中文
相关论文

相关论文: SAOT: An Enhanced Locality-Aware Spectral Transfor…

200 篇论文

Transformer encoders contextualize token representations by attending to all other tokens at each layer, leading to quadratic increase in compute effort with the input length. In practice, however, the input text of many NLP tasks can be…

计算与语言 · 计算机科学 2023-06-01 Jeremiah Milbauer , Annie Louis , Mohammad Javad Hosseini , Alex Fabrikant , Donald Metzler , Tal Schuster

Operator learning is a variant of machine learning that is designed to approximate maps between function spaces from data. The Fourier Neural Operator (FNO) is one of the main model architectures used for operator learning. The FNO combines…

数值分析 · 数学 2025-09-29 Samuel Lanthaler , Andrew M. Stuart , Margaret Trautner

Partial differential equations (PDEs) govern a wide range of physical phenomena, but their numerical solution remains computationally demanding, especially when repeated simulations are required across many parameter settings. Recent…

机器学习 · 计算机科学 2026-05-13 Hamda Hmida , Hsiu-Wen Chang Joly , Youssef Mesri

Local feature matching is an essential technique in image matching and plays a critical role in a wide range of vision-based applications. However, existing Transformer-based detector-free local feature matching methods encounter challenges…

计算机视觉与模式识别 · 计算机科学 2024-10-31 Naijian Cao , Renjie He , Yuchao Dai , Mingyi He

Pre-training has been investigated to improve the efficiency and performance of training neural operators in data-scarce settings. However, it is largely in its infancy due to the inherent complexity and diversity, such as long…

机器学习 · 计算机科学 2024-05-08 Zhongkai Hao , Chang Su , Songming Liu , Julius Berner , Chengyang Ying , Hang Su , Anima Anandkumar , Jian Song , Jun Zhu

Fluid antenna systems (FAS) offer remarkable spatial flexibility but face significant challenges in acquiring high-resolution channel state information (CSI), leading to considerable overhead. To address this issue, we propose CANet, a…

信号处理 · 电气工程与系统科学 2026-01-28 Yanliang Jin , Runze Yu , Yuan Gao , Shengli Liu , Xiaoli Chu , Kai-Kit Wong , Chan-Byoung Chae

Recent advances in the theory of Neural Operators (NOs) have enabled fast and accurate computation of the solutions to complex systems described by partial differential equations (PDEs). Despite their great success, current NO-based…

机器学习 · 计算机科学 2024-03-18 Ashutosh Singh , Ricardo Augusto Borsoi , Deniz Erdogmus , Tales Imbiriba

Accelerating deep neural networks (DNNs) has been attracting increasing attention as it can benefit a wide range of applications, e.g., enabling mobile systems with limited computing resources to own powerful visual recognition ability. A…

计算机视觉与模式识别 · 计算机科学 2017-12-21 Tianshui Chen , Liang Lin , Wangmeng Zuo , Xiaonan Luo , Lei Zhang

We introduce the Laplace neural operator (LNO), which leverages the Laplace transform to decompose the input space. Unlike the Fourier Neural Operator (FNO), LNO can handle non-periodic signals, account for transient responses, and exhibit…

机器学习 · 计算机科学 2023-05-31 Qianying Cao , Somdatta Goswami , George Em Karniadakis

Learning PDE dynamics with neural solvers can significantly improve wall-clock efficiency and accuracy compared with classical numerical solvers. In recent years, foundation models for PDEs have largely adopted multi-scale windowed…

机器学习 · 计算机科学 2026-03-16 Jiayi Li , Flora D. Salim

Recent advancements in vision backbones have significantly improved their performance by simultaneously modeling images' local and global contexts. However, the bidirectional interaction between these two contexts has not been well explored…

计算机视觉与模式识别 · 计算机科学 2025-02-28 Qihang Fan , Huaibo Huang , Xiaoqiang Zhou , Ran He

The versatility of self-attention mechanism earned transformers great success in almost all data modalities, with limitations on the quadratic complexity and difficulty of training. To apply transformers across different data modalities,…

机器学习 · 计算机科学 2024-08-20 Viet Anh Nguyen , Minh Lenhat , Khoa Nguyen , Duong Duc Hieu , Dao Huu Hung , Truong Son Hy

Designing universal artificial intelligence (AI) solver for partial differential equations (PDEs) is an open-ended problem and a significant challenge in science and engineering. Currently, data-driven solvers have achieved great success,…

机器学习 · 计算机科学 2025-02-24 Qinglong Ma , Peizhi Zhao , Sen Wang , Tao Song

Accurate segmentation of neural structures in Electron Microscopy (EM) images is paramount for neuroscience. However, this task is challenged by intricate morphologies, low signal-to-noise ratios, and scarce annotations, limiting the…

计算机视觉与模式识别 · 计算机科学 2025-11-18 Zhenghua Li , Hang Chen , Zihao Sun , Kai Li , Xiaolin Hu

Fourier Neural Operators (FNO) have emerged as promising solutions for efficiently solving partial differential equations (PDEs) by learning infinite-dimensional function mappings through frequency domain transformations. However, the…

机器学习 · 计算机科学 2025-05-22 Tianyu Chen , Haoyi Zhou , Ying Li , Hao Wang , Zhenzhe Zhang , Tianchen Zhu , Shanghang Zhang , Jianxin Li

Neural ODEs (NODEs) have emerged as powerful tools for modeling time series data, offering the flexibility to adapt to varying input scales and capture complex dynamics. However, they face significant challenges: first, their reliance on…

机器学习 · 计算机科学 2025-10-07 Muhao Guo , Yang Weng

Synthetic aperture radar (SAR) image change detection is critical in remote sensing image analysis. Recently, the attention mechanism has been widely used in change detection tasks. However, existing attention mechanisms often employ…

图像与视频处理 · 电气工程与系统科学 2024-07-19 Jiangwei Xie , Feng Gao , Xiaowei Zhou , Junyu Dong

Recently, Vision Transformer and its variants have shown great promise on various computer vision tasks. The ability of capturing short- and long-range visual dependencies through self-attention is arguably the main source for the success.…

计算机视觉与模式识别 · 计算机科学 2021-07-02 Jianwei Yang , Chunyuan Li , Pengchuan Zhang , Xiyang Dai , Bin Xiao , Lu Yuan , Jianfeng Gao

Adapting End-to-End ASR models to out-of-domain datasets with text data is challenging. Factorized neural Transducer (FNT) aims to address this issue by introducing a separate vocabulary decoder to predict the vocabulary. Nonetheless, this…

计算与语言 · 计算机科学 2024-06-07 Junzhe Liu , Jianwei Yu , Xie Chen

Unsupervised Domain Adaptation (UDA) can effectively address domain gap issues in real-world image Super-Resolution (SR) by accessing both the source and target data. Considering privacy policies or transmission restrictions of source data…

计算机视觉与模式识别 · 计算机科学 2024-03-21 Yuang Ai , Xiaoqiang Zhou , Huaibo Huang , Lei Zhang , Ran He