Search Results for author: Zuoqiang Shi

Found 32 papers, 10 papers with code

Interpolation between CNNs and ResNets

no code implementations ICML 2020 Zonghan Yang, Yang Liu, Chenglong Bao, Zuoqiang Shi

Although ordinary differential equations (ODEs) provide insights for designing networks architectures, its relationship with the non-residual convolutional neural networks (CNNs) is still unclear.

Adversarial Attack Image Classification

Addressing preferred orientation in single-particle cryo-EM through AI-generated auxiliary particles

no code implementations26 Sep 2023 HUI ZHANG, Dihan Zheng, Qiurong Wu, Nieng Yan, Zuoqiang Shi, Mingxu Hu, Chenglong Bao

The single-particle cryo-EM field faces the persistent challenge of preferred orientation, lacking general computational solutions.

An axiomatized PDE model of deep neural networks

no code implementations23 Jul 2023 Tangjun Wang, Wenqi Tao, Chenglong Bao, Zuoqiang Shi

Based on the convection-diffusion equation, we design a new training method for ResNets.

Non-Line-of-Sight Imaging With Signal Superresolution Network

no code implementations CVPR 2023 Jianyu Wang, Xintong Liu, Leping Xiao, Zuoqiang Shi, Lingyun Qiu, Xing Fu

This paper proposes a general learning-based pipeline for increasing imaging quality with only a few scanning points.

Few-shot Non-line-of-sight Imaging with Signal-surface Collaborative Regularization

no code implementations CVPR 2023 Xintong Liu, Jianyu Wang, Leping Xiao, Xing Fu, Lingyun Qiu, Zuoqiang Shi

In this work, we propose a signal-surface collaborative regularization (SSCR) framework that provides noise-robust reconstructions with a minimal number of measurements.

Autonomous Driving Bayesian Inference

Non-line-of-sight imaging with arbitrary illumination and detection pattern

no code implementations1 Nov 2022 Xintong Liu, Jianyu Wang, Leping Xiao, Zuoqiang Shi, Xing Fu, Lingyun Qiu

Non-line-of-sight (NLOS) imaging aims at reconstructing targets obscured from the direct line of sight.

Autonomous Driving

Point normal orientation and surface reconstruction by incorporating isovalue constraints to Poisson equation

1 code implementation30 Sep 2022 Dong Xiao, Zuoqiang Shi, Siyu Li, Bailin Deng, Bin Wang

In this work, we bridge orientation and reconstruction in the implicit space and propose a novel approach to orient point cloud normals by incorporating isovalue constraints to the Poisson equation.

Surface Reconstruction

Semi-Supervised Clustering via Dynamic Graph Structure Learning

no code implementations6 Sep 2022 Huaming Ling, Chenglong Bao, Xin Liang, Zuoqiang Shi

However, existing methods adopt a static affinity matrix to learn the low-dimensional representations of data points and do not optimize the affinity matrix during the learning process.

Clustering Graph structure learning

A scalable deep learning approach for solving high-dimensional dynamic optimal transport

no code implementations16 May 2022 Wei Wan, Yuejin Zhang, Chenglong Bao, Bin Dong, Zuoqiang Shi

In this work, we propose a deep learning based method to solve the dynamic optimal transport in high dimensional space.

BI-GreenNet: Learning Green's functions by boundary integral network

no code implementations28 Apr 2022 Guochang Lin, Fukai Chen, Pipi Hu, Xiang Chen, Junqing Chen, Jun Wang, Zuoqiang Shi

In addition, we also use the Green's function calculated by our method to solve a class of PDE, and also obtain high-precision solutions, which shows the good generalization ability of our method on solving PDEs.

M2N: Mesh Movement Networks for PDE Solvers

1 code implementation24 Apr 2022 Wenbin Song, Mingrui Zhang, Joseph G. Wallwork, Junpeng Gao, Zheng Tian, Fanglei Sun, Matthew D. Piggott, Junqing Chen, Zuoqiang Shi, Xiang Chen, Jun Wang

However, mesh movement methods, such as the Monge-Ampere method, require the solution of auxiliary equations, which can be extremely expensive especially when the mesh is adapted frequently.

Graph Attention

Learning Modified Indicator Functions for Surface Reconstruction

1 code implementation18 Nov 2021 Dong Xiao, Siyou Lin, Zuoqiang Shi, Bin Wang

We design a novel deep neural network to perform surface integral and learn the modified indicator functions from un-oriented and noisy point clouds.

LEMMA Surface Reconstruction

Training Deep Neural Networks with Adaptive Momentum Inspired by the Quadratic Optimization

no code implementations18 Oct 2021 Tao Sun, Huaming Ling, Zuoqiang Shi, Dongsheng Li, Bao Wang

In this paper, to eliminate the effort for tuning the momentum-related hyperparameter, we propose a new adaptive momentum inspired by the optimal choice of the heavy ball momentum for quadratic optimization.

BIG-bench Machine Learning Image Classification +3

A neural network framework for learning Green's function

no code implementations29 Sep 2021 Guochang Lin, Fukai Chen, Pipi Hu, Xiang Chen, Junqing Chen, Jun Wang, Zuoqiang Shi

Green's function plays a significant role in both theoretical analysis and numerical computing of partial differential equations (PDEs).

A framework of deep neural networks via the solution operator of partial differential equations

no code implementations29 Sep 2021 Wenqi Tao, Zuoqiang Shi

To show the effectiveness for general form of PDEs, we show that several effective networks can be interpreted by our general form of PDEs and design a training method motivated by PDEs theory to train DNN models for better robustness and less chance of overfitting.

Performance-Guaranteed ODE Solvers with Complexity-Informed Neural Networks

no code implementations NeurIPS Workshop DLDE 2021 Feng Zhao, Xiang Chen, Jun Wang, Zuoqiang Shi, Shao-Lun Huang

Traditionally, we provide technical parameters for ODE solvers, such as the order, the stepsize and the local error threshold.

Diffusion Mechanism in Residual Neural Network: Theory and Applications

1 code implementation7 May 2021 Tangjun Wang, Zehao Dou, Chenglong Bao, Zuoqiang Shi

In many learning tasks with limited training samples, the diffusion connects the labeled and unlabeled data points and is a critical component for achieving high classification accuracy.

Binary Classification Classification +4

A Second-Order Nonlocal Approximation for Manifold Poisson Model with Dirichlet Boundary

no code implementations4 Jan 2021 YaJie Zhang, Zuoqiang Shi

Recently, we constructed a class of nonlocal Poisson model on manifold under Dirichlet boundary with global $\mathcal{O}(\delta^2)$ truncation error to its local counterpart, where $\delta$ denotes the nonlocal horizon parameter.

Numerical Analysis Numerical Analysis Analysis of PDEs

Deep Learning with Data Privacy via Residual Perturbation

no code implementations1 Jan 2021 Wenqi Tao, Huaming Ling, Zuoqiang Shi, Bao Wang

Empirically, we show that residual perturbation outperforms the state-of-the-art DP stochastic gradient descent (DPSGD) in both membership privacy protection and maintaining the DL models' utility.

Privacy Preserving

An Unsupervised Deep Learning Approach for Real-World Image Denoising

1 code implementation ICLR 2021 Dihan Zheng, Sia Huat Tan, Xiaowen Zhang, Zuoqiang Shi, Kaisheng Ma, Chenglong Bao

In the real-world case, the noise distribution is so complex that the simplified additive white Gaussian (AWGN) assumption rarely holds, which significantly deteriorates the Gaussian denoisers' performance.

Image Denoising

Layer-wise Adversarial Defense: An ODE Perspective

no code implementations1 Jan 2021 Zonghan Yang, Yang Liu, Chenglong Bao, Zuoqiang Shi

Deep neural networks are observed to be fragile against adversarial attacks, which have dramatically limited their practical applicability.

Adversarial Defense

Task-Oriented Feature Distillation

1 code implementation NeurIPS 2020 Linfeng Zhang, Yukang Shi, Zuoqiang Shi, Kaisheng Ma, Chenglong Bao

Moreover, an orthogonal loss is applied to the feature resizing layer in TOFD to improve the performance of knowledge distillation.

3D Classification General Classification +2

Interpolation between Residual and Non-Residual Networks

1 code implementation10 Jun 2020 Zonghan Yang, Yang Liu, Chenglong Bao, Zuoqiang Shi

Although ordinary differential equations (ODEs) provide insights for designing network architectures, its relationship with the non-residual convolutional neural networks (CNNs) is still unclear.

Adversarial Attack Image Classification

CURE: Curvature Regularization For Missing Data Recovery

no code implementations28 Jan 2019 Bin Dong, Haocheng Ju, Yiping Lu, Zuoqiang Shi

For that, we introduce a new regularization by combining the low dimension manifold regularization with a higher order Curvature Regularization, and we call this new regularization CURE for short.

Image Inpainting

ResNets Ensemble via the Feynman-Kac Formalism to Improve Natural and Robust Accuracies

4 code implementations NeurIPS 2019 Bao Wang, Binjie Yuan, Zuoqiang Shi, Stanley J. Osher

However, both natural and robust accuracies, in classifying clean and adversarial images, respectively, of the trained robust models are far from satisfactory.

Adversarial Attack Adversarial Defense

Deep Neural Nets with Interpolating Function as Output Activation

1 code implementation NeurIPS 2018 Bao Wang, Xiyang Luo, Zhen Li, Wei Zhu, Zuoqiang Shi, Stanley J. Osher

We replace the output layer of deep neural nets, typically the softmax function, by a novel interpolating function.

A Flow Model of Neural Networks

no code implementations21 Aug 2017 Zhen Li, Zuoqiang Shi

Based on a natural connection between ResNet and transport equation or its characteristic equation, we propose a continuous flow model for both ResNet and plain net.

Scalable low dimensional manifold model in the reconstruction of noisy and incomplete hyperspectral images

no code implementations18 May 2016 Wei Zhu, Zuoqiang Shi, Stanley Osher

We present a scalable low dimensional manifold model for the reconstruction of noisy and incomplete hyperspectral images.

A Harmonic Extension Approach for Collaborative Ranking

no code implementations16 Feb 2016 Da Kuang, Zuoqiang Shi, Stanley Osher, Andrea Bertozzi

We present a new perspective on graph-based methods for collaborative ranking for recommender systems.

Collaborative Ranking Matrix Completion +1

Harmonic Extension

no code implementations22 Sep 2015 Zuoqiang Shi, Jian Sun, Minghao Tian

To tackle this problem, we propose a new method called the point integral method (PIM).

BIG-bench Machine Learning

Cannot find the paper you are looking for? You can Submit a new open access paper.