首页/论文/1612.04530

arXiv 1612.045302016-12-14cs.CVstat.ML

Permutation-equivariant neural networks applied to dynamics prediction

Araya；Earth-Life-Science Institute（地球生命科学研究所）

Nicholas Guttenberg, Nathaniel Virgo, Olaf Witkowski, Hidetoshi Aoki, Ryota Kanai

备注：: 7 pages, 4 figures

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

英文摘要相关论文

英文摘要：

The introduction of convolutional layers greatly advanced the performance of neural networks on image tasks due to innately capturing a way of encoding and learning translation-invariant operations, matching one of the underlying symmetries of the image domain. In comparison, there are a number of problems in which there are a number of different inputs which are all 'of the same type' --- multiple particles, multiple agents, multiple stock prices, etc. The corresponding symmetry to this is permutation symmetry, in that the algorithm should not depend on the specific ordering of the input data. We discuss a permutation-invariant neural network layer in analogy to convolutional layers, and show the ability of this architecture to learn to predict the motion of a variable number of interacting hard discs in 2D. In the same way that convolutional layers can generalize to different image sizes, the permutation layer we describe generalizes to different numbers of objects.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

阅读原文

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

本文内容

英文摘要相关论文

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

继续探索

相关论文

ACNe: Attentive Context Normalization for Robust Permutation-Equivariant Learning

University of Victoria（维多利亚大学）；Google Research（谷歌研究院）

Many problems in computer vision require dealing with sparse, unordered data in the form of point clouds. Permutation-equivariant networks have become a popular solution-they operate on individual data points with simple perceptrons and extract contextual information with global pooling. This can be achieved with a simple normalization of the feature maps, a global operation that is unaffected by the order. In this paper, we propose Attentive Context Normalization (ACN), a simple yet effective technique to build permutation-equivariant networks robust to outliers. Specifically, we show how to …

2021-02-01cs.CV

Point-to-Pose Voting based Hand Pose Estimation using Residual Permutation Equivariant Layer

Technical University of Munich（慕尼黑工业大学）；German Aerospace Center（德国航空航天中心）

Recently, 3D input data based hand pose estimation methods have shown state-of-the-art performance, because 3D data capture more spatial information than the depth image. Whereas 3D voxel-based methods need a large amount of memory, PointNet based methods need tedious preprocessing steps such as K-nearest neighbour search for each point. In this paper, we present a novel deep learning hand pose estimation method for an unordered point cloud. Our method takes 1024 3D points as input and does not require additional information. We use Permutation Equivariant Layer (PEL) as the basic element, whe…

2018-12-05cs.CV

等变层与不变层：点云分类的骨干网络与池化比较研究

Equivariant vs. Invariant Layers: A Comparison of Backbone and Pooling for Point Cloud Classification

Vanderbilt University（范德堡大学）

该研究针对点云分类任务，探究置换等变骨干网络与置换不变全局池化的相互作用，发现池化层选择对性能影响显著，为设计更优的置换不变集合神经网络提供参考。

2024-07-12cs.CVcs.LG

π³：排列等变视觉几何学习

$π^3$: Permutation-Equivariant Visual Geometry Learning

Shanghai Jiao Tong University（上海交通大学）；Shanghai AI Laboratory（上海人工智能实验室）；Shanghai Innovation Institute（上海创新研究院）；Zhejiang University（浙江大学）；University of Science and Technology of China（中国科学技术大学）；Fudan University（复旦大学）

π³通过排列等变架构实现无需参考视角的视觉几何重建，提升相机姿态和点地图重建的准确性和鲁棒性。

2026-03-07cs.CV

置换等变量子卷积神经网络

Permutation-equivariant quantum convolutional neural networks

Istituto Nazionale di Ottica del Consiglio Nazionale delle Ricerche (CNR-INO)（意大利国家光学研究所（国家研究委员会光学研究所））；University of Florence（佛罗伦萨大学）；European Laboratory for Non-Linear Spectroscopy (LENS)（欧洲非线性光谱实验室）

借助几何量子机器学习，本文提出了遵循对称群及其子群的等变量子卷积神经网络架构，通过优化像素到量子比特的嵌入顺序及引入dropout策略，在图像与图分类任务中显著提升了性能。

2024-04-28cs.AIcs.CVcs.LG

Deep Permutation Equivariant Structure from Motion

Weizmann Institute of Science（魏茨曼科学研究学院）；NVIDIA Research（英伟达研究院）

Existing deep methods produce highly accurate 3D reconstructions in stereo and multiview stereo settings, i.e., when cameras are both internally and externally calibrated. Nevertheless, the challenge of simultaneous recovery of camera poses and 3D scene structure in multiview settings with deep networks is still outstanding. Inspired by projective factorization for Structure from Motion (SFM) and by deep matrix completion techniques, we propose a neural network architecture that, given a set of point tracks in multiple images of a static scene, recovers both the camera parameters and a (sparse…

2021-10-24cs.CVcs.LG

更多相关论文收起更多论文

MeshFlow: 基于等变流匹配的网格生成

MeshFlow: Mesh Generation with Equivariant Flow Matching

City University of Hong Kong（香港城市大学）；Stanford University（斯坦福大学）；The University of Texas, Austin（德克萨斯大学奥斯汀分校）

提出MeshFlow，利用等变最优传输流匹配模型直接生成三角网格，避免序列化，通过改进扩散变压器架构实现等变性，推理速度提升约18倍。

2026-08-24cs.CVcs.GR

3D-Rotation-Equivariant Quaternion Neural Networks

Shanghai Jiao Tong University（上海交通大学）；Tongji University（同济大学）

This paper proposes a set of rules to revise various neural networks for 3D point cloud processing to rotation-equivariant quaternion neural networks (REQNNs). We find that when a neural network uses quaternion features under certain conditions, the network feature naturally has the rotation-equivariance property. Rotation equivariance means that applying a specific rotation transformation to the input point cloud is equivalent to applying the same rotation transformation to all intermediate-layer quaternion features. Besides, the REQNN also ensures that the intermediate-layer features are inv…

2020-10-11cs.CVcs.LGstat.ML

A Simple and Universal Rotation Equivariant Point-cloud Network

Technion – Israel Institute of Technology（以色列理工学院）；NVIDIA Research（英伟达研究院）

Equivariance to permutations and rigid motions is an important inductive bias for various 3D learning problems. Recently it has been shown that the equivariant Tensor Field Network architecture is universal -- it can approximate any equivariant function. In this paper we suggest a much simpler architecture, prove that it enjoys the same universality guarantees and evaluate its performance on Modelnet40. The code to reproduce our experiments is available at \url{https://github.com/simpleinvariance/UniversalNetwork}

2022-05-27cs.CVcs.LG

Equivariant Mesh Attention Networks

University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Mila（米拉研究所）；Université de Montréal（蒙特利尔大学）；Imperial College London（帝国理工学院）；Qualcomm AI Research（高通人工智能研究院）

Equivariance to symmetries has proven to be a powerful inductive bias in deep learning research. Recent works on mesh processing have concentrated on various kinds of natural symmetries, including translations, rotations, scaling, node permutations, and gauge transformations. To date, no existing architecture is equivariant to all of these transformations. In this paper, we present an attention-based architecture for mesh data that is provably equivariant to all transformations mentioned above. Our pipeline relies on the use of relative tangential features: a simple, effective, equivariance-fr…

2022-08-27cs.CVcs.LGstat.ML

Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point clouds

Stanford University（斯坦福大学）；University of California, Berkeley（加州大学伯克利分校）；Lawrence Berkeley National Lab（劳伦斯伯克利国家实验室）；Google（谷歌）

We introduce tensor field neural networks, which are locally equivariant to 3D rotations, translations, and permutations of points at every layer. 3D rotation equivariance removes the need for data augmentation to identify features in arbitrary orientations. Our network uses filters built from spherical harmonics; due to the mathematical consequences of this filter choice, each layer accepts as input (and guarantees as output) scalars, vectors, and higher-order tensors, in the geometric sense of these terms. We demonstrate the capabilities of tensor field networks with tasks in geometry, physi…

2018-05-18cs.AIcs.CVcs.LG

Equivariant Multi-View Networks

University of Pennsylvania（宾夕法尼亚大学）

Several popular approaches to 3D vision tasks process multiple views of the input independently with deep neural networks pre-trained on natural images, achieving view permutation invariance through a single round of pooling over all views. We argue that this operation discards important information and leads to subpar global descriptors. In this paper, we propose a group convolutional approach to multiple view aggregation where convolutions are performed over a discrete subgroup of the rotation group, enabling, thus, joint reasoning over all views in an equivariant (instead of invariant) fash…

2019-10-27cs.CV

Conditional Set Generation with Transformers

Deepmind

A set is an unordered collection of unique elements--and yet many machine learning models that generate sets impose an implicit or explicit ordering. Since model performance can depend on the choice of order, any particular ordering can lead to sub-optimal results. An alternative solution is to use a permutation-equivariant set generator, which does not specify an order-ing. An example of such a generator is the DeepSet Prediction Network (DSPN). We introduce the Transformer Set Prediction Network (TSPN), a flexible permutation-equivariant model for set prediction based on the transformer, tha…

2020-07-01cs.CVcs.LG