中文
相关论文

相关论文: CubeNet: Equivariance to 3D Rotation and Translati…

200 篇论文

Group equivariant and steerable convolutional neural networks (regular and steerable G-CNNs) have recently emerged as a very effective model class for learning from signal data such as 2D and 3D images, video, and other data where…

机器学习 · 计算机科学 2018-04-02 Taco S. Cohen , Mario Geiger , Maurice Weiler

We introduce the SE(3)-Transformer, a variant of the self-attention module for 3D point clouds and graphs, which is equivariant under continuous 3D roto-translations. Equivariance is important to ensure stable and predictable performance in…

机器学习 · 计算机科学 2020-11-26 Fabian B. Fuchs , Daniel E. Worrall , Volker Fischer , Max Welling

Convolutional Neural Networks (CNN) have been successful in processing data signals that are uniformly sampled in the spatial domain (e.g., images). However, most data signals do not natively exist on a grid, and in the process of being…

计算机视觉与模式识别 · 计算机科学 2019-01-09 Chiyu "Max" Jiang , Dequan Wang , Jingwei Huang , Philip Marcus , Matthias Nießner

Although provably robust to translational perturbations, convolutional neural networks (CNNs) are known to suffer from extreme performance degradation when presented at test time with more general geometric transformations of inputs.…

计算机视觉与模式识别 · 计算机科学 2022-03-31 Lachlan Ewen MacDonald , Sameera Ramasinghe , Simon Lucey

3D point clouds deep learning is a promising field of research that allows a neural network to learn features of point clouds directly, making it a robust tool for solving 3D scene understanding tasks. While recent works show that point…

计算机视觉与模式识别 · 计算机科学 2022-03-22 Zhiyuan Zhang , Binh-Son Hua , Sai-Kit Yeung

Deep convolutional neural networks (CNNs) have been intensively used for multi-class segmentation of data from different modalities and achieved state-of-the-art performances. However, a common problem when dealing with large, high…

计算机视觉与模式识别 · 计算机科学 2018-04-13 Chengjia Wang , Tom MacGillivray , Gillian Macnaught , Guang Yang , David Newby

Convolutional Neural Networks (CNN) have been regarded as a powerful class of models for image recognition problems. Nevertheless, it is not trivial when utilizing a CNN for learning spatio-temporal video representation. A few studies have…

计算机视觉与模式识别 · 计算机科学 2017-11-29 Zhaofan Qiu , Ting Yao , Tao Mei

In this paper we show how Group Equivariant Convolutional Neural Networks use subsampling to learn to break equivariance to their symmetries. We focus on 2D rotations and reflections and investigate the impact of broken equivariance on…

计算机视觉与模式识别 · 计算机科学 2023-08-23 Tom Edixhoven , Attila Lengyel , Jan van Gemert

This paper proposes a convolution structure for learning SE(3)-equivariant features from 3D point clouds. It can be viewed as an equivariant version of kernel point convolutions (KPConv), a widely used convolution form to process point…

计算机视觉与模式识别 · 计算机科学 2023-06-16 Minghan Zhu , Maani Ghaffari , William A. Clark , Huei Peng

Objects in aerial images have greater variations in scale and orientation than in typical images, so detection is more difficult. Convolutional neural networks use a variety of frequency- and orientation-specific kernels to identify objects…

计算机视觉与模式识别 · 计算机科学 2021-11-08 Guo-Ye Yang , Xiang-Li Li , Ralph R. Martin , Shi-Min Hu

Recent progresses in 3D deep learning has shown that it is possible to design special convolution operators to consume point cloud data. However, a typical drawback is that rotation invariance is often not guaranteed, resulting in networks…

计算机视觉与模式识别 · 计算机科学 2019-08-20 Zhiyuan Zhang , Binh-Son Hua , David W. Rosen , Sai-Kit Yeung

With the impressive capability to capture visual content, deep convolutional neural networks (CNN) have demon- strated promising performance in various vision-based ap- plications, such as classification, recognition, and objec- t…

计算机视觉与模式识别 · 计算机科学 2015-09-16 Zhen Liu

The translation equivariance of convolutions can make convolutional neural networks translation equivariant or invariant. Equivariance to other transformations (e.g. rotations, affine transformations, scalings) may also be desirable as soon…

信号处理 · 电气工程与系统科学 2021-05-05 Mateus Sangalli , Samy Blusseau , Santiago Velasco-Forero , Jesus Angulo

Deploying 3D graph neural networks (GNNs) that are equivariant to 3D rotations (the group SO(3)) on edge devices is challenging due to their high computational cost. This paper addresses the problem by compressing and accelerating an…

机器学习 · 计算机科学 2026-03-04 Haoyu Zhou , Ping Xue , Hao Zhang , Tianfan Fu

Convolutional kernels are basic and vital components of deep Convolutional Neural Networks (CNN). In this paper, we equip convolutional kernels with shape attributes to generate the deep Irregular Convolutional Neural Networks (ICNN).…

计算机视觉与模式识别 · 计算机科学 2017-06-27 Jiabin Ma , Wei Wang , Liang Wang

Recent success in training deep neural networks have prompted active investigation into the features learned on their intermediate layers. Such research is difficult because it requires making sense of non-linear computations performed by…

机器学习 · 计算机科学 2016-03-01 Yixuan Li , Jason Yosinski , Jeff Clune , Hod Lipson , John Hopcroft

Many problems in science and engineering can be formulated in terms of geometric patterns in high-dimensional spaces. We present high-dimensional convolutional networks (ConvNets) for pattern recognition problems that arise in the context…

计算机视觉与模式识别 · 计算机科学 2020-05-19 Christopher Choy , Junha Lee , Rene Ranftl , Jaesik Park , Vladlen Koltun

Several recent works have empirically observed that Convolutional Neural Nets (CNNs) are (approximately) invertible. To understand this approximate invertibility phenomenon and how to leverage it more effectively, we focus on a theoretical…

机器学习 · 统计学 2017-05-25 Anna C. Gilbert , Yi Zhang , Kibok Lee , Yuting Zhang , Honglak Lee

Neural networks in the real domain have been studied for a long time and achieved promising results in many vision tasks for recent years. However, the extensions of the neural network models in other number fields and their potential…

计算机视觉与模式识别 · 计算机科学 2019-03-05 Xuanyu Zhu , Yi Xu , Hongteng Xu , Changjian Chen

With the beginning of the noisy intermediate-scale quantum (NISQ) era, a quantum neural network (QNN) has recently emerged as a solution for several specific problems that classical neural networks cannot solve. Moreover, a quantum…

量子物理 · 物理学 2022-10-19 Hankyul Baek , Won Joon Yun , Joongheon Kim