Search Results for author: Zongben Xu

Found 64 papers, 14 papers with code

DAC-MR: Data Augmentation Consistency Based Meta-Regularization for Meta-Learning

1 code implementation13 May 2023 Jun Shu, Xiang Yuan, Deyu Meng, Zongben Xu

Besides, meta-data-driven meta-loss objective combined with DAC-MR is capable of achieving better meta-level generalization.

Data Augmentation Meta-Learning

Keypoint-Guided Optimal Transport

1 code implementation23 Mar 2023 Xiang Gu, Yucheng Yang, Wei Zeng, Jian Sun, Zongben Xu

In this paper, we propose a novel KeyPoint-Guided model by ReLation preservation (KPG-RL) that searches for the optimal matching (i. e., transport plan) guided by the keypoints in OT.

Domain Adaptation Image-to-Image Translation

Improve Noise Tolerance of Robust Loss via Noise-Awareness

no code implementations18 Jan 2023 Kehui Ding, Jun Shu, Deyu Meng, Zongben Xu

To achieve setting such instance-dependent hyperparameters for robust loss, we propose a meta-learning method capable of adaptively learning a hyperparameter prediction function, called Noise-Aware-Robust-Loss-Adjuster (NARL-Adjuster).


Separation-Free Spectral Super-Resolution via Convex Optimization

no code implementations28 Nov 2022 Zai Yang, Yi-Lin Mo, Gongguo Tang, Zongben Xu

Atomic norm methods have recently been proposed for spectral super-resolution with flexibility in dealing with missing data and miscellaneous noises.

Miscellaneous Spectral Super-Resolution +1

KXNet: A Model-Driven Deep Neural Network for Blind Super-Resolution

1 code implementation21 Sep 2022 Jiahong Fu, Hong Wang, Qi Xie, Qian Zhao, Deyu Meng, Zongben Xu

Although current deep learning-based methods have gained promising performance in the blind single image super-resolution (SISR) task, most of them mainly focus on heuristically constructing diverse network architectures and put less emphasis on the explicit embedding of the physical generation mechanism between blur kernels and high-resolution (HR) images.

Blind Super-Resolution Image Super-Resolution +1

CMW-Net: Learning a Class-Aware Sample Weighting Mapping for Robust Deep Learning

1 code implementation11 Feb 2022 Jun Shu, Xiang Yuan, Deyu Meng, Zongben Xu

Specifically, by seeing each training class as a separate learning task, our method aims to extract an explicit weighting function with sample loss and task/class feature as input, and sample weight as output, expecting to impose adaptively varying weighting schemes to different sample classes based on their own intrinsic bias characteristics.

Image Classification Partial Label Learning

Adversarial Reweighting for Partial Domain Adaptation

1 code implementation NeurIPS 2021 Xiang Gu, Xi Yu, Yan Yang, Jian Sun, Zongben Xu

To tackle the challenge of negative domain transfer, we propose a novel Adversarial Reweighting (AR) approach that adversarially learns the weights of source domain data to align the source and target domain distributions, and the transferable deep recognition network is learned on the reweighted source domain data.

Partial Domain Adaptation

Federated Dynamic Neural Network for Deep MIMO Detection

no code implementations24 Nov 2021 Yuwen Yang, Feifei Gao, Jiang Xue, Ting Zhou, Zongben Xu

In this paper, we develop a dynamic detection network (DDNet) based detector for multiple-input multiple-output (MIMO) systems.

Fourier Series Expansion Based Filter Parametrization for Equivariant Convolutions

1 code implementation30 Jul 2021 Qi Xie, Qian Zhao, Zongben Xu, Deyu Meng

It has been shown that equivariant convolution is very helpful for many types of computer vision tasks.

Image Super-Resolution

A Unified Hyper-GAN Model for Unpaired Multi-contrast MR Image Translation

1 code implementation26 Jul 2021 Heran Yang, Jian Sun, Liwei Yang, Zongben Xu

Hyper-GAN consists of a pair of hyper-encoder and hyper-decoder to first map from the source contrast to a common feature space, and then further map to the target contrast image.


Understanding Deep MIMO Detection

no code implementations11 May 2021 Qiang Hu, Feifei Gao, Hao Zhang, Geoffrey Y. Li, Zongben Xu

We demonstrate that data-driven DL detector asymptotically approaches to the maximum a posterior (MAP) detector in various scenarios but requires enough training samples to converge in time-varying channels.

Training Networks in Null Space of Feature Covariance for Continual Learning

1 code implementation CVPR 2021 Shipeng Wang, Xiaorong Li, Jian Sun, Zongben Xu

To balance plasticity and stability of network in continual learning, in this paper, we propose a novel network training algorithm called Adam-NSCL, which sequentially optimizes network parameters in the null space of previous tasks.

Continual Learning

Learning adaptive differential evolution algorithm from optimization experiences by policy gradient

no code implementations6 Feb 2021 Jianyong Sun, Xin Liu, Thomas Bäck, Zongben Xu

A reinforcement learning algorithm, named policy gradient, is applied to learn an agent (i. e. parameter controller) that can provide the control parameters of a proposed differential evolution adaptively during the search procedure.

Stochastic Optimization

Robust spectral compressive sensing via vanilla gradient descent

no code implementations21 Jan 2021 Xunmeng Wu, Zai Yang, Zongben Xu

This paper investigates the recovery of a spectrally sparse signal from its partially revealed noisy entries within the framework of spectral compressive sensing.

Compressive Sensing Matrix Completion Information Theory Information Theory

Domain-Free Adversarial Splitting for Domain Generalization

no code implementations1 Jan 2021 Xiang Gu, Jiasun Feng, Jian Sun, Zongben Xu

In this framework, we model the domain generalization as a learning problem that enforces the learner to be able to generalize well for any train/val subsets splitting of the training dataset.

Domain Generalization Meta-Learning

Amortized Variational Deep Q Network

1 code implementation3 Nov 2020 Haotian Zhang, Yuhao Wang, Jianyong Sun, Zongben Xu

Efficient exploration is one of the most important issues in deep reinforcement learning.

Efficient Exploration OpenAI Gym +1

Select-ProtoNet: Learning to Select for Few-Shot Disease Subtype Prediction

no code implementations2 Sep 2020 Ziyi Yang, Jun Shu, Yong Liang, Deyu Meng, Zongben Xu

Current machine learning has made great progress on computer vision and many other fields attributed to the large amount of high-quality training samples, while it does not work very well on genomic data analysis, since they are notoriously known as small data.

feature selection Few-Shot Image Classification +1

Polarimetric SAR Image Semantic Segmentation with 3D Discrete Wavelet Transform and Markov Random Field

no code implementations5 Aug 2020 Haixia Bi, Lin Xu, Xiangyong Cao, Yong Xue, Zongben Xu

Polarimetric synthetic aperture radar (PolSAR) image segmentation is currently of great importance in image processing for remote sensing applications.

Image Segmentation Semantic Segmentation

MLR-SNet: Transferable LR Schedules for Heterogeneous Tasks

no code implementations29 Jul 2020 Jun Shu, Yanwen Zhu, Qian Zhao, Zongben Xu, Deyu Meng

Meanwhile, it always needs to search proper LR schedules from scratch for new tasks, which, however, are often largely different with task variations, like data modalities, network architectures, or training data capacities.

text-classification Text Classification

Meta Transition Adaptation for Robust Deep Learning with Noisy Labels

no code implementations10 Jun 2020 Jun Shu, Qian Zhao, Zongben Xu, Deyu Meng

To discover intrinsic inter-class transition probabilities underlying data, learning with noise transition has become an important approach for robust deep learning on corrupted labels.

Learning with noisy labels

Graph Neural Network Encoding for Community Detection in Attribute Networks

no code implementations6 Jun 2020 Jianyong Sun, Wei Zheng, Qingfu Zhang, Zongben Xu

Based on the new encoding method and the two objectives, a multiobjective evolutionary algorithm (MOEA) based upon NSGA-II, termed as continuous encoding MOEA, is developed for the transformed community detection problem with continuous decision variables.

Community Detection

Learning to be Global Optimizer

no code implementations10 Mar 2020 Haotian Zhang, Jianyong Sun, Zongben Xu

This paper proposes to learn a two-phase (including a minimization phase and an escaping phase) global optimization algorithm for smooth non-convex functions.

Image Classification

On Hyper-parameter Tuning for Stochastic Optimization Algorithms

no code implementations4 Mar 2020 Haotian Zhang, Jianyong Sun, Zongben Xu

This paper proposes the first-ever algorithmic framework for tuning hyper-parameters of stochastic optimization algorithm based on reinforcement learning.

Bayesian Optimization Stochastic Optimization

Adaptive Structural Hyper-Parameter Configuration by Q-Learning

no code implementations2 Mar 2020 Haotian Zhang, Jianyong Sun, Zongben Xu

Tuning hyper-parameters for evolutionary algorithms is an important issue in computational intelligence.

Q-Learning reinforcement-learning +2

Learning Adaptive Loss for Robust Learning with Noisy Labels

no code implementations16 Feb 2020 Jun Shu, Qian Zhao, Keyu Chen, Zongben Xu, Deyu Meng

Four kinds of SOTA robust loss functions are attempted to be integrated into our algorithm, and comprehensive experiments substantiate the general availability and effectiveness of the proposed method in both its accuracy and generalization performance, as compared with conventional hyperparameter tuning strategy, even with carefully tuned hyperparameters.

Learning with noisy labels Meta-Learning

Learning Neural Surrogate Model for Warm-Starting Bayesian Optimization

no code implementations ICLR 2020 Haotian Zhang, Jian Sun, Zongben Xu

Bayesian optimization is an effective tool to optimize black-box functions and popular for hyper-parameter tuning in machine learning.

Bayesian Optimization

Neural Diffusion Distance for Image Segmentation

no code implementations NeurIPS 2019 Jian Sun, Zongben Xu

To compute high-resolution diffusion distance or segmentation mask, we design an up-sampling strategy by feature-attentional interpolation which can be learned when training spec-diff-net.

Image Segmentation Weakly supervised Semantic Segmentation +1

Meta-Weight-Net: Learning an Explicit Mapping For Sample Weighting

3 code implementations NeurIPS 2019 Jun Shu, Qi Xie, Lixuan Yi, Qian Zhao, Sanping Zhou, Zongben Xu, Deyu Meng

Current deep neural networks (DNNs) can easily overfit to biased training data with corrupted labels or class imbalance.

Ranked #22 on Image Classification on Clothing1M (using extra training data)

Image Classification Meta-Learning

Multispectral and Hyperspectral Image Fusion by MS/HS Fusion Net

no code implementations CVPR 2019 Qi Xie, Minghao Zhou, Qian Zhao, Deyu Meng, WangMeng Zuo, Zongben Xu

In this paper, we propose a model-based deep learning approach for merging an HrMS and LrHS images to generate a high-resolution hyperspectral (HrHS) image.

HyperAdam: A Learnable Task-Adaptive Adam for Network Training

2 code implementations22 Nov 2018 Shipeng Wang, Jian Sun, Zongben Xu

Deep neural networks are traditionally trained using human-designed stochastic optimization algorithms, such as SGD and Adam.

Stochastic Optimization

Model-Driven Deep Learning for Physical Layer Communications

no code implementations17 Sep 2018 Hengtao He, Shi Jin, Chao-Kai Wen, Feifei Gao, Geoffrey Ye Li, Zongben Xu

Intelligent communication is gradually considered as the mainstream direction in future wireless communications.

Intelligent Communication

Small Sample Learning in Big Data Era

no code implementations14 Aug 2018 Jun Shu, Zongben Xu, Deyu Meng

This category mainly focuses on learning with insufficient samples, and can also be called small data learning in some literatures.

Small Data Image Classification

Semi-supervised Transfer Learning for Image Rain Removal

1 code implementation CVPR 2019 Wei Wei, Deyu Meng, Qian Zhao, Zongben Xu, Ying Wu

However, previous deep learning methods need to pre-collect a large set of image pairs with/without synthesized rain for training, which tends to make the neural network be biased toward learning the specific patterns of the synthesized rain, while be less able to generalize to real test samples whose rain types differ from those in the training data.

Single Image Deraining Transfer Learning

Learning through deterministic assignment of hidden parameters

no code implementations22 Mar 2018 Jian Fang, Shao-Bo Lin, Zongben Xu

Supervised learning frequently boils down to determining hidden and bright parameters in a parameterized hypothesis space based on finite input-output samples.

Should We Encode Rain Streaks in Video as Deterministic or Stochastic?

no code implementations ICCV 2017 Wei Wei, Lixuan Yi, Qi Xie, Qian Zhao, Deyu Meng, Zongben Xu

Videos taken in the wild sometimes contain unexpected rain streaks, which brings difficulty in subsequent video processing tasks.

SPLBoost: An Improved Robust Boosting Algorithm Based on Self-paced Learning

no code implementations20 Jun 2017 Kaidong Wang, Yao Wang, Qian Zhao, Deyu Meng, Zongben Xu

Specifically, the underlying loss being minimized by the traditional AdaBoost is the exponential loss, which is proved to be very sensitive to random noise/outliers.

ADMM-Net: A Deep Learning Approach for Compressive Sensing MRI

no code implementations19 May 2017 Yan Yang, Jian Sun, Huibin Li, Zongben Xu

Due to the combination of the advantages in model-based approach and deep learning approach, the ADMM-Nets achieve state-of-the-art reconstruction accuracies with fast computational speed.

Compressive Sensing Image Reconstruction

Hyperspectral Image Classification with Markov Random Fields and a Convolutional Neural Network

1 code implementation1 May 2017 Xiangyong Cao, Feng Zhou, Lin Xu, Deyu Meng, Zongben Xu, John Paisley

This paper presents a new supervised classification algorithm for remotely sensed hyperspectral image (HSI) which integrates spectral and spatial information in a unified Bayesian framework.

Ranked #13 on Hyperspectral Image Classification on Indian Pines (Overall Accuracy metric)

Classification General Classification +1

Denoising Hyperspectral Image with Non-i.i.d. Noise Structure

no code implementations1 Feb 2017 Yang Chen, Xiangyong Cao, Qian Zhao, Deyu Meng, Zongben Xu

In real scenarios, however, the noise existed in a natural HSI is always with much more complicated non-i. i. d.


Multispectral Images Denoising by Intrinsic Tensor Sparsity Regularization

no code implementations CVPR 2016 Qi Xie, Qian Zhao, Deyu Meng, Zongben Xu, Shuhang Gu, WangMeng Zuo, Lei Zhang

Multispectral images (MSI) can help deliver more faithful representation for real scenes than the traditional image system, and enhance the performance of many computer vision tasks.


Greedy Criterion in Orthogonal Greedy Learning

no code implementations20 Apr 2016 Lin Xu, Shao-Bo Lin, Jinshan Zeng, Xia Liu, Zongben Xu

In this paper, we find that SGD is not the unique greedy criterion and introduce a new greedy criterion, called "$\delta$-greedy threshold" for learning.

Low-rank Matrix Factorization under General Mixture Noise Distributions

no code implementations ICCV 2015 Xiangyong Cao, Qian Zhao, Deyu Meng, Yang Chen, Zongben Xu

Many computer vision problems can be posed as learning a low-dimensional subspace from high dimensional data.

Image Restoration

A Novel Sparsity Measure for Tensor Recovery

no code implementations ICCV 2015 Qian Zhao, Deyu Meng, Xu Kong, Qi Xie, Wenfei Cao, Yao Wang, Zongben Xu

In this paper, we propose a new sparsity regularizer for measuring the low-rank structure underneath a tensor.

Deep Representation of Facial Geometric and Photometric Attributes for Automatic 3D Facial Expression Recognition

no code implementations10 Nov 2015 Huibin Li, Jian Sun, Dong Wang, Zongben Xu, Liming Chen

In this paper, we present a novel approach to automatic 3D Facial Expression Recognition (FER) based on deep representation of facial 3D geometric and 2D photometric attributes.

3D Facial Expression Recognition

Shrinkage degree in $L_2$-re-scale boosting for regression

no code implementations17 May 2015 Lin Xu, Shao-Bo Lin, Yao Wang, Zongben Xu

Re-scale boosting (RBoosting) is a variant of boosting which can essentially improve the generalization performance of boosting learning.


Model selection of polynomial kernel regression

no code implementations7 Mar 2015 Shaobo Lin, Xingping Sun, Zongben Xu, Jinshan Zeng

On one hand, based on the worst-case learning rate analysis, we show that the regularization term in polynomial kernel regression is not necessary.

Model Selection regression

Total Variation Regularized Tensor RPCA for Background Subtraction from Compressive Measurements

no code implementations6 Mar 2015 Wenfei Cao, Yao Wang, Jian Sun, Deyu Meng, Can Yang, Andrzej Cichocki, Zongben Xu

In this paper, we propose a novel tensor-based robust PCA (TenRPCA) approach for BSCM by decomposing video frames into backgrounds with spatial-temporal correlations and foregrounds with spatio-temporal continuity in a tensor framework.

Learning a Convolutional Neural Network for Non-uniform Motion Blur Removal

no code implementations CVPR 2015 Jian Sun, Wenfei Cao, Zongben Xu, Jean Ponce

In this paper, we address the problem of estimating and removing non-uniform motion blur from a single blurry image.


Video Primal Sketch: A Unified Middle-Level Representation for Video

no code implementations10 Feb 2015 Zhi Han, Zongben Xu, Song-Chun Zhu

This paper presents a middle-level video representation named Video Primal Sketch (VPS), which integrates two regimes of models: i) sparse coding model using static or moving primitives to explicitly represent moving corners, lines, feature points, etc., ii) FRAME /MRF model reproducing feature statistics extracted from input video to implicitly represent textured motion, such as water and fire.

Greedy metrics in orthogonal greedy learning

no code implementations13 Nov 2014 Lin Xu, Shaobo Lin, Jinshan Zeng, Zongben Xu

Orthogonal greedy learning (OGL) is a stepwise learning scheme that adds a new atom from a dictionary via the steepest gradient descent and build the estimator via orthogonal projecting the target function to the space spanned by the selected atoms in each greedy step.

Model Selection

Learning and approximation capability of orthogonal super greedy algorithm

no code implementations18 Sep 2014 Jian Fang, Shao-Bo Lin, Zongben Xu

We consider the approximation capability of orthogonal super greedy algorithms (OSGA) and its applications in supervised learning.

Decomposable Nonlocal Tensor Dictionary Learning for Multispectral Image Denoising

no code implementations CVPR 2014 Yi Peng, Deyu Meng, Zongben Xu, Chenqiang Gao, Yi Yang, Biao Zhang

As compared to the conventional RGB or gray-scale images, multispectral images (MSI) can deliver more faithful representation for real scenes, and enhance the performance of many computer vision tasks.

Dictionary Learning Image Denoising

On the Optimal Solution of Weighted Nuclear Norm Minimization

no code implementations23 May 2014 Qi Xie, Deyu Meng, Shuhang Gu, Lei Zhang, WangMeng Zuo, Xiangchu Feng, Zongben Xu

Nevertheless, so far the global optimal solution of WNNM problem is not completely solved yet due to its non-convexity in general cases.

Image Denoising

Sparse K-Means with $\ell_{\infty}/\ell_0$ Penalty for High-Dimensional Data Clustering

no code implementations31 Mar 2014 Xiangyu Chang, Yu Wang, Rongjian Li, Zongben Xu

Nevertheless, this framework has two serious drawbacks: One is that the solution of the framework unavoidably involves a considerable portion of redundant noise features in many situations, and the other is that the framework neither offers intuitive explanations on why this framework can select relevant features nor leads to any theoretical guarantee for feature selection consistency.

feature selection

Categorization Axioms for Clustering Results

no code implementations9 Mar 2014 Jian Yu, Zongben Xu

Cluster analysis has attracted more and more attention in the field of machine learning and data mining.

General Classification

Is Extreme Learning Machine Feasible? A Theoretical Assessment (Part II)

no code implementations24 Jan 2014 Shaobo Lin, Xia Liu, Jian Fang, Zongben Xu

On one hand, we find that the randomness causes an additional uncertainty problem of ELM, both in approximation and learning.

Learning rates of $l^q$ coefficient regularization learning with Gaussian kernel

no code implementations19 Dec 2013 Shaobo Lin, Jinshan Zeng, Jian Fang, Zongben Xu

Regularization is a well recognized powerful strategy to improve the performance of a learning machine and $l^q$ regularization schemes with $0<q<\infty$ are central in use.

Learning Theory

Compressed Sensing SAR Imaging with Multilook Processing

no code implementations27 Oct 2013 Jian Fang, Zongben Xu, Bingchen Zhang, Wen Hong, Yirong Wu

Multilook processing is a widely used speckle reduction approach in synthetic aperture radar (SAR) imaging.

Compressive Sensing Image Reconstruction

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