首页/论文/1801.01451

arXiv 1801.014512018-01cs.CVcs.LG

通过稀疏分层傅里叶交互网络降低深度网络复杂度

Reducing Deep Network Complexity via Sparse Hierarchical Fourier Interaction Networks

School of Information, University of California, Berkeley（加州大学伯克利分校信息学院）

Andrew Kiruluta, Samantha Williams

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

摘要英文摘要相关论文

AI总结：

本文针对深度网络复杂度问题，提出融合分层逐块傅里叶变换与Top K掩码机制的稀疏分层傅里叶交互网络，实现局部细节与全局上下文的同时获取，并通过保留关键频谱系数降低复杂度。

摘要：

本文提出稀疏分层傅里叶交互网络，这是一种融合频域建模三大互补原则的架构基础模块：一是分层逐块傅里叶变换，可同时获取局部细节与全局上下文；二是可学习、可微分的Top K掩码机制，仅保留最具信息的频谱系数，从而利用视觉与语言信号的自然可压缩性。

英文摘要：

This paper presents a Sparse Hierarchical Fourier Interaction Networks, an architectural building block that unifies three complementary principles of frequency domain modeling: A hierarchical patch wise Fourier transform that affords simultaneous access to local detail and global context; A learnable, differentiable top K masking mechanism which retains only the most informative spectral coefficients, thereby exploiting the natural compressibility of visual and linguistic signals.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

阅读原文

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

本文内容

摘要英文摘要相关论文

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

继续探索

相关论文

View Vertically: A Hierarchical Network for Trajectory Prediction via Fourier Spectrums

Huazhong University of Science and Technology（华中科技大学）；JD Explore Academy（京东探索研究院）

Understanding and forecasting future trajectories of agents are critical for behavior analysis, robot navigation, autonomous cars, and other related applications. Previous methods mostly treat trajectory prediction as time sequence generation. Different from them, this work studies agents' trajectories in a "vertical" view, i.e., modeling and forecasting trajectories from the spectral domain. Different frequency bands in the trajectory spectrums could hierarchically reflect agents' motion preferences at different scales. The low-frequency and high-frequency portions could represent their coars…

2022-07-13cs.CV

A Novel Hierarchical Light Field Coding Scheme Based on Hybrid Stacked Multiplicative Layers and Fourier Disparity Layers for Glasses-Free 3D Displays

Indian Institute of Technology Madras（印度理工学院马德拉斯分校）

This paper presents a novel hierarchical coding scheme for light fields based on transmittance patterns of low-rank multiplicative layers and Fourier disparity layers. The proposed scheme identifies multiplicative layers of light field view subsets optimized using a convolutional neural network for different scanning orders. Our approach exploits the hidden low-rank structure in the multiplicative layers obtained from the subsets of different scanning patterns. The spatial redundancies in the multiplicative layers can be efficiently removed by performing low-rank approximation at different ran…

2021-08-27cs.CVeess.IV

Absum: Simple Regularization Method for Reducing Structural Sensitivity of Convolutional Neural Networks

NTT Software Innovation Center（NTT软件创新中心）；Keio University（庆应义塾大学）；NTT Communication Science Laboratories（NTT通信科学实验室）；NTT Secure Platform Laboratories（NTT安全平台实验室）

We propose Absum, which is a regularization method for improving adversarial robustness of convolutional neural networks (CNNs). Although CNNs can accurately recognize images, recent studies have shown that the convolution operations in CNNs commonly have structural sensitivity to specific noise composed of Fourier basis functions. By exploiting this sensitivity, they proposed a simple black-box adversarial attack: Single Fourier attack. To reduce structural sensitivity, we can use regularization of convolution filter weights since the sensitivity of linear transform can be assessed by the nor…

2019-09-19cs.CVcs.LGstat.ML

F2T2-HiT：用于反射去除的U形FFT Transformer与分层Transformer

F2T2-HiT: A U-Shaped FFT Transformer and Hierarchical Transformer for Reflection Removal

OPPO AI Center（OPPO人工智能中心）

针对真实场景中复杂多变的单图像反射去除问题，提出在UNet中融合FFT Transformer与分层Transformer的F2T2-HiT，并在三个公开测试集上达到最先进性能。

2025-06-05cs.CV

Reducing Complexity of HEVC: A Deep Learning Approach

Beihang University（北京航空航天大学）；Imperial College London（伦敦帝国理工学院）

High Efficiency Video Coding (HEVC) significantly reduces bit-rates over the proceeding H.264 standard but at the expense of extremely high encoding complexity. In HEVC, the quad-tree partition of coding unit (CU) consumes a large proportion of the HEVC encoding complexity, due to the bruteforce search for rate-distortion optimization (RDO). Therefore, this paper proposes a deep learning approach to predict the CU partition for reducing the HEVC complexity at both intra- and inter-modes, which is based on convolutional neural network (CNN) and long- and short-term memory (LSTM) network. First,…

2018-03-22cs.CV

基于分层监督的上下文扩展分割

Scaling In-Context Segmentation with Hierarchical Supervision

Division of Medical Physics, Department of Radiology, Medical Center – University of Freiburg（医学物理系，放射科，弗赖堡大学医学中心）

本文提出PatchICL框架，通过选择性图像分块与多级监督实现高效上下文学习，提升医学图像分割性能并降低计算开销。

2026-04-22cs.CV

更多相关论文收起更多论文

Functional Regularization for Reinforcement Learning via Learned Fourier Features

Carnegie Mellon University（卡内基梅隆大学）

We propose a simple architecture for deep reinforcement learning by embedding inputs into a learned Fourier basis and show that it improves the sample efficiency of both state-based and image-based RL. We perform infinite-width analysis of our architecture using the Neural Tangent Kernel and theoretically show that tuning the initial variance of the Fourier basis is equivalent to functional regularization of the learned deep network. That is, these learned Fourier features allow for adjusting the degree to which networks underfit or overfit different frequencies in the training data, and hence…

2021-12-06cs.AIcs.CVcs.LG

Automatic Whole-body Bone Age Assessment Using Deep Hierarchical Features

Chonnam National University（全南国立大学）

Bone age assessment gives us evidence to analyze the children growth status and the rejuvenation involved chronological and biological ages. All the previous works consider left-hand X-ray image of a child in their works. In this paper, we carry out a study on estimating human age using whole-body bone CT images and a novel convolutional neural network. Our model with additional connections shows an effective way to generate a massive number of vital features while reducing overfitting influence on small training data in the medical image analysis research area. A dataset and a comparison with…

2019-01-29cs.CV

Vertex Feature Encoding and Hierarchical Temporal Modeling in a Spatial-Temporal Graph Convolutional Network for Action Recognition

Interdisciplinary Centre for Security, Reliability and Trust (SnT)（安全、可靠性与信任跨学科中心（SnT））；University of Luxembourg（卢森堡大学）

This paper extends the Spatial-Temporal Graph Convolutional Network (ST-GCN) for skeleton-based action recognition by introducing two novel modules, namely, the Graph Vertex Feature Encoder (GVFE) and the Dilated Hierarchical Temporal Convolutional Network (DH-TCN). On the one hand, the GVFE module learns appropriate vertex features for action recognition by encoding raw skeleton data into a new feature space. On the other hand, the DH-TCN module is capable of capturing both short-term and long-term temporal dependencies using a hierarchical dilated convolutional network. Experiments have been…

2019-12-20cs.CV

语义与内容至关重要：面向图像去雨的多先验分层Mamba

Semantics and Content Matter: Towards Multi-Prior Hierarchical Mamba for Image Deraining

针对现有图像去雨方法难以保留语义与空间细节的问题，本文提出多先验分层Mamba网络MPHM，融合CLIP与DINOv2先验并设计渐进融合模块与分层Mamba模块，在基准数据集和真实场景上取得更优性能。

2025-11-17cs.CV

Three-Dimensional Fourier Scattering Transform and Classification of Hyperspectral Images

UMIACS, University of Maryland at College Park（马里兰大学帕克分校高级计算机研究所）；University of Maryland at College Park（马里兰大学帕克分校）；Courant Institute of Mathematical Sciences, New York University（纽约大学库朗数学科学研究所）

Recent developments in machine learning and signal processing have resulted in many new techniques that are able to effectively capture the intrinsic yet complex properties of hyperspectral imagery. Tasks ranging from anomaly detection to classification can now be solved by taking advantage of very efficient algorithms which have their roots in representation theory and in computational approximation. Time-frequency methods are one example of such techniques. They provide means to analyze and extract the spectral content from data. On the other hand, hierarchical methods such as neural network…

2020-11-21cs.CV

LLHA-Net: 一种用于双视角对应学习的分层注意力网络

LLHA-Net: A Hierarchical Attention Network for Two-View Correspondence Learning

College of Cyber Security, Jinan University, Guangzhou 510632, China（网络安全学院，暨南大学，广州510632，中国）；School of computer Engineering / School of Data Science, Guangzhou City University of Technology, 510800, China（计算机工程学院/数据科学学院，广州城市科技学院，510800，中国）；Department of Strategic and Advanced Interdisciplinary Research, Peng Cheng Laboratory, Shenzhen 518000, China（战略与先进跨学科研究部，鹏城实验室，深圳518000，中国）；School of Electronics and Information Engineering, Tongji University, Shanghai, 201804, China（电子信息工程学院，同济大学，上海201804，中国）

LLHA-Net通过分层注意力机制提升双视角特征点匹配的鲁棒性与精度，优于现有方法。

2025-12-31cs.CV

Batch-FPM：随机批量更新的多参数物理傅里叶叠层显微神经网络

Batch-FPM: Random batch-update multi-parameter physical Fourier ptychography neural network

Beijing Institute of Technology（北京理工大学）；Changchun University of Science and Technology（长春理工大学）

针对FPM重建时间长且噪声鲁棒性差的问题，提出基于物理神经网络和批量更新SGD优化的快速鲁棒重建方法，实现多参数校正与近实时数字重聚焦，显著提升计算效率与临床实用性。

2024-08-25cs.CVeess.IVphysics.optics