Search Results for author:
Found 72 papers, 20 papers with code
Adversarial Reweighting with $α$-Power Maximization for Domain Adaptation
To theoretically analyze our method, we deduce an upper bound of target domain expected error for PDA, which is approximately minimized in our approach.
Learning-based Multi-continuum Model for Multiscale Flow Problems
Multiscale problems can usually be approximated through numerical homogenization by an equation with some effective parameters that can capture the macroscopic behavior of the original system on the coarse grid to speed up the simulation.
TRG-Net: An Interpretable and Controllable Rain Generator
Our unpaired generation experiments demonstrate that the rain generated by the proposed rain generator is not only of higher quality, but also more effective for deraining and downstream tasks compared to current state-of-the-art rain generation methods.
Rotation Equivariant Proximal Operator for Deep Unfolding Methods in Image Restoration
In current deep unfolding methods, such a proximal network is generally designed as a CNN architecture, whose necessity has been proven by a recent theory.
Optimal Transport-Guided Conditional Score-Based Diffusion Models
Conditional score-based diffusion model (SBDM) is for conditional generation of target data with paired data as condition, and has achieved great success in image translation.
Towards High-Fidelity Text-Guided 3D Face Generation and Manipulation Using only Images
In this paper, we propose a text-guided 3D faces generation method, refer as TG-3DFace, for generating realistic 3D faces using text guidance.
Multichannel Frequency Estimation in Challenging Scenarios via Structured Matrix Embedding and Recovery (StruMER)
We propose a universal signal-domain approach to solve the optimization problems by embedding the noiseless multichannel signal of interest into a series of low-rank positive-semidefinite block matrices of Hankel and Toeplitz submatrices and formulating the original parameter-domain optimization problems as equivalent structured matrix recovery problems.
Direction-of-Arrival Estimation for Constant Modulus Signals Using a Structured Matrix Recovery Technique
This paper addresses the problem of direction-of-arrival (DOA) estimation for constant modulus (CM) source signals using a uniform or sparse linear array.
DAC-MR: Data Augmentation Consistency Based Meta-Regularization for Meta-Learning
Besides, meta-data-driven meta-loss objective combined with DAC-MR is capable of achieving better meta-level generalization.
Keypoint-Guided Optimal Transport
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.
Improve Noise Tolerance of Robust Loss via Noise-Awareness
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
Atomic norm methods have recently been proposed for spectral super-resolution with flexibility in dealing with missing data and miscellaneous noises.
KXNet: A Model-Driven Deep Neural Network for Blind Super-Resolution
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.
CMW-Net: Learning a Class-Aware Sample Weighting Mapping for Robust Deep Learning
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.
Ranked #3 on
Image Classification
on WebVision-1000
Adversarial Reweighting for Partial Domain Adaptation
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.
Ranked #1 on
Partial Domain Adaptation
on DomainNet
Federated Dynamic Neural Network for Deep MIMO Detection
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
It has been shown that equivariant convolution is very helpful for many types of computer vision tasks.
A Unified Hyper-GAN Model for Unpaired Multi-contrast MR Image Translation
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.
Learning an Explicit Hyperparameter Prediction Function Conditioned on Tasks
Meta learning has attracted much attention recently in machine learning community.
Understanding Deep MIMO Detection
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
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.
Learning adaptive differential evolution algorithm from optimization experiences by policy gradient
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.
Robust spectral compressive sensing via vanilla gradient descent
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
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.
Amortized Variational Deep Q Network
Efficient exploration is one of the most important issues in deep reinforcement learning.
Select-ProtoNet: Learning to Select for Few-Shot Disease Subtype Prediction
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.
Polarimetric SAR Image Semantic Segmentation with 3D Discrete Wavelet Transform and Markov Random Field
Polarimetric synthetic aperture radar (PolSAR) image segmentation is currently of great importance in image processing for remote sensing applications.
MLR-SNet: Transferable LR Schedules for Heterogeneous Tasks
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.
Cross-Attention in Coupled Unmixing Nets for Unsupervised Hyperspectral Super-Resolution
The recent advancement of deep learning techniques has made great progress on hyperspectral image super-resolution (HSI-SR).
Meta Transition Adaptation for Robust Deep Learning with Noisy Labels
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.
Graph Neural Network Encoding for Community Detection in Attribute Networks
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.
Learning to be Global Optimizer
This paper proposes to learn a two-phase (including a minimization phase and an escaping phase) global optimization algorithm for smooth non-convex functions.
On Hyper-parameter Tuning for Stochastic Optimization Algorithms
This paper proposes the first-ever algorithmic framework for tuning hyper-parameters of stochastic optimization algorithm based on reinforcement learning.
Adaptive Structural Hyper-Parameter Configuration by Q-Learning
Tuning hyper-parameters for evolutionary algorithms is an important issue in computational intelligence.
Learning Adaptive Loss for Robust Learning with Noisy Labels
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 Neural Surrogate Model for Warm-Starting Bayesian Optimization
Bayesian optimization is an effective tool to optimize black-box functions and popular for hyper-parameter tuning in machine learning.
Neural Diffusion Distance for Image Segmentation
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.
Meta-Weight-Net: Learning an Explicit Mapping For Sample Weighting
Current deep neural networks (DNNs) can easily overfit to biased training data with corrupted labels or class imbalance.
Ranked #24 on
Image Classification
on Clothing1M
(using extra training data)
Multispectral and Hyperspectral Image Fusion by MS/HS Fusion Net
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
Deep neural networks are traditionally trained using human-designed stochastic optimization algorithms, such as SGD and Adam.
Model-Driven Deep Learning for Physical Layer Communications
Intelligent communication is gradually considered as the mainstream direction in future wireless communications.
Unpaired Brain MR-to-CT Synthesis using a Structure-Constrained CycleGAN
The cycleGAN is becoming an influential method in medical image synthesis.
Small Sample Learning in Big Data Era
This category mainly focuses on learning with insufficient samples, and can also be called small data learning in some literatures.
Semi-supervised Transfer Learning for Image Rain Removal
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.
Ranked #8 on
Single Image Deraining
on Test100
Learning through deterministic assignment of hidden parameters
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?
Videos taken in the wild sometimes contain unexpected rain streaks, which brings difficulty in subsequent video processing tasks.
Neural Multi-Atlas Label Fusion: Application to Cardiac MR Images
There are two major challenges in this category of methods, i. e., atlas selection and label fusion.
SPLBoost: An Improved Robust Boosting Algorithm Based on Self-paced Learning
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
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.
Hyperspectral Image Classification with Markov Random Fields and a Convolutional Neural Network
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, using extra
training data)
Denoising Hyperspectral Image with Non-i.i.d. Noise Structure
In real scenarios, however, the noise existed in a natural HSI is always with much more complicated non-i. i. d.
Deep ADMM-Net for Compressive Sensing MRI
Compressive Sensing (CS) is an effective approach for fast Magnetic Resonance Imaging (MRI).
Multispectral Images Denoising by Intrinsic Tensor Sparsity Regularization
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
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
Many computer vision problems can be posed as learning a low-dimensional subspace from high dimensional data.
A Novel Sparsity Measure for Tensor Recovery
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
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
Facial Expression Recognition
Shrinkage degree in $L_2$-re-scale boosting for regression
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
On one hand, based on the worst-case learning rate analysis, we show that the regularization term in polynomial kernel regression is not necessary.
Total Variation Regularized Tensor RPCA for Background Subtraction from Compressive Measurements
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
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
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
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.
Learning and approximation capability of orthogonal super greedy algorithm
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
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.
On the Optimal Solution of Weighted Nuclear Norm Minimization
Nevertheless, so far the global optimal solution of WNNM problem is not completely solved yet due to its non-convexity in general cases.
Sparse K-Means with $\ell_{\infty}/\ell_0$ Penalty for High-Dimensional Data Clustering
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.
Categorization Axioms for Clustering Results
Cluster analysis has attracted more and more attention in the field of machine learning and data mining.
Is Extreme Learning Machine Feasible? A Theoretical Assessment (Part II)
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
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.
Compressed Sensing SAR Imaging with Multilook Processing
Multilook processing is a widely used speckle reduction approach in synthetic aperture radar (SAR) imaging.
Image Inpainting by Patch Propagation Using Patch Sparsity
The patch with larger structure sparsity will be assigned higher priority for further inpainting.
