Search Results for author:
Found 47 papers, 16 papers with code
A Three-stage Approach for Segmenting Degraded Color Images: Smoothing, Lifting and Thresholding (SLaT)
In this paper, we propose a SLaT (Smoothing, Lifting and Thresholding) method with three stages for multiphase segmentation of color images corrupted by different degradations: noise, information loss, and blur.
Linkage between piecewise constant Mumford-Shah model and ROF model and its virtue in image segmentation
The piecewise constant Mumford-Shah (PCMS) model and the Rudin-Osher-Fatemi (ROF) model are two important variational models in image segmentation and image restoration, respectively.
A Two-stage Classification Method for High-dimensional Data and Point Clouds
High-dimensional data classification is a fundamental task in machine learning and imaging science.
Large-Scale Semi-Supervised Learning via Graph Structure Learning over High-Dense Points
A novel approach is then proposed to construct the graph of the input data from the learned graph of a small number of vertexes with some preferred properties.
Deep Tensor CCA for Multi-view Learning
We present Deep Tensor Canonical Correlation Analysis (DTCCA), a method to learn complex nonlinear transformations of multiple views (more than two) of data such that the resulting representations are linearly correlated in high order.
Joint Demosaicking and Denoising Benefits from a Two-stage Training Strategy
Image demosaicking and denoising are the first two key steps of the color image production pipeline.
Edge Adaptive Hybrid Regularization Model For Image Deblurring
In the proposed model, it detects the edges and then spatially adjusts the parameters of Tikhonov and TV regularization terms for each pixel according to the edge information.
A deep neural network approach on solving the linear transport model under diffusive scaling
In our framework, the solution is approximated by a neural network that satisfies both the governing equation and other constraints.
Numerical Analysis Numerical Analysis
Rank-One Prior: Toward Real-Time Scene Recovery
To improve visual quality under different weather/imaging conditions, we propose a real-time light correction method to recover the degraded scenes in the cases of sandstorms, underwater, and haze.
Structure-Preserving Deraining with Residue Channel Prior Guidance
Although these methods can remove part of the rain streaks, it is difficult for them to adapt to real-world scenarios and restore high-quality rain-free images with clear and accurate structures.
Transformer for Single Image Super-Resolution
LTB is composed of a series of Efficient Transformers (ET), which occupies a small GPU memory occupation, thanks to the specially designed Efficient Multi-Head Attention (EMHA).
A Systematic Survey of Deep Learning-based Single-Image Super-Resolution
This is an exhaustive survey of SISR, which can help researchers better understand SISR and inspire more exciting research in this field.
A Survey on Epistemic (Model) Uncertainty in Supervised Learning: Recent Advances and Applications
This paper provides a comprehensive review of epistemic uncertainty learning techniques in supervised learning over the last five years.
Pixel Screening Based Intermediate Correction for Blind Deblurring
Blind deblurring has attracted much interest with its wide applications in reality.
CTCNet: A CNN-Transformer Cooperation Network for Face Image Super-Resolution
Then, we design an efficient Feature Refinement Module (FRM) to enhance the encoded features.
Convex Augmentation for Total Variation Based Phase Retrieval
Phase retrieval is an important problem with significant physical and industrial applications.
Lightweight Bimodal Network for Single-Image Super-Resolution via Symmetric CNN and Recursive Transformer
Single-image super-resolution (SISR) has achieved significant breakthroughs with the development of deep learning.
Multiple Degradation and Reconstruction Network for Single Image Denoising via Knowledge Distillation
Single image denoising (SID) has achieved significant breakthroughs with the development of deep learning.
A hybrid data driven-physics constrained Gaussian process regression framework with deep kernel for uncertainty quantification
The proposed model learns from both data and physics constraints through the training of a deep neural network, which serves as part of the covariance function in GPR.
Snow Mask Guided Adaptive Residual Network for Image Snow Removal
Recently, some methods have been proposed for snow removing, and most methods deal with snow images directly as the optimization object.
Spherical Image Inpainting with Frame Transformation and Data-driven Prior Deep Networks
Spherical image processing has been widely applied in many important fields, such as omnidirectional vision for autonomous cars, global climate modelling, and medical imaging.
Uncertainty-Aware Unsupervised Image Deblurring with Deep Residual Prior
To address this challenge, we suggest a dataset-free deep residual prior for the kernel induced error (termed as residual) expressed by a customized untrained deep neural network, which allows us to flexibly adapt to different blurs and images in real scenarios.
Retinex Image Enhancement Based on Sequential Decomposition With a Plug-and-Play Framework
In this paper, using a sequential Retinex decomposition strategy, we design a plug-and-play framework based on the Retinex theory for simultaneously image enhancement and noise removal.
Decomposition-Based Variational Network for Multi-Contrast MRI Super-Resolution and Reconstruction
We thus build a model to reconstruct the target image and decompose the reference image as a common component and a unique component.
ACTIVE: A Deep Model for Sperm and Impurity Detection in Microscopic Videos
The accurate detection of sperms and impurities is a very challenging task, facing problems such as the small size of targets, indefinite target morphologies, low contrast and resolution of the video, and similarity of sperms and impurities.
Towards NeuroAI: Introducing Neuronal Diversity into Artificial Neural Networks
In the human brain, neuronal diversity is an enabling factor for all kinds of biological intelligent behaviors.
Hierarchical Perception Adversarial Learning Framework for Compressed Sensing MRI
HP-ALF can perceive the image information in the hierarchical mechanism: image-level perception and patch-level perception.
Multi-Prototypes Convex Merging Based K-Means Clustering Algorithm
Specifically, CM can obtain the optimal merging and estimate the correct k. By integrating these two techniques with K-Means algorithm, the proposed MCKM is an efficient and explainable clustering algorithm for escaping the undesirable local minima of K-Means problem without given k first.
One Neuron Saved Is One Neuron Earned: On Parametric Efficiency of Quadratic Networks
In this paper, with theoretical and empirical studies, we show that quadratic networks enjoy parametric efficiency, thereby confirming that the superior performance of quadratic networks is due to the intrinsic expressive capability.
PFT-SSR: Parallax Fusion Transformer for Stereo Image Super-Resolution
Stereo image super-resolution aims to boost the performance of image super-resolution by exploiting the supplementary information provided by binocular systems.
Randomly Projected Convex Clustering Model: Motivation, Realization, and Cluster Recovery Guarantees
In this paper, we propose a randomly projected convex clustering model for clustering a collection of $n$ high dimensional data points in $\mathbb{R}^d$ with $K$ hidden clusters.
EWT: Efficient Wavelet-Transformer for Single Image Denoising
Transformer-based image denoising methods have achieved encouraging results in the past year.
Fast MRI Reconstruction via Edge Attention
To solve this problem, we propose a lightweight and accurate Edge Attention MRI Reconstruction Network (EAMRI) to reconstruct images with edge guidance.
Recognizable Information Bottleneck
The recent PAC-Bayes IB uses information complexity instead of information compression to establish a connection with the mutual information generalization bound.
Rethink Depth Separation with Intra-layer Links
Then, we modify the depth separation theory by showing that a shallow network with intra-layer links does not need to go as wide as before to express some hard functions constructed by a deep network.
Cloud-RAIN: Point Cloud Analysis with Reflectional Invariance
We prove a theorem to explain why Cloud-RAIN can enjoy reflection symmetry.
Deep ReLU Networks Have Surprisingly Simple Polytopes
A ReLU network is a piecewise linear function over polytopes.
BearingPGA-Net: A Lightweight and Deployable Bearing Fault Diagnosis Network via Decoupled Knowledge Distillation and FPGA Acceleration
To the best of our knowledge, this is the first instance of deploying a CNN-based bearing fault diagnosis model on an FPGA.
DSFNet: Dual-GCN and Location-fused Self-attention with Weighted Fast Normalized Fusion for Polyps Segmentation
Polyps segmentation poses a significant challenge in medical imaging due to the flat surface of polyps and their texture similarity to surrounding tissues.
EvalCrafter: Benchmarking and Evaluating Large Video Generation Models
For video generation, various open-sourced models and public-available services have been developed to generate high-quality videos.
VDIP-TGV: Blind Image Deconvolution via Variational Deep Image Prior Empowered by Total Generalized Variation
However, we empirically find that VDIP struggles with processing image details and tends to generate suboptimal results when the blur kernel is large.
Dynamic Multimodal Information Bottleneck for Multimodality Classification
Specifically, our information bottleneck module serves to filter out the task-irrelevant information and noises in the fused feature, and we further introduce a sufficiency loss to prevent dropping of task-relevant information, thus explicitly preserving the sufficiency of prediction information in the distilled feature.
A conservative hybrid physics-informed neural network method for Maxwell-Ampère-Nernst-Planck equations
However, when the spatial dimension is one, the original curl-free relaxation component is inapplicable, and the approximation formula for dummy variables, which works well in a 2-dimensional scenario, fails to provide a reasonable output in the 1-dimensional case.
VJT: A Video Transformer on Joint Tasks of Deblurring, Low-light Enhancement and Denoising
Video restoration task aims to recover high-quality videos from low-quality observations.
Navigating Beyond Dropout: An Intriguing Solution Towards Generalizable Image Super Resolution
Deep learning has led to a dramatic leap on Single Image Super-Resolution (SISR) performances in recent years.
Edge-guided Low-light Image Enhancement with Inertial Bregman Alternating Linearized Minimization
To overcome this limitation, we introduce a simple yet effective Retinex model with the proposed edge extraction prior.
Kernel Correlation-Dissimilarity for Multiple Kernel k-Means Clustering
The main objective of the Multiple Kernel k-Means (MKKM) algorithm is to extract non-linear information and achieve optimal clustering by optimizing base kernel matrices.
