中文
相关论文

相关论文: Roto-Translation Covariant Convolutional Networks …

200 篇论文

Rotation invariance and translation invariance have great values in image recognition tasks. In this paper, we bring a new architecture in convolutional neural network (CNN) named cyclic convolutional layer to achieve rotation invariance in…

计算机视觉与模式识别 · 计算机科学 2017-06-20 Shiyuan Li

Extracting discriminative local features that are invariant to imaging variations is an integral part of establishing correspondences between images. In this work, we introduce a self-supervised learning framework to extract discriminative…

计算机视觉与模式识别 · 计算机科学 2023-03-29 Jongmin Lee , Byungjin Kim , Seungwook Kim , Minsu Cho

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.…

计算机视觉与模式识别 · 计算机科学 2023-10-13 Facundo Manuel Quiroga , Franco Ronchetti , Laura Lanzarini , Aurelio Fernandez-Bariviera

Convolutional Neural Networks have revolutionized vision applications. There are image domains and representations, however, that cannot be handled by standard CNNs (e.g., spherical images, superpixels). Such data are usually processed…

计算机视觉与模式识别 · 计算机科学 2022-07-20 David Hart , Michael Whitney , Bryan Morse

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.…

计算机视觉与模式识别 · 计算机科学 2018-03-19 Diego Marcos , Michele Volpi , Benjamin Kellenberger , Devis Tuia

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…

机器学习 · 计算机科学 2018-03-20 Maurice Weiler , Fred A. Hamprecht , Martin Storath

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

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

Convolutional neural networks (CNNs) achieved the state-of-the-art performance in medical image segmentation due to their ability to extract highly complex feature representations. However, it is argued in recent studies that traditional…

计算机视觉与模式识别 · 计算机科学 2025-03-31 Zhendi Gong , Andrew P. French , Guoping Qiu , Xin Chen

Spherical convolutional networks have been introduced recently as tools to learn powerful feature representations of 3D shapes. Spherical CNNs are equivariant to 3D rotations making them ideally suited to applications where 3D data may be…

计算机视觉与模式识别 · 计算机科学 2019-05-16 Carlos Esteves , Avneesh Sud , Zhengyi Luo , Kostas Daniilidis , Ameesh Makadia

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…

计算机视觉与模式识别 · 计算机科学 2022-11-08 Mateus Sangalli , Samy Blusseau , Santiago Velasco-Forero , Jesus Angulo

The majority of deep learning (DL) based deformable image registration methods use convolutional neural networks (CNNs) to estimate displacement fields from pairs of moving and fixed images. This, however, requires the convolutional kernels…

图像与视频处理 · 电气工程与系统科学 2022-08-02 Yihao Liu , Lianrui Zuo , Shuo Han , Yuan Xue , Jerry L. Prince , Aaron Carass

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…

计算机视觉与模式识别 · 计算机科学 2018-07-06 Diego Marcos , Michele Volpi , Nikos Komodakis , Devis Tuia

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…

计算机视觉与模式识别 · 计算机科学 2019-12-04 Xu Shen , Xinmei Tian , Anfeng He , Shaoyan Sun , Dacheng Tao

We present Roto-Translation Equivariant Spherical Deconvolution (RT-ESD), an $E(3)\times SO(3)$ equivariant framework for sparse deconvolution of volumes where each voxel contains a spherical signal. Such 6D data naturally arises in…

图像与视频处理 · 电气工程与系统科学 2023-04-14 Axel Elaldi , Guido Gerig , Neel Dey

We present a PDE-based framework that generalizes Group equivariant Convolutional Neural Networks (G-CNNs). In this framework, a network layer is seen as a set of PDE-solvers where geometrically meaningful PDE-coefficients become the…

机器学习 · 计算机科学 2022-08-24 Bart Smets , Jim Portegies , Erik Bekkers , Remco Duits

This paper investigates the super-resolution (SR) of velocity fields in two-dimensional fluids from the viewpoint of rotational equivariance. SR refers to techniques that estimate high-resolution images from those in low resolution and has…

流体动力学 · 物理学 2022-10-26 Yuki Yasuda , Ryo Onishi

For many years, it has been shown how much exploiting equivariances can be beneficial when solving image analysis tasks. For example, the superiority of convolutional neural networks (CNNs) compared to dense networks mainly comes from an…

计算机视觉与模式识别 · 计算机科学 2023-04-20 Valentin Delchevalerie , Alexandre Mayer , Adrien Bibal , Benoît Frénay

This paper develops a rotation-invariant needlet convolution for rotation group SO(3) to distill multiscale information of spherical signals. The spherical needlet transform is generalized from $\mathbb{S}^2$ onto the SO(3) group, which…

图像与视频处理 · 电气工程与系统科学 2022-06-22 Kai Yi , Jialin Chen , Yu Guang Wang , Bingxin Zhou , Pietro Liò , Yanan Fan , Jan Hamann

Within the world of machine learning there exists a wide range of different methods with respective advantages and applications. This paper seeks to present and discuss one such method, namely Convolutional Neural Networks (CNNs). CNNs are…

计算机视觉与模式识别 · 计算机科学 2020-11-30 Lars Lien Ankile , Morgan Feet Heggland , Kjartan Krange