English
Related papers

Related papers: Harmonic Networks: Deep Translation and Rotation E…

200 papers

CNNs exhibit inherent equivariance to image translation, leading to efficient parameter and data usage, faster learning, and improved robustness. The concept of translation equivariant networks has been successfully extended to rotation…

Computer Vision and Pattern Recognition · Computer Science 2024-11-07 Tomáš Karella , Adam Harmanec , Jan Kotera , Jan Blažek , Filip Šroubek

In many computer vision tasks, we expect a particular behavior of the output with respect to rotations of the input image. If this relationship is explicitly encoded, instead of treated as any other variation, the complexity of the problem…

Computer Vision and Pattern Recognition · Computer Science 2018-07-06 Diego Marcos , Michele Volpi , Nikos Komodakis , Devis Tuia

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…

Computer Vision and Pattern Recognition · Computer Science 2021-11-29 Jianbo Jiao , João F. Henriques

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…

Computer Vision and Pattern Recognition · Computer Science 2020-12-07 Carlos Esteves

In remote sensing images, the absolute orientation of objects is arbitrary. Depending on an object's orientation and on a sensor's flight path, objects of the same semantic class can be observed in different orientations in the same image.…

Computer Vision and Pattern Recognition · Computer Science 2018-03-19 Diego Marcos , Michele Volpi , Benjamin Kellenberger , Devis Tuia

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…

Computer Vision and Pattern Recognition · Computer Science 2023-03-02 Zikai Sun , Thierry Blu

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…

Computer Vision and Pattern Recognition · Computer Science 2021-12-02 João F. Henriques , Andrea Vedaldi

In many machine learning tasks it is desirable that a model's prediction transforms in an equivariant way under transformations of its input. Convolutional neural networks (CNNs) implement translational equivariance by construction; for…

Machine Learning · Computer Science 2018-03-20 Maurice Weiler , Fred A. Hamprecht , Martin Storath

Deep Convolutional Neural Networks (CNNs) are empirically known to be invariant to moderate translation but not to rotation in image classification. This paper proposes a deep CNN model, called CyCNN, which exploits polar mapping of input…

Computer Vision and Pattern Recognition · Computer Science 2020-07-23 Jinpyo Kim , Wooekun Jung , Hyungmo Kim , Jaejin Lee

Convolutional neural networks (CNNs) have achieved state-of-the-art results on many visual recognition tasks. However, current CNN models still exhibit a poor ability to be invariant to spatial transformations of images. Intuitively, with…

Computer Vision and Pattern Recognition · Computer Science 2019-12-04 Xu Shen , Xinmei Tian , Anfeng He , Shaoyan Sun , Dacheng Tao

We analyze the role of rotational equivariance in convolutional neural networks (CNNs) applied to spherical images. We compare the performance of the group equivariant networks known as S2CNNs and standard non-equivariant CNNs trained with…

Machine Learning · Computer Science 2022-07-13 Jan E. Gerken , Oscar Carlsson , Hampus Linander , Fredrik Ohlsson , Christoffer Petersson , Daniel Persson

In this paper, we introduce group convolutional neural networks (GCNNs) equivariant to color variation. GCNNs have been designed for a variety of geometric transformations from 2D and 3D rotation groups, to semi-groups such as scale.…

Computer Vision and Pattern Recognition · Computer Science 2026-04-14 Yulong Yang , Felix O'Mahony , Christine Allen-Blanchette

Convolutional Neural Networks (CNNs) have demonstrated state-of-the-art performance on many visual recognition tasks. However, the combination of convolution and pooling operations only shows invariance to small local location changes in…

Computer Vision and Pattern Recognition · Computer Science 2019-12-02 Xu Shen , Xinmei Tian , Shaoyan Sun , Dacheng Tao

This paper is concerned with a fundamental problem in geometric deep learning that arises in the construction of convolutional neural networks on surfaces. Due to curvature, the transport of filter kernels on surfaces results in a…

Computer Vision and Pattern Recognition · Computer Science 2020-06-03 Ruben Wiersma , Elmar Eisemann , Klaus Hildebrandt

Invariance to spatial transformations such as translations and rotations is a desirable property and a basic design principle for classification neural networks. However, the commonly used convolutional neural networks (CNNs) are actually…

Machine Learning · Computer Science 2023-06-30 Yihan Wang , Lijia Yu , Xiao-Shan Gao

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…

Computer Vision and Pattern Recognition · Computer Science 2015-06-23 Karel Lenc , Andrea Vedaldi

The purpose of this short and simple note is to clarify a common misconception about convolutional neural networks (CNNs). CNNs are made up of convolutional layers which are shift equivariant due to weight sharing. However, convolutional…

Computer Vision and Pattern Recognition · Computer Science 2023-12-08 Nick McGreivy , Ammar Hakim

Convolutional neural networks (CNNs) are inherently equivariant to translation. Efforts to embed other forms of equivariance have concentrated solely on rotation. We expand the notion of equivariance in CNNs through the Polar Transformer…

Computer Vision and Pattern Recognition · Computer Science 2018-02-02 Carlos Esteves , Christine Allen-Blanchette , Xiaowei Zhou , Kostas Daniilidis

Equivariance of neural networks to transformations helps to improve their performance and reduce generalization error in computer vision tasks, as they apply to datasets presenting symmetries (e.g. scalings, rotations, translations). The…

Computer Vision and Pattern Recognition · Computer Science 2022-11-08 Mateus Sangalli , Samy Blusseau , Santiago Velasco-Forero , Jesus Angulo

Convolutional Neural Networks (CNN) offer state of the art performance in various computer vision tasks. Many of those tasks require different subtypes of affine invariances (scale, rotational, translational) to image transformations.…

Computer Vision and Pattern Recognition · Computer Science 2023-10-13 Facundo Manuel Quiroga , Franco Ronchetti , Laura Lanzarini , Aurelio Fernandez-Bariviera
‹ Prev 1 2 3 10 Next ›