中文
相关论文

相关论文: Convolutional layers are equivariant to discrete s…

200 篇论文

State-of-the-art deep learning systems often require large amounts of data and computation. For this reason, leveraging known or unknown structure of the data is paramount. Convolutional neural networks (CNNs) are successful examples of…

计算机视觉与模式识别 · 计算机科学 2020-12-07 Carlos Esteves

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 effectiveness of Convolutional Neural Networks (CNNs) has been substantially attributed to their built-in property of translation equivariance. However, CNNs do not have embedded mechanisms to handle other types of transformations. In…

计算机视觉与模式识别 · 计算机科学 2020-02-07 Ivan Sosnovik , Michał Szmaja , Arnold Smeulders

Translating or rotating an input image should not affect the results of many computer vision tasks. Convolutional neural networks (CNNs) are already translation equivariant: input image translations produce proportionate feature map…

计算机视觉与模式识别 · 计算机科学 2017-04-12 Daniel E. Worrall , Stephan J. Garbin , Daniyar Turmukhambetov , Gabriel J. Brostow

We propose a generalization of convolutional neural networks (CNNs) to irregular domains, through the use of a translation operator on a graph structure. In regular settings such as images, convolutional layers are designed by translating a…

离散数学 · 计算机科学 2018-11-06 Bastien Pasdeloup , Vincent Gripon , Jean-Charles Vialatte , Dominique Pastor , Pascal Frossard

In this work we investigate how to achieve equivariance to input transformations in deep networks, purely from data, without being given a model of those transformations. Convolutional Neural Networks (CNNs), for example, are equivariant to…

计算机视觉与模式识别 · 计算机科学 2021-11-29 Jianbo Jiao , João F. Henriques

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

Equivariant neural networks are a class of neural networks designed to preserve symmetries inherent in the data. In this paper, we introduce a general method for modifying a neural network to enforce equivariance, a process we refer to as…

机器学习 · 计算机科学 2025-11-19 Erkao Bao , Jingcheng Lu , Linqi Song , Nathan Hart-Hodgson , William Parson , Yanheng Zhou

The translational equivariant nature of Convolutional Neural Networks (CNNs) is a reason for its great success in computer vision. However, networks do not enjoy more general equivariance properties such as rotation or scaling, ultimately…

计算机视觉与模式识别 · 计算机科学 2023-03-02 Zikai Sun , Thierry Blu

We introduce Group equivariant Convolutional Neural Networks (G-CNNs), a natural generalization of convolutional neural networks that reduces sample complexity by exploiting symmetries. G-CNNs use G-convolutions, a new type of layer that…

机器学习 · 计算机科学 2016-06-06 Taco S. Cohen , Max Welling

Although Convolutional Neural Networks (CNNs) are widely used, their translation invariance (ability to deal with translated inputs) is still subject to some controversy. We explore this question using translation-sensitivity maps to…

机器学习 · 计算机科学 2021-04-20 Johannes C. Myburgh , Coenraad Mouton , Marelie H. Davel

Convolutional Neural Networks (CNNs) are extremely efficient, since they exploit the inherent translation-invariance of natural images. However, translation is just one of a myriad of useful spatial transformations. Can the same efficiency…

计算机视觉与模式识别 · 计算机科学 2021-12-02 João F. Henriques , Andrea Vedaldi

In this proceeding we give an overview of the idea of covariance (or equivariance) featured in the recent development of convolutional neural networks (CNNs). We study the similarities and differences between the use of covariance in…

机器学习 · 计算机科学 2019-06-07 Miranda C. N. Cheng , Vassilis Anagiannis , Maurice Weiler , Pim de Haan , Taco S. Cohen , Max Welling

The convolutional layers of standard convolutional neural networks (CNNs) are equivariant to translation. However, the convolution and fully-connected layers are not equivariant or invariant to other affine geometric transformations.…

计算机视觉与模式识别 · 计算机科学 2022-09-23 Jaspreet Singh , Chandan Singh

The ability of convolutional neural networks (CNNs) to recognize objects regardless of their position in the image is due to the translation-equivariance of the convolutional operation. Group-equivariant CNNs transfer this equivariance to…

计算机视觉与模式识别 · 计算机科学 2023-04-13 Thomas Wimmer , Vladimir Golkov , Hoai Nam Dang , Moritz Zaiss , Andreas Maier , Daniel Cremers

When seeing a new object, humans can immediately recognize it across different retinal locations: the internal object representation is invariant to translation. It is commonly believed that Convolutional Neural Networks (CNNs) are…

计算机视觉与模式识别 · 计算机科学 2021-10-13 Valerio Biscione , Jeffrey S. Bowers

When seeing a new object, humans can immediately recognize it across different retinal locations: we say that the internal object representation is invariant to translation. It is commonly believed that Convolutional Neural Networks (CNNs)…

计算机视觉与模式识别 · 计算机科学 2020-11-25 Valerio Biscione , Jeffrey Bowers

Despite the importance of image representations such as histograms of oriented gradients and deep Convolutional Neural Networks (CNN), our theoretical understanding of them remains limited. Aiming at filling this gap, we investigate three…

计算机视觉与模式识别 · 计算机科学 2015-06-23 Karel Lenc , Andrea Vedaldi

A fundamental problem in object recognition is the development of image representations that are invariant to common transformations such as translation, rotation, and small deformations. There are multiple hypotheses regarding the source…

计算机视觉与模式识别 · 计算机科学 2018-01-08 Eric Kauderer-Abrams

We review a novel neural network architecture called lattice gauge equivariant convolutional neural networks (L-CNNs), which can be applied to generic machine learning problems in lattice gauge theory while exactly preserving gauge…

高能物理 - 格点 · 物理学 2021-11-09 Matteo Favoni , Andreas Ipp , David I. Müller , Daniel Schuh
‹ 上一页 1 2 3 10 下一页 ›