English
Related papers

Related papers: A Multi-Resolution Framework for U-Nets with Appli…

200 papers

Neural networks have seen limited use in prediction for high-dimensional data with small sample sizes, because they tend to overfit and require tuning many more hyperparameters than existing off-the-shelf machine learning methods. With…

Machine Learning · Statistics 2020-05-12 Jean Feng , Noah Simon

We propose a computational framework, Hetero-EUCLID, for segmentation and parameter identification to characterize the full hyperelastic behavior of all constituents of a heterogeneous material. In this work, we leverage the Bayesian-EUCLID…

Computational Engineering, Finance, and Science · Computer Science 2026-01-19 Kanhaiya Lal Chaurasiya , Saurav Dutta , Siddhant Kumar , Akshay Joshi

Recently, deep learning approaches with various network architectures have achieved significant performance improvement over existing iterative reconstruction methods in various imaging problems. However, it is still unclear why these deep…

Machine Learning · Statistics 2018-01-26 Jong Chul Ye , Yoseob Han , Eunju Cha

We use Deep Operator Networks (DeepONets) to perform super-resolution reconstruction of the solutions of two types of partial differential equations and compare the model predictions with the results obtained using conventional…

Image and Video Processing · Electrical Eng. & Systems 2024-10-29 Siyuan Yang

Understanding the details of small-scale convection and storm formation is crucial to accurately represent the larger-scale planetary dynamics. Presently, atmospheric scientists run high-resolution, storm-resolving simulations to capture…

Atmospheric and Oceanic Physics · Physics 2021-12-03 Harshini Mangipudi , Griffin Mooers , Mike Pritchard , Tom Beucler , Stephan Mandt

X-ray computed tomography (CT) using sparse projection views is a recent approach to reduce the radiation dose. However, due to the insufficient projection views, an analytic reconstruction approach using the filtered back projection (FBP)…

Computer Vision and Pattern Recognition · Computer Science 2018-03-29 Yoseob Han , Jong Chul Ye

In this paper we consider the limiting case of neural networks (NNs) architectures when the number of neurons in each hidden layer and the number of hidden layers tend to infinity thus forming a continuum, and we derive approximation errors…

Machine Learning · Computer Science 2026-05-12 Christophe Prieur , Mircea Lazar , Bogdan Robu

Image dehazing has witnessed significant advancements with the development of deep learning models. However, most existing methods focus solely on single-modal RGB features, neglecting the inherent correlation between scene depth and haze…

Computer Vision and Pattern Recognition · Computer Science 2026-01-21 Zengyuan Zuo , Junjun Jiang , Gang Wu , Xianming Liu

Wavelet-based grid adaptation methods use multiresolution analysis for error estimation, offering a mathematically rigorous approach to adaptive grid refinement when solving Partial Differential Equations (PDEs). However, applying these…

Numerical Analysis · Mathematics 2026-03-20 Changxiao Nigel Shen , Wim M. van Rees

Popular deep models for action recognition in videos generate independent predictions for short clips, which are then pooled heuristically to assign an action label to the full video segment. As not all frames may characterize the…

Computer Vision and Pattern Recognition · Computer Science 2018-04-02 Jue Wang , Anoop Cherian , Fatih Porikli , Stephen Gould

Many state-of-the-art computer vision architectures leverage U-Net for its adaptability and efficient feature extraction. However, the multi-resolution convolutional design often leads to significant computational demands, limiting…

Image and Video Processing · Electrical Eng. & Systems 2024-11-18 Sanghyun Byun , Kayvan Shah , Ayushi Gang , Christopher Apton , Jacob Song , Woo Seong Chung

Existing image fusion methods pay few research attention to image fusion efficiency and network architecture. However, the efficiency and accuracy of image fusion has an important impact in practical applications. To solve this problem, we…

Computer Vision and Pattern Recognition · Computer Science 2020-10-07 Aiqing Fang , Xinbo Zhao , Jiaqi Yang , Beibei Qin , Yanning Zhang

In this work, we revisit the global average pooling layer proposed in [13], and shed light on how it explicitly enables the convolutional neural network to have remarkable localization ability despite being trained on image-level labels.…

Computer Vision and Pattern Recognition · Computer Science 2015-12-15 Bolei Zhou , Aditya Khosla , Agata Lapedriza , Aude Oliva , Antonio Torralba

We propose a multi-layer variational autoencoder method, we call HR-VQVAE, that learns hierarchical discrete representations of the data. By utilizing a novel objective function, each layer in HR-VQVAE learns a discrete representation of…

Computer Vision and Pattern Recognition · Computer Science 2022-08-10 Mohammad Adiban , Kalin Stefanov , Sabato Marco Siniscalchi , Giampiero Salvi

Graphical forecasting models learn the structure of time series data via projecting onto a graph, with recent techniques capturing spatial-temporal associations between variables via edge weights. Hierarchical variants offer a distinct…

Machine Learning · Computer Science 2025-04-04 Thomas Bailie , Yun Sing Koh , S. Karthik Mukkavilli , Varvara Vetrova

We propose a general framework for solving forward and inverse problems constrained by partial differential equations, where we interpolate neural networks onto finite element spaces to represent the (partial) unknowns. The framework…

Numerical Analysis · Mathematics 2023-10-11 Santiago Badia , Wei Li , Alberto F. Martín

Dynamic relational data arise in many machine learning applications, yet their evolving structure poses challenges for learning representations that remain consistent and interpretable over time. A common approach is to learn time varying…

Machine Learning · Statistics 2026-05-05 Haruka Ezoe , Hiroki Matsumoto , Ryohei Hisano

Models for audio source separation usually operate on the magnitude spectrum, which ignores phase information and makes separation performance dependant on hyper-parameters for the spectral front-end. Therefore, we investigate end-to-end…

Sound · Computer Science 2018-06-11 Daniel Stoller , Sebastian Ewert , Simon Dixon

Variational Autoencoder (VAE), a simple and effective deep generative model, has led to a number of impressive empirical successes and spawned many advanced variants and theoretical investigations. However, recent studies demonstrate that,…

Machine Learning · Computer Science 2019-01-08 Xuezhe Ma , Chunting Zhou , Eduard Hovy

Feature attribution methods aim to improve the transparency of deep neural networks by identifying the input features that influence a model's decision. Pixel-based heatmaps have become the standard for attributing features to…

Machine Learning · Statistics 2025-06-06 Gabriel Kasmi , Amandine Brunetto , Thomas Fel , Jayneel Parekh