REVIEW 5 cited by
Scaling Spherical CNNs
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
Spherical CNNs generalize CNNs to functions on the sphere, by using spherical convolutions as the main linear operation. The most accurate and efficient way to compute spherical convolutions is in the spectral domain (via the convolution theorem), which is still costlier than the usual planar convolutions. For this reason, applications of spherical CNNs have so far been limited to small problems that can be approached with low model capacity. In this work, we show how spherical CNNs can be scaled for much larger problems. To achieve this, we make critical improvements including novel variants of common model components, an implementation of core operations to exploit hardware accelerator characteristics, and application-specific input representations that exploit the properties of our model. Experiments show our larger spherical CNNs reach state-of-the-art on several targets of the QM9 molecular benchmark, which was previously dominated by equivariant graph neural networks, and achieve competitive performance on multiple weather forecasting tasks. Our code is available at https://github.com/google-research/spherical-cnn.
Forward citations
Cited by 5 Pith papers
-
SciVid: Cross-Domain Evaluation of Video Models in Scientific Applications
General-purpose video foundation models, adapted with lightweight readout heads, reach state-of-the-art performance on three of five scientific video benchmarks.
-
Attention on the Sphere
Quadrature-weighted attention on the sphere gives Transformers approximate rotation equivariance and improves accuracy on spherical physics and vision tasks, with the biggest gains on shallow-water simulations.
-
ArchesWeather & ArchesWeatherGen: a deterministic and generative model for efficient ML weather forecasting
ArchesWeatherGen, a flow-matching model trained on residuals of a deterministic transformer, generates ensemble forecasts that outperform IFS ENS and NeuralGCM on most WeatherBench headline variables at 1.5 degrees re...
-
Panoramic Scene Understanding: A Survey from Distortion-Aware Engineering to Sphere-Native Modeling
Survey organizing panoramic scene analysis literature by architectural design and training paradigm, identifying the absence of methods achieving both strict spherical equivariance and full reuse of perspective-pretra...
-
Correspondence-Free Fast and Robust Spherical Point Pattern Registration
Spherical point patterns can be aligned by aligning their mean directions and recovering the residual rotation with 1D circular cross-correlation of azimuth histograms, plus iterative refinement.
Discussion (0). Continue with ORCID to comment.