English
Related papers

Related papers: SUPRA: Subspace Parameterized Attention for Neural…

200 papers

Unsupervised domain adaptation (UDA) aims to adapt a model trained on the source domain (e.g. synthetic data) to the target domain (e.g. real-world data) without requiring further annotations on the target domain. This work focuses on UDA…

Computer Vision and Pattern Recognition · Computer Science 2022-07-27 Lukas Hoyer , Dengxin Dai , Luc Van Gool

We prove error bounds for operator surrogates of solution operators for partial differential and boundary integral equations on families of domains which are diffeomorphic to one common reference (or latent) domain $D_{ref}$. The pullback…

Machine Learning · Computer Science 2026-04-21 Helmut Harbrecht , Christoph Schwab

Domain shift is a well-known problem in the medical imaging community. In particular, for endoscopic image analysis where the data can have different modalities the performance of deep learning (DL) methods gets adversely affected. In other…

Computer Vision and Pattern Recognition · Computer Science 2023-04-11 Rafael Martinez-Garcia-Peña , Mansoor Ali Teevno , Gilberto Ochoa-Ruiz , Sharib Ali

Though unsupervised domain adaptation (UDA) has achieved very impressive progress recently, it remains a great challenge due to missing target annotations and the rich discrepancy between source and target distributions. We propose Spectral…

Computer Vision and Pattern Recognition · Computer Science 2022-06-07 Jingyi Zhang , Jiaxing Huang , Zichen Tian , Shijian Lu

Convolutional Neural Networks (CNNs) have achieved impressive results across many super-resolution (SR) and image restoration tasks. While many such networks can upscale low-resolution (LR) images using just the raw pixel-level information,…

Image and Video Processing · Electrical Eng. & Systems 2021-10-29 Matthew Aquilina , Christian Galea , John Abela , Kenneth P. Camilleri , Reuben A. Farrugia

Neural operators (NOs) struggle with high-contrast multiscale partial differential equations (PDEs), where fine-scale heterogeneities cause large errors. To address this, we use the Generalized Multiscale Finite Element Method (GMsFEM) that…

The attention mechanism of a transformer has a quadratic complexity, leading to high inference costs and latency for long sequences. However, attention matrices are mostly sparse, which implies that many entries may be omitted from…

Machine Learning · Computer Science 2025-11-25 Jeffrey Willette , Heejun Lee , Sung Ju Hwang

Attention mechanisms, which enable a neural network to accurately focus on all the relevant elements of the input, have become an essential component to improve the performance of deep neural networks. There are mainly two attention…

Computer Vision and Pattern Recognition · Computer Science 2021-02-02 Qing-Long Zhang Yu-Bin Yang

In latest years, deep learning has gained a leading role in the pansharpening of multiresolution images. Given the lack of ground truth data, most deep learning-based methods carry out supervised training in a reduced-resolution domain.…

Image and Video Processing · Electrical Eng. & Systems 2023-07-28 Matteo Ciotola , Giovanni Poggi , Giuseppe Scarpa

Neural operators improve conventional neural networks by expanding their capabilities of functional mappings between different function spaces to solve partial differential equations (PDEs). One of the most notable methods is the Fourier…

Machine Learning · Computer Science 2024-07-29 Xuanle Zhao , Yue Sun , Tielin Zhang , Bo Xu

Deep neural networks have emerged as powerful tools for learning operators defined over infinite-dimensional function spaces. However, existing theories frequently encounter difficulties related to dimensionality and limited…

Machine Learning · Computer Science 2026-05-12 Jianfei Li , Shuo Huang , Han Feng , Ding-Xuan Zhou , Gitta Kutyniok

To solve high-dimensional parameter-dependent partial differential equations (pPDEs), a neural network architecture is presented. It is constructed to map parameters of the model data to corresponding finite element solutions. To improve…

Numerical Analysis · Mathematics 2024-03-20 Janina E. Schütte , Martin Eigel

The term `surrogate modeling' in computational science and engineering refers to the development of computationally efficient approximations for expensive simulations, such as those arising from numerical solution of partial differential…

Numerical Analysis · Mathematics 2022-08-12 Maarten V. de Hoop , Daniel Zhengyu Huang , Elizabeth Qian , Andrew M. Stuart

Convolutional layers in Artificial Neural Networks (ANN) treat the channel features equally without feature selection flexibility. While using ANNs for image denoising in real-world applications with unknown noise distributions,…

Image and Video Processing · Electrical Eng. & Systems 2020-12-24 Huayu Li , Haiyu Wu , Xiwen Chen , Hanning Zhang , Abolfazl Razi

Self-supervised adaptation (SSA) improves foundation model transfer to medical domains but is computationally prohibitive. Although parameter efficient fine-tuning methods such as LoRA have been explored for supervised adaptation, their…

Computer Vision and Pattern Recognition · Computer Science 2025-09-30 Moein Sorkhei , Emir Konuk , Jingyu Guo , Chanjuan Meng , Christos Matsoukas , Kevin Smith

Predictive learning for spatio-temporal processes (PL-STP) on complex spatial domains plays a critical role in various scientific and engineering fields, with its essence being the construction of operators between infinite-dimensional…

Machine Learning · Computer Science 2024-09-10 Qinglu Meng , Yingguang Li , Zhiliang Deng , Xu Liu , Gengxiang Chen , Qiutong Wu , Changqing Liu , Xiaozhong Hao

We present a deep learning emulator for stochastic and chaotic spatio-temporal systems, explicitly conditioned on the parameter values of the underlying partial differential equations (PDEs). Our approach involves pre-training the model on…

Machine Learning · Computer Science 2025-09-12 Ira J. S. Shokar , Rich R. Kerswell , Peter H. Haynes

From natural language processing to vision, Scaled Dot Product Attention (SDPA) is the backbone of most modern deep learning applications. Unfortunately, its memory and computational requirements can be prohibitive in low-resource settings.…

Machine Learning · Computer Science 2025-02-18 Peyman Hosseini , Mehran Hosseini , Ignacio Castro , Matthew Purver

Neural operators are a type of deep architecture that learns to solve (i.e. learns the nonlinear solution operator of) partial differential equations (PDEs). The current state of the art for these models does not provide explicit…

Machine Learning · Computer Science 2022-08-03 Emilia Magnani , Nicholas Krämer , Runa Eschenhagen , Lorenzo Rosasco , Philipp Hennig

Identifying parameters in partial differential equations (PDEs) represents a very broad class of applied inverse problems. In recent years, several unsupervised learning approaches using (deep) neural networks have been developed to solve…

Numerical Analysis · Mathematics 2025-08-22 Siyu Cen , Bangti Jin , Qimeng Quan , Zhi Zhou