中文
相关论文

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

200 篇论文

Existing techniques to encode spatial invariance within deep convolutional neural networks only model 2D transformation fields. This does not account for the fact that objects in a 2D space are a projection of 3D ones, and thus they have…

计算机视觉与模式识别 · 计算机科学 2020-03-26 Sunghun Joung , Seungryong Kim , Hanjae Kim , Minsu Kim , Ig-Jae Kim , Junghyun Cho , Kwanghoon Sohn

Homogenization is a technique commonly used in multiscale computational science and engineering for predicting collective response of heterogeneous materials and extracting effective mechanical properties. In this paper, a three-dimensional…

计算工程、金融与科学 · 计算机科学 2020-02-19 Chengping Rao , Yang Liu

With the substantial performance of neural networks in sensitive fields increases the need for interpretable deep learning models. Major challenge is to uncover the multiscale and distributed representation hidden inside the basket mappings…

计算机视觉与模式识别 · 计算机科学 2022-11-10 Piduguralla Manaswini , Jignesh S. Bhatt

In recent years, neural implicit representations have made remarkable progress in modeling of 3D shapes with arbitrary topology. In this work, we address two key limitations of such representations, in failing to capture local 3D geometric…

计算机视觉与模式识别 · 计算机科学 2022-04-01 Yunlu Chen , Basura Fernando , Hakan Bilen , Matthias Nießner , Efstratios Gavves

Transformers have attracted increasing interests in computer vision, but they still fall behind state-of-the-art convolutional networks. In this work, we show that while Transformers tend to have larger model capacity, their generalization…

计算机视觉与模式识别 · 计算机科学 2021-09-16 Zihang Dai , Hanxiao Liu , Quoc V. Le , Mingxing Tan

Convolutional Neural Networks (CNNs) are commonly thought to recognise objects by learning increasingly complex representations of object shapes. Some recent studies suggest a more important role of image textures. We here put these…

计算机视觉与模式识别 · 计算机科学 2022-11-11 Robert Geirhos , Patricia Rubisch , Claudio Michaelis , Matthias Bethge , Felix A. Wichmann , Wieland Brendel

Determining the relative pose of a previously unseen object between two images is pivotal to the success of generalizable object pose estimation. Existing approaches typically predict 3D translation utilizing the ground-truth object…

计算机视觉与模式识别 · 计算机科学 2025-03-18 Chen Zhao , Tong Zhang , Zheng Dang , Mathieu Salzmann

Convolutional neural networks have been highly successful in image-based learning tasks due to their translation equivariance property. Recent work has generalized the traditional convolutional layer of a convolutional neural network to…

计算机视觉与模式识别 · 计算机科学 2021-06-30 Monami Banerjee , Rudrasis Chakraborty , Jose Bouza , Baba C. Vemuri

Convolutional neural networks owe much of their success to hard-coding translation equivariance. Quantum convolutional neural networks (QCNNs) have been proposed as near-term quantum analogues, but the relevant notion of translation depends…

量子物理 · 物理学 2026-04-28 Dmitry Chirkov , Igor Lobanov

We present a novel algorithm for point cloud segmentation. Our approach transforms unstructured point clouds into regular voxel grids, and further uses a kernel-based interpolated variational autoencoder (VAE) architecture to encode the…

图形学 · 计算机科学 2019-08-21 Hsien-Yu Meng , Lin Gao , YuKun Lai , Dinesh Manocha

Quantum Neural Networks (QNNs) are suggested as one of the quantum algorithms which can be efficiently simulated with a low depth on near-term quantum hardware in the presence of noises. However, their performance highly relies on choosing…

量子物理 · 物理学 2024-03-14 Su Yeon Chang , Michele Grossi , Bertrand Le Saux , Sofia Vallecorsa

Convolutional Neural networks (CNN) have been the first choice of paradigm in many computer vision applications. The convolution operation however has a significant weakness which is it only operates on a local neighborhood of pixels, thus…

计算机视觉与模式识别 · 计算机科学 2022-06-14 Michael Yang

In this paper, we propose a novel formulation to extend CNNs to two-dimensional (2D) manifolds using orthogonal basis functions, called Zernike polynomials. In many areas, geometric features play a key role in understanding scientific…

计算机视觉与模式识别 · 计算机科学 2023-05-12 Zhiyu Sun , Ethan Rooke , Jerome Charton , Yusen He , Jia Lu , Stephen Baek

Deep learning with 3D data such as reconstructed point clouds and CAD models has received great research interests recently. However, the capability of using point clouds with convolutional neural network has been so far not fully explored.…

计算机视觉与模式识别 · 计算机科学 2018-03-30 Binh-Son Hua , Minh-Khoi Tran , Sai-Kit Yeung

In this paper we construct and theoretically analyse group equivariant convolutional kernel networks (CKNs) which are useful in understanding the geometry of (equivariant) CNNs through the lens of reproducing kernel Hilbert spaces (RKHSs).…

机器学习 · 计算机科学 2024-08-09 Soutrik Roy Chowdhury

Deep convolutional neural networks have revolutionized many machine learning and computer vision tasks, however, some remaining key challenges limit their wider use. These challenges include improving the network's robustness to…

计算机视觉与模式识别 · 计算机科学 2019-05-21 Eldad Haber , Keegan Lensink , Eran Treister , Lars Ruthotto

Convolutional networks are large linear systems divided into layers and connected by non-linear units. These units are the "articulations" that allow the network to adapt to the input. To understand how a network manages to solve a problem…

计算机视觉与模式识别 · 计算机科学 2019-11-15 Pablo Navarrete Michelini , Hanwen Liu , Yunhua Lu , Xingqun Jiang

This paper introduces a new model to learn graph neural networks equivariant to rotations, translations, reflections and permutations called E(n)-Equivariant Graph Neural Networks (EGNNs). In contrast with existing methods, our work does…

机器学习 · 计算机科学 2022-02-17 Victor Garcia Satorras , Emiel Hoogeboom , Max Welling

The design of convolutional neural architectures that are exactly equivariant to continuous translations is an active field of research. It promises to benefit scientific computing, notably by making existing imaging systems more physically…

计算机视觉与模式识别 · 计算机科学 2025-06-19 Jérémy Scanvic , Quentin Barthélemy , Julián Tachella

The conventional pose estimation of a 3D object usually requires the knowledge of the 3D model of the object. Even with the recent development in convolutional neural networks (CNNs), a 3D model is often necessary in the final estimation.…

机器人学 · 计算机科学 2019-01-01 Zhongang Cai , Cunjun Yu , Quang-Cuong Pham