English
Related papers

Related papers: Normalization-Equivariant Neural Networks with App…

200 papers

Non-local self-similarity is well-known to be an effective prior for the image denoising problem. However, little work has been done to incorporate it in convolutional neural networks, which surpass non-local model-based methods despite…

Image and Video Processing · Electrical Eng. & Systems 2023-07-19 Diego Valsesia , Giulia Fracastoro , Enrico Magli

Deep convolutional neural networks trained on large datsets have emerged as an intriguing alternative for compressing images and solving inverse problems such as denoising and compressive sensing. However, it has only recently been realized…

Machine Learning · Computer Science 2019-07-09 Reinhard Heckel

Equivariant neural networks have shown improved performance, expressiveness and sample complexity on symmetrical domains. But for some specific symmetries, representations, and choice of coordinates, the most common point-wise activations,…

Machine Learning · Computer Science 2024-01-18 Marco Pacini , Xiaowen Dong , Bruno Lepri , Gabriele Santin

Conventionally, image denoising and high-level vision tasks are handled separately in computer vision. In this paper, we cope with the two jointly and explore the mutual influence between them. First we propose a convolutional neural…

Computer Vision and Pattern Recognition · Computer Science 2018-04-18 Ding Liu , Bihan Wen , Xianming Liu , Zhangyang Wang , Thomas S. Huang

The success of deep learning is inseparable from normalization layers. Researchers have proposed various normalization functions, and each of them has both advantages and disadvantages. In response, efforts have been made to design a…

Machine Learning · Computer Science 2024-02-20 Zikai Zhou , Shuo Zhang , Ziruo Wang , Huanran Chen

Convolution and transposed convolution are fundamental operators widely used in neural networks. However, transposed convolution (a.k.a. deconvolution) does not serve as a true inverse of convolution due to inherent differences in their…

Computer Vision and Pattern Recognition · Computer Science 2025-08-18 Xuhong Huang , Shiqi Liu , Kai Zhang , Ying Tai , Jian Yang , Hui Zeng , Lei Zhang

Dense depth and surface normal predictors should possess the equivariant property to cropping-and-resizing -- cropping the input image should result in cropping the same output image. However, we find that state-of-the-art depth and normal…

Computer Vision and Pattern Recognition · Computer Science 2023-10-18 Yuanyi Zhong , Anand Bhattad , Yu-Xiong Wang , David Forsyth

Normalization techniques have become a basic component in modern convolutional neural networks (ConvNets). In particular, many recent works demonstrate that promoting the orthogonality of the weights helps train deep models and improve…

Computer Vision and Pattern Recognition · Computer Science 2022-01-05 Sheng Liu , Xiao Li , Yuexiang Zhai , Chong You , Zhihui Zhu , Carlos Fernandez-Granda , Qing Qu

We propose to learn a fully-convolutional network model that consists of a Chain of Identity Mapping Modules and residual on the residual architecture for image denoising. Our network structure possesses three distinctive features that are…

Computer Vision and Pattern Recognition · Computer Science 2020-04-29 Saeed Anwar , Cong Phuoc Huynh , Fatih Porikli

In this paper we present a generalized Deep Learning-based approach for solving ill-posed large-scale inverse problems occuring in medical image reconstruction. Recently, Deep Learning methods using iterative neural networks and cascaded…

Image and Video Processing · Electrical Eng. & Systems 2020-08-26 Andreas Kofler , Markus Haltmeier , Tobias Schaeffter , Marc Kachelrieß , Marc Dewey , Christian Wald , Christoph Kolbitsch

Using weight decay to penalize the L2 norms of weights in neural networks has been a standard training practice to regularize the complexity of networks. In this paper, we show that a family of regularizers, including weight decay, is…

Machine Learning · Computer Science 2022-06-09 Ziquan Liu , Yufei Cui , Antoni B. Chan

One key ingredient of image restoration is to define a realistic prior on clean images to complete the missing information in the observation. State-of-the-art restoration methods rely on a neural network to encode this prior. Typical image…

Image and Video Processing · Electrical Eng. & Systems 2025-11-14 Marien Renaud , Eliot Guez , Arthur Leclaire , Nicolas Papadakis

Training neural networks is an optimization problem, and finding a decent set of parameters through gradient descent can be a difficult task. A host of techniques has been developed to aid this process before and during the training phase.…

Machine Learning · Computer Science 2020-08-19 Divya Gaur , Joachim Folz , Andreas Dengel

The translational equivariant nature of Convolutional Neural Networks (CNNs) is a reason for its great success in computer vision. However, networks do not enjoy more general equivariance properties such as rotation or scaling, ultimately…

Computer Vision and Pattern Recognition · Computer Science 2023-03-02 Zikai Sun , Thierry Blu

Normalization layers are widely used in deep neural networks to stabilize training. In this paper, we consider the training of convolutional neural networks with gradient descent on a single training example. This optimization problem…

Machine Learning · Computer Science 2019-07-24 Zhenwei Dai , Reinhard Heckel

The translation equivariance of convolutional layers enables convolutional neural networks to generalize well on image problems. While translation equivariance provides a powerful inductive bias for images, we often additionally desire…

Machine Learning · Statistics 2020-09-25 Marc Finzi , Samuel Stanton , Pavel Izmailov , Andrew Gordon Wilson

Training state-of-the-art, deep neural networks is computationally expensive. One way to reduce the training time is to normalize the activities of the neurons. A recently introduced technique called batch normalization uses the…

Machine Learning · Statistics 2016-07-22 Jimmy Lei Ba , Jamie Ryan Kiros , Geoffrey E. Hinton

In recent years the use of convolutional layers to encode an inductive bias (translational equivariance) in neural networks has proven to be a very fruitful idea. The successes of this approach have motivated a line of research into…

For most state-of-the-art architectures, Rectified Linear Unit (ReLU) becomes a standard component accompanied with each layer. Although ReLU can ease the network training to an extent, the character of blocking negative values may suppress…

Computer Vision and Pattern Recognition · Computer Science 2017-11-20 Xuanyi Dong , Guoliang Kang , Kun Zhan , Yi Yang

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