Scaling Spherical CNNs
- URL: http://arxiv.org/abs/2306.05420v1
- Date: Thu, 8 Jun 2023 17:59:08 GMT
- Title: Scaling Spherical CNNs
- Authors: Carlos Esteves, Jean-Jacques Slotine, Ameesh Makadia
- Abstract summary: 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.
- Score: 19.735829027026902
- License: http://creativecommons.org/licenses/by/4.0/
- 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.
Related papers
- CAM Back Again: Large Kernel CNNs from a Weakly Supervised Object
Localization Perspective [2.7195102129095003]
Large kernel CNNs have been reported to perform well in downstream vision tasks as well as in classification performance.
We revisit the performance of large kernel CNNs in downstream task, focusing on the weakly supervised object localization task.
Our study compares the modern large kernel CNNs ConvNeXt, RepLKNet, and SLaK to test the validity of the naive expectation that ERF size is important for improving downstream task performance.
arXiv Detail & Related papers (2024-03-11T12:48:22Z) - Transferability of Convolutional Neural Networks in Stationary Learning
Tasks [96.00428692404354]
We introduce a novel framework for efficient training of convolutional neural networks (CNNs) for large-scale spatial problems.
We show that a CNN trained on small windows of such signals achieves a nearly performance on much larger windows without retraining.
Our results show that the CNN is able to tackle problems with many hundreds of agents after being trained with fewer than ten.
arXiv Detail & Related papers (2023-07-21T13:51:45Z) - Interpreting convolutional neural networks' low dimensional
approximation to quantum spin systems [1.631115063641726]
Convolutional neural networks (CNNs) have been employed along with Variational Monte Carlo methods for finding the ground state of quantum many-body spin systems.
We provide a theoretical and experimental analysis of how the CNN optimize learning for spin systems, and investigate the CNN's low dimensional approximation.
Our results allow us to gain a comprehensive, improved understanding of how CNNs successfully approximate quantum spin Hamiltonians.
arXiv Detail & Related papers (2022-10-03T02:49:16Z) - Efficient Quantum Feature Extraction for CNN-based Learning [5.236201168829204]
We propose a quantum-classical deep network structure to enhance classical CNN model discriminability.
We build PQC, which is a more potent function approximator, with more complex structures to capture the features within the receptive field.
The results disclose that the model with ansatz in high expressibility achieves lower cost and higher accuracy.
arXiv Detail & Related papers (2022-01-04T17:04:07Z) - 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) - Spectral Leakage and Rethinking the Kernel Size in CNNs [10.432041176720842]
We show that the small size of CNN kernels make them susceptible to spectral leakage.
We demonstrate improved classification accuracy over baselines with conventional $3times 3$ kernels.
We also show that CNNs employing the Hamming window display increased robustness against certain types of adversarial attacks.
arXiv Detail & Related papers (2021-01-25T14:49:29Z) - 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) - PSConv: Squeezing Feature Pyramid into One Compact Poly-Scale
Convolutional Layer [76.44375136492827]
Convolutional Neural Networks (CNNs) are often scale-sensitive.
We bridge this regret by exploiting multi-scale features in a finer granularity.
The proposed convolution operation, named Poly-Scale Convolution (PSConv), mixes up a spectrum of dilation rates.
arXiv Detail & Related papers (2020-07-13T05:14:11Z) - Spin-Weighted Spherical CNNs [58.013031812072356]
We present a new type of spherical CNN that allows anisotropic filters in an efficient way, without ever leaving the sphere domain.
The key idea is to consider spin-weighted spherical functions, which were introduced in physics in the study of gravitational waves.
Our method outperforms previous methods on tasks like classification of spherical images, classification of 3D shapes and semantic segmentation of spherical panoramas.
arXiv Detail & Related papers (2020-06-18T17:57:21Z) - Approximation and Non-parametric Estimation of ResNet-type Convolutional
Neural Networks [52.972605601174955]
We show a ResNet-type CNN can attain the minimax optimal error rates in important function classes.
We derive approximation and estimation error rates of the aformentioned type of CNNs for the Barron and H"older classes.
arXiv Detail & Related papers (2019-03-24T19:42:39Z)
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.