English
Related papers

Related papers: Convolution with even-sized kernels and symmetric …

200 papers

Large kernel convolutions offer a scalable alternative to vision transformers for high-resolution 3D volumetric analysis, yet naively increasing kernel size often leads to optimization instability. Motivated by the spatial bias inherent in…

Computer Vision and Pattern Recognition · Computer Science 2026-02-02 Ho Hin Lee , Quan Liu , Shunxing Bao , Yuankai Huo , Bennett A. Landman

Recent research shows that for training with $\ell_2$ loss, convolutional neural networks (CNNs) whose width (number of channels in convolutional layers) goes to infinity correspond to regression with respect to the CNN Gaussian Process…

Machine Learning · Computer Science 2019-11-05 Zhiyuan Li , Ruosong Wang , Dingli Yu , Simon S. Du , Wei Hu , Ruslan Salakhutdinov , Sanjeev Arora

Convolution kernels are the basic structural component of convolutional neural networks (CNNs). In the last years there has been a growing interest in fisheye cameras for many applications. However, the radially symmetric projection model…

Computer Vision and Pattern Recognition · Computer Science 2024-02-05 Bruno Berenguel-Baeta , Maria Santos-Villafranca , Jesus Bermudez-Cameo , Alejandro Perez-Yus , Jose J. Guerrero

Deploying deep Convolutional Neural Networks (CNNs) is impacted by their memory footprint and speed requirements, which mainly come from convolution. Widely-used convolution algorithms, im2col and MEC, produce a lowered matrix from an…

Computer Vision and Pattern Recognition · Computer Science 2021-04-20 Hossam Amer , Ahmed H. Salamah , Ahmad Sajedi , En-hui Yang

We propose a new method to create compact convolutional neural networks (CNNs) by exploiting sparse convolutions. Different from previous works that learn sparsity in models, we directly employ hand-crafted kernels with regular sparse…

Computer Vision and Pattern Recognition · Computer Science 2018-09-12 Chun-Fu Chen , Quanfu Fan , Marco Pistoia , Gwo Giun Lee

Modern deep neural networks require a tremendous amount of data to train, often needing hundreds or thousands of labeled examples to learn an effective representation. For these networks to work with less data, more structure must be built…

Computer Vision and Pattern Recognition · Computer Science 2019-03-06 Reuben Feinman , Brenden M. Lake

We present a convolutional network that is equivariant to rigid body motions. The model uses scalar-, vector-, and tensor fields over 3D Euclidean space to represent data, and equivariant convolutions to map between such representations.…

Machine Learning · Computer Science 2018-10-30 Maurice Weiler , Mario Geiger , Max Welling , Wouter Boomsma , Taco Cohen

Establishing correspondence between shapes is a fundamental problem in geometry processing, arising in a wide variety of applications. The problem is especially difficult in the setting of non-isometric deformations, as well as in the…

Computer Vision and Pattern Recognition · Computer Science 2016-05-23 Davide Boscaini , Jonathan Masci , Emanuele Rodolà , Michael M. Bronstein

We explore the symmetry of the mean k x k weight kernel in each layer of various convolutional neural networks. Unlike individual neurons, the mean kernels in internal layers tend to be symmetric about their centers instead of favoring…

Computer Vision and Pattern Recognition · Computer Science 2025-04-24 Bilal Alsallakh , Timothy Wroge , Vivek Miglani , Narine Kokhlikyan

Although equirectangular projection (ERP) is a convenient form to store omnidirectional images (also known as 360-degree images), it is neither equal-area nor conformal, thus not friendly to subsequent visual communication. In the context…

Image and Video Processing · Electrical Eng. & Systems 2021-12-28 Mu Li , Kede Ma , Jinxing Li , David Zhang

The large spatial/temporal/frequency scale of geoscience and remote-sensing datasets causes memory issues when using convolutional neural networks for (sub-) surface data segmentation. Recently developed fully reversible or fully invertible…

Geophysics · Physics 2024-07-02 Bas Peters , Eldad Haber , Keegan Lensink

We propose a spherical kernel for efficient graph convolution of 3D point clouds. Our metric-based kernels systematically quantize the local 3D space to identify distinctive geometric relationships in the data. Similar to the regular grid…

Computer Vision and Pattern Recognition · Computer Science 2020-03-24 Huan Lei , Naveed Akhtar , Ajmal Mian

We present first empirical results from our ongoing investigation of distribution shifts in image data used for various computer vision tasks. Instead of analyzing the original training and test data, we propose to study shifts in the…

Computer Vision and Pattern Recognition · Computer Science 2022-01-24 Paul Gavrikov , Janis Keuper

The state-of-the-art performance for several real-world problems is currently reached by convolutional neural networks (CNN). Such learning models exploit recent results in the field of deep learning, typically leading to highly performing,…

Machine Learning · Computer Science 2021-08-31 Giosuè Cataldo Marinò , Alessandro Petrini , Dario Malchiodi , Marco Frasca

Euclidean deep learning is often inadequate for addressing real-world signals where the representation space is irregular and curved with complex topologies. Interpreting the geometric properties of such feature spaces has become paramount…

Computer Vision and Pattern Recognition · Computer Science 2024-09-12 Ramzan Basheer , Deepak Mishra

The principle of equivariance to symmetry transformations enables a theoretically grounded approach to neural network architecture design. Equivariant networks have shown excellent performance and data efficiency on vision and medical…

Machine Learning · Computer Science 2019-05-15 Taco S. Cohen , Maurice Weiler , Berkay Kicanaoglu , Max Welling

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

Deep models have achieved significant process on single image super-resolution (SISR) tasks, in particular large models with large kernel ($3\times3$ or more). However, the heavy computational footprint of such models prevents their…

Computer Vision and Pattern Recognition · Computer Science 2024-03-13 Gang Wu , Junjun Jiang , Kui Jiang , Xianming Liu

An important goal in visual recognition is to devise image representations that are invariant to particular transformations. In this paper, we address this goal with a new type of convolutional neural network (CNN) whose invariance is…

Computer Vision and Pattern Recognition · Computer Science 2015-01-08 Julien Mairal , Piotr Koniusz , Zaid Harchaoui , Cordelia Schmid

We introduce a regularization loss based on kernel mean embeddings with rotation-invariant kernels on the hypersphere (also known as dot-product kernels) for self-supervised learning of image representations. Besides being fully competitive…

Computer Vision and Pattern Recognition · Computer Science 2023-03-09 Léon Zheng , Gilles Puy , Elisa Riccietti , Patrick Pérez , Rémi Gribonval