
• SphereDiffusion: Spherical Geometry-Aware Distortion Resilient Diffusion Model [63.685132323224124]
  Controllable spherical panoramic image generation holds substantial applicative potential across a variety of domains. In this paper, we introduce a novel framework of SphereDiffusion to address these unique challenges. Experiments on Structured3D dataset show that SphereDiffusion significantly improves the quality of controllable spherical image generation and relatively reduces around 35% FID on average.
  arXiv  Detail & Related papers  (2024-03-15T06:26:46Z)
• Hybrid Neural Representations for Spherical Data [25.080272865553003]
  We introduce a novel approach named Hybrid Neural Representations for Spherical data (HNeR-S) Our main idea is to use spherical feature-grids to obtain positional features which are combined with a multilayer perception to predict the target signal. We consider feature-grids with equirectangular and hierarchical equal area isolatitude pixelization structures that align with weather data and CMB data, respectively.
  arXiv  Detail & Related papers  (2024-02-05T13:03:00Z)
• Learnable wavelet neural networks for cosmological inference [5.1268138545584145]
  Learnable scattering transform is a kind of convolutional neural network that uses trainable wavelets as filters. We present two models based on the scattering transform, one constructed for performance, and one constructed for interpretability. We find that scattering architectures are able to outperform a CNN, significantly in the case of small training data samples.
  arXiv  Detail & Related papers  (2023-07-24T22:12:16Z)
• Spherical Feature Pyramid Networks For Semantic Segmentation [0.0]
  We develop graph-based models for representing the signal on a spherical mesh. Our models achieve state-of-the-art performance with an mIOU of 48.75, an improvement of 3.75 IoU points over the previous best spherical CNN.
  arXiv  Detail & Related papers  (2023-07-05T21:19:13Z)
• Scaling Spherical CNNs [19.735829027026902]
  We show how spherical convolutions can be scaled for much larger problems. Experiments show our larger spherical CNNs reach state-of-the-art on several targets of the QM9 molecular benchmark.
  arXiv  Detail & Related papers  (2023-06-08T17:59:08Z)
• PDO-e$\text{S}^\text{2}$CNNs: Partial Differential Operator Based Equivariant Spherical CNNs [77.53203546732664]
  We use partial differential operators to design a spherical equivariant CNN, PDO-e$textStext2$CNN, which is exactly rotation equivariant in the continuous domain. In experiments, PDO-e$textStext2$CNNs show greater parameter efficiency and outperform other spherical CNNs significantly on several tasks.
  arXiv  Detail & Related papers  (2021-04-08T07:54:50Z)
• Concentric Spherical GNN for 3D Representation Learning [53.45704095146161]
  We propose a novel multi-resolution convolutional architecture for learning over concentric spherical feature maps. Our hierarchical architecture is based on alternatively learning to incorporate both intra-sphere and inter-sphere information. We demonstrate the effectiveness of our approach in improving state-of-the-art performance on 3D classification tasks with rotated data.
  arXiv  Detail & Related papers  (2021-03-18T19:05:04Z)
• Spherical Transformer: Adapting Spherical Signal to CNNs [53.18482213611481]
  Spherical Transformer can transform spherical signals into vectors that can be directly processed by standard CNNs. We evaluate our approach on the tasks of spherical MNIST recognition, 3D object classification and omnidirectional image semantic segmentation.
  arXiv  Detail & Related papers  (2021-01-11T12:33:16Z)
• A Point-Cloud Deep Learning Framework for Prediction of Fluid Flow Fields on Irregular Geometries [62.28265459308354]
  Network learns end-to-end mapping between spatial positions and CFD quantities. Incompress laminar steady flow past a cylinder with various shapes for its cross section is considered. Network predicts the flow fields hundreds of times faster than our conventional CFD.
  arXiv  Detail & Related papers  (2020-10-15T12:15:02Z)
• Spherical Convolutional Neural Networks: Stability to Perturbations in SO(3) [175.96910854433574]
  Spherical convolutional neural networks (Spherical CNNs) learn nonlinear representations from 3D data by exploiting the data structure. This paper investigates the properties that Spherical CNNs exhibit as they pertain to the rotational structure inherent in spherical signals.
  arXiv  Detail & Related papers  (2020-10-12T17:16:07Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.