English
Related papers

Related papers: Truly shift-equivariant convolutional neural netwo…

200 papers

In neural networks, the property of being equivariant to transformations improves generalization when the corresponding symmetry is present in the data. In particular, scale-equivariant networks are suited to computer vision tasks where the…

Machine Learning · Statistics 2022-10-11 Mateus Sangalli , Samy Blusseau , Santiago Velasco-Forero , Jesus Angulo

Deep convolutional neural networks achieve excellent image up-sampling performance. However, CNN-based methods tend to restore high-resolution results highly depending on traditional interpolations (e.g. bicubic). In this paper, we present…

Computer Vision and Pattern Recognition · Computer Science 2018-03-28 Bolun Cai , Xiangmin Xu , Kailing Guo , Kui Jia , Dacheng Tao

Deep convolutional neural networks (CNN) have recently been shown to generate promising results for aesthetics assessment. However, the performance of these deep CNN methods is often compromised by the constraint that the neural network…

Computer Vision and Pattern Recognition · Computer Science 2017-04-04 Shuang Ma , Jing Liu , Chang Wen Chen

The simplicity and effectiveness of the UNet architecture makes it ubiquitous in image restoration, image segmentation, and diffusion models. They are often assumed to be equivariant to translations, yet they traditionally consist of layers…

Computer Vision and Pattern Recognition · Computer Science 2026-03-13 Jérémy Scanvic , Quentin Barthélemy , Julián Tachella

Translating or rotating an input image should not affect the results of many computer vision tasks. Convolutional neural networks (CNNs) are already translation equivariant: input image translations produce proportionate feature map…

Computer Vision and Pattern Recognition · Computer Science 2017-04-12 Daniel E. Worrall , Stephan J. Garbin , Daniyar Turmukhambetov , Gabriel J. Brostow

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

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

Many convolutional neural networks (CNNs) rely on progressive downsampling of their feature maps to increase the network's receptive field and decrease computational cost. However, this comes at the price of losing granularity in the…

Computer Vision and Pattern Recognition · Computer Science 2023-05-17 Robin Hesse , Simone Schaub-Meyer , Stefan Roth

While scale-invariant modeling has substantially boosted the performance of visual recognition tasks, it remains largely under-explored in deep networks based image restoration. Naively applying those scale-invariant techniques (e.g.…

Computer Vision and Pattern Recognition · Computer Science 2019-12-20 Yuchen Fan , Jiahui Yu , Ding Liu , Thomas S. Huang

One impressive advantage of convolutional neural networks (CNNs) is their ability to automatically learn feature representation from raw pixels, eliminating the need for hand-designed procedures. However, recent methods for single image…

Computer Vision and Pattern Recognition · Computer Science 2016-07-27 Yifan Wang , Lijun Wang , Hongyu Wang , Peihua Li

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

Recently, the generalization behavior of Convolutional Neural Networks (CNN) is gradually transparent through explanation techniques with the frequency components decomposition. However, the importance of the phase spectrum of the image for…

Computer Vision and Pattern Recognition · Computer Science 2021-08-20 Guangyao Chen , Peixi Peng , Li Ma , Jia Li , Lin Du , Yonghong Tian

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

While accuracy is an evident criterion for ultrasound image segmentation, output consistency across different tests is equally crucial for tracking changes in regions of interest in applications such as monitoring the patients' response to…

Image and Video Processing · Electrical Eng. & Systems 2022-03-31 Mostafa Sharifzadeh , Habib Benali , Hassan Rivaz

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

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

Conformal symmetries, i.e.\ coordinate transformations that preserve angles, play a key role in many fields, including physics, mathematics, computer vision and (geometric) machine learning. Here we build a neural network that is…

Machine Learning · Computer Science 2025-05-20 Maksim Zhdanov , Nabil Iqbal , Erik Bekkers , Patrick Forré

Deep Convolutional Neural Networks (DCNNs) are used extensively in medical image segmentation and hence 3D navigation for robot-assisted Minimally Invasive Surgeries (MISs). However, current DCNNs usually use down sampling layers for…

Machine Learning · Computer Science 2020-06-05 Xiao-Yun Zhou , Jian-Qing Zheng , Peichao Li , Guang-Zhong Yang

Tomographic image reconstruction is relevant for many medical imaging modalities including X-ray, ultrasound (US) computed tomography (CT) and photoacoustics, for which the access to full angular range tomographic projections might be not…

Image and Video Processing · Electrical Eng. & Systems 2019-06-14 Valery Vishnevskiy , Richard Rau , Orcun Goksel

Convolutional Neural Networks (CNNs) have advanced significantly in visual representation learning and recognition. However, they face notable challenges in performance and computational efficiency when dealing with real-world, multi-scale…

Computer Vision and Pattern Recognition · Computer Science 2024-03-28 Wenzhuo Liu , Fei Zhu , Cheng-Lin Liu