English
Related papers

Related papers: Scale-Equivariant Deep Learning for 3D Data

200 papers

Accurate medical image segmentation is essential for diagnosis and treatment planning of diseases. Convolutional Neural Networks (CNNs) have achieved state-of-the-art performance for automatic medical image segmentation. However, they are…

Image and Video Processing · Electrical Eng. & Systems 2020-11-05 Ran Gu , Guotai Wang , Tao Song , Rui Huang , Michael Aertsen , Jan Deprest , Sébastien Ourselin , Tom Vercauteren , Shaoting Zhang

Filter-decomposition-based group equivariant convolutional neural networks (CNNs) have shown promising stability and data efficiency for 3D image feature extraction. However, these networks, which rely on parameter sharing and discrete…

Computer Vision and Pattern Recognition · Computer Science 2026-01-08 Wenzhao Zhao , Steffen Albert , Barbara D. Wichtmann , Angelika Maurer , Ulrike Attenberger , Frank G. Zöllner , Jürgen Hesser

Human face images usually appear with wide range of visual scales. The existing face representations pursue the bandwidth of handling scale variation via multi-scale scheme that assembles a finite series of predefined scales. Such…

Computer Vision and Pattern Recognition · Computer Science 2022-09-20 Hailin Shi , Hang Du , Yibo Hu , Jun Wang , Dan Zeng , Ting Yao

Medical image segmentation plays a vital role in various clinical applications, enabling accurate delineation and analysis of anatomical structures or pathological regions. Traditional CNNs have achieved remarkable success in this field.…

Image and Video Processing · Electrical Eng. & Systems 2024-04-18 Seyed M. R. Modaresi , Aomar Osmani , Mohammadreza Razzazi , Abdelghani Chibani

In this work, we focus on using convolution neural networks (CNN) to perform object recognition on the event data. In object recognition, it is important for a neural network to be robust to the variations of the data during testing. For…

Computer Vision and Pattern Recognition · Computer Science 2019-12-02 Ziyun Wang

Convolutional neural networks lack shift equivariance due to the presence of downsampling layers. In image classification, adaptive polyphase downsampling (APS-D) was recently proposed to make CNNs perfectly shift invariant. However, in…

Computer Vision and Pattern Recognition · Computer Science 2021-12-08 Anadi Chaman , Ivan Dokmanić

As a fundamental part of computational healthcare, Computer Tomography (CT) and Magnetic Resonance Imaging (MRI) provide volumetric data, making the development of algorithms for 3D image analysis a necessity. Despite being computationally…

Image and Video Processing · Electrical Eng. & Systems 2023-07-26 C. I. Ugwu , S. Casarin , O. Lanz

In the task of Object Recognition, there exists a dichotomy between the categorization of objects and estimating object pose, where the former necessitates a view-invariant representation, while the latter requires a representation capable…

Computer Vision and Pattern Recognition · Computer Science 2016-04-20 Mohamed Elhoseiny , Tarek El-Gaaly , Amr Bakry , Ahmed Elgammal

Extending the translation equivariance property of convolutional neural networks to larger symmetry groups has been shown to reduce sample complexity and enable more discriminative feature learning. Further, exploiting additional symmetries…

Computer Vision and Pattern Recognition · Computer Science 2025-02-12 Lisa Weijler , Pedro Hermosilla

Even though convolutional neural networks (CNN) has achieved near-human performance in various computer vision tasks, its ability to tolerate scale variations is limited. The popular practise is making the model bigger first, and then train…

Computer Vision and Pattern Recognition · Computer Science 2014-11-25 Yichong Xu , Tianjun Xiao , Jiaxing Zhang , Kuiyuan Yang , Zheng Zhang

Sketch-based modeling strives to bring the ease and immediacy of drawing to the 3D world. However, while drawings are easy for humans to create, they are very challenging for computers to interpret due to their sparsity and ambiguity. We…

Graphics · Computer Science 2018-06-20 Johanna Delanoy , Mathieu Aubry , Phillip Isola , Alexei A. Efros , Adrien Bousseau

We propose a framework for rotation and translation covariant deep learning using $SE(2)$ group convolutions. The group product of the special Euclidean motion group $SE(2)$ describes how a concatenation of two roto-translations results in…

Computer Vision and Pattern Recognition · Computer Science 2018-06-12 Erik J Bekkers , Maxime W Lafarge , Mitko Veta , Koen AJ Eppenhof , Josien PW Pluim , Remco Duits

Monocular 3D object parsing is highly desirable in various scenarios including occlusion reasoning and holistic scene interpretation. We present a deep convolutional neural network (CNN) architecture to localize semantic parts in 2D image…

Computer Vision and Pattern Recognition · Computer Science 2017-04-24 Chi Li , M. Zeeshan Zia , Quoc-Huy Tran , Xiang Yu , Gregory D. Hager , Manmohan Chandraker

Group Convolutional Neural Networks (G-CNNs) constrain learned features to respect the symmetries in the selected group, and lead to better generalization when these symmetries appear in the data. If this is not the case, however,…

Computer Vision and Pattern Recognition · Computer Science 2023-01-18 David W. Romero , Suhas Lohit

Convolutional neural networks (CNNs) have demonstrated remarkable results in image classification for benchmark tasks and practical applications. The CNNs with deeper architectures have achieved even higher performance recently thanks to…

Computer Vision and Pattern Recognition · Computer Science 2019-04-15 Ryo Takahashi , Takashi Matsubara , Kuniaki Uehara

In this work we establish the relation between optimal control and training deep Convolution Neural Networks (CNNs). We show that the forward propagation in CNNs can be interpreted as a time-dependent nonlinear differential equation and…

Neural and Evolutionary Computing · Computer Science 2017-06-23 Eldad Haber , Lars Ruthotto , Elliot Holtham , Seong-Hwan Jun

Convolutional Neural Networks (CNN) have been successful in processing data signals that are uniformly sampled in the spatial domain (e.g., images). However, most data signals do not natively exist on a grid, and in the process of being…

Computer Vision and Pattern Recognition · Computer Science 2019-01-09 Chiyu "Max" Jiang , Dequan Wang , Jingwei Huang , Philip Marcus , Matthias Nießner

In today's digital age, Convolutional Neural Networks (CNNs), a subset of Deep Learning (DL), are widely used for various computer vision tasks such as image classification, object detection, and image segmentation. There are numerous types…

Machine Learning · Computer Science 2024-02-29 Abolfazl Younesi , Mohsen Ansari , MohammadAmin Fazli , Alireza Ejlali , Muhammad Shafique , Jörg Henkel

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

This work investigates use of equivariant neural networks as efficient and high-performance frameworks for image reconstruction and denoising in nuclear medicine. Our work aims to tackle limitations of conventional Convolutional Neural…

Image and Video Processing · Electrical Eng. & Systems 2025-02-03 Amirreza Hashemi , Yuemeng Feng , Arman Rahmim , Hamid Sabet