English
Related papers

Related papers: Truly shift-invariant convolutional neural network…

200 papers

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

Convolutional neural networks have shown remarkable performance in recent years on various computer vision problems. However, the traditional convolutional neural network architecture lacks a critical property: shift equivariance and…

Computer Vision and Pattern Recognition · Computer Science 2025-11-27 Quentin Gabot , Teck-Yian Lim , Jérémy Fix , Joana Frontera-Pons , Chengfang Ren , Jean-Philippe Ovarlez

Radio spectrum monitoring in contested environments motivates the need for reliable automatic signal classification technology. Prior work highlights deep learning as a promising approach, but existing models depend on brute-force Doppler…

Signal Processing · Electrical Eng. & Systems 2025-11-19 Avi Bagchi , Dwight Hutchenson

We propose learnable polyphase sampling (LPS), a pair of learnable down/upsampling layers that enable truly shift-invariant and equivariant convolutional networks. LPS can be trained end-to-end from data and generalizes existing handcrafted…

Computer Vision and Pattern Recognition · Computer Science 2022-10-17 Renan A. Rojas-Gomez , Teck-Yian Lim , Alexander G. Schwing , Minh N. Do , Raymond A. Yeh

Downsampling operators break the shift invariance of convolutional neural networks (CNNs) and this affects the robustness of features learned by CNNs when dealing with even small pixel-level shift. Through a large-scale correlation analysis…

Computer Vision and Pattern Recognition · Computer Science 2024-12-03 Sourajit Saha , Tejas Gokhale

Modern convolutional networks are not shift-invariant, as small input shifts or translations can cause drastic changes in the output. Commonly used downsampling methods, such as max-pooling, strided-convolution, and average-pooling, ignore…

Computer Vision and Pattern Recognition · Computer Science 2019-06-11 Richard Zhang

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

The convolutional neural networks (CNNs) are not inherently shift invariant or equivariant. The downsampling operation, used in CNNs, is one of the key reasons which breaks the shift invariant property of a CNN. Conversely, downsampling…

Computer Vision and Pattern Recognition · Computer Science 2026-03-19 Jaspreet Singh , Petra Bosilj , Grzegorz Cielniak

Although CNNs are believed to be invariant to translations, recent works have shown this is not the case, due to aliasing effects that stem from downsampling layers. The existing architectural solutions to prevent aliasing are partial since…

Computer Vision and Pattern Recognition · Computer Science 2025-10-27 Hagay Michaeli , Tomer Michaeli , Daniel Soudry

This paper focuses on improving the mathematical interpretability of convolutional neural networks (CNNs) in the context of image classification. Specifically, we tackle the instability issue arising in their first layer, which tends to…

Computer Vision and Pattern Recognition · Computer Science 2025-04-21 Hubert Leterme , Kévin Polisano , Valérie Perrier , Karteek Alahari

We address the problem that state-of-the-art Convolution Neural Networks (CNN) classifiers are not invariant to small shifts. The problem can be solved by the removal of sub-sampling operations such as stride and max pooling, but at a cost…

Computer Vision and Pattern Recognition · Computer Science 2019-11-27 Ganesh Sundaramoorthi , Timothy E. Wang

Convolutional neural networks have achieved great success in various vision tasks; however, they incur heavy resource costs. By using deeper and wider networks, network accuracy can be improved rapidly. However, in an environment with…

Computer Vision and Pattern Recognition · Computer Science 2018-11-01 Yunho Jeon , Junmo Kim

Convolutional Neural Networks (CNNs) are commonly assumed to be invariant to small image transformations: either because of the convolutional architecture or because they were trained using data augmentation. Recently, several authors have…

Computer Vision and Pattern Recognition · Computer Science 2020-01-24 Aharon Azulay , Yair Weiss

In this paper we challenge the common assumption that convolutional layers in modern CNNs are translation invariant. We show that CNNs can and will exploit the absolute spatial location by learning filters that respond exclusively to…

Computer Vision and Pattern Recognition · Computer Science 2020-06-02 Osman Semih Kayhan , Jan C. van Gemert

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

Inverse problems exist in many domains such as phase imaging, image processing, and computer vision. These problems are often solved with application-specific algorithms, even though their nature remains the same: mapping input image(s) to…

Computational Physics · Physics 2021-10-22 Feng Wang , Alberto Eljarrat , Johannes Müller , Trond Henninen , Erni Rolf , Christoph Koch

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…

Computer Vision and Pattern Recognition · Computer Science 2018-01-08 Eric Kauderer-Abrams

The convolutional neural network (CNN) remains an essential tool in solving computer vision problems. Standard convolutional architectures consist of stacked layers of operations that progressively downscale the image. Aliasing is a…

Image and Video Processing · Electrical Eng. & Systems 2021-02-16 Antônio H. Ribeiro , Thomas B. Schön

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…

Computer Vision and Pattern Recognition · Computer Science 2020-02-07 Ivan Sosnovik , Michał Szmaja , Arnold Smeulders

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
‹ Prev 1 2 3 10 Next ›