Search Results for author:
Found 47 papers, 16 papers with code
HOIN: High-Order Implicit Neural Representations
Implicit neural representations (INR) suffer from worsening spectral bias, which results in overly smooth solutions to the inverse problem.
Deep unfolding Network for Hyperspectral Image Super-Resolution with Automatic Exposure Correction
In recent years, the fusion of high spatial resolution multispectral image (HR-MSI) and low spatial resolution hyperspectral image (LR-HSI) has been recognized as an effective method for HSI super-resolution (HSI-SR).
S^2MVTC: a Simple yet Efficient Scalable Multi-View Tensor Clustering
Specifically, we first construct the embedding feature tensor by stacking the embedding features of different views into a tensor and rotating it.
Inverse-Free Fast Natural Gradient Descent Method for Deep Learning
Firstly, we reformulate the gradient preconditioning formula in the natural gradient descent (NGD) as a weighted sum of per-sample gradients using the Sherman-Morrison-Woodbury formula.
TERM Model: Tensor Ring Mixture Model for Density Estimation
However, a substantial number of potential tensor permutations can lead to a tensor network with the same structure but varying expressive capabilities.
A Novel Deep Clustering Framework for Fine-Scale Parcellation of Amygdala Using dMRI Tractography
The amygdala plays a vital role in emotional processing and exhibits structural diversity that necessitates fine-scale parcellation for a comprehensive understanding of its anatomico-functional correlations.
Phase Guided Light Field for Spatial-Depth High Resolution 3D Imaging
On 3D imaging, light field cameras typically are of single shot, and however, they heavily suffer from low spatial resolution and depth accuracy.
Low-Rank Multitask Learning based on Tensorized SVMs and LSSVMs
In contrast to previous MTL frameworks, our decision function in the dual induces a weighted kernel function with a task-coupling term characterized by the similarities of the task-specific factors, better revealing the explicit relations across tasks in MTL.
Tensor Regression
Tensors, as high dimensional extensions of vectors, are considered as natural representations of high dimensional data.
Once-Training-All-Fine: No-Reference Point Cloud Quality Assessment via Domain-relevance Degradation Description
Second, to reduce the significant domain discrepancy, we establish an intermediate domain, the description domain, based on insights from subjective experiments, by considering the domain relevance among samples located in the perception domain and learning a structured latent space.
Multi-view MERA Subspace Clustering
Benefiting from multiple interactions among orthogonal/semi-orthogonal (low-rank) factors, the low-rank MERA has a strong representation power to capture the complex inter/intra-view information in the self-representation tensor.
Illumination-insensitive Binary Descriptor for Visual Measurement Based on Local Inter-patch Invariance
Existing binary descriptors may not perform well for long-term visual measurement tasks due to their sensitivity to illumination variations.
Level-line Guided Edge Drawing for Robust Line Segment Detection
Line segment detection plays a cornerstone role in computer vision tasks.
Adaptively Topological Tensor Network for Multi-view Subspace Clustering
Therefore, a pre-defined tensor decomposition may not fully exploit low rank information for a certain dataset, resulting in sub-optimal multi-view clustering performance.
A Comprehensive Review of Image Line Segment Detection and Description: Taxonomies, Comparisons, and Challenges
The challenges in existing methods and corresponding insights for potentially solving them are also provided to inspire researchers.
Low Rank Optimization for Efficient Deep Learning: Making A Balance between Compact Architecture and Fast Training
However, the high computational complexity and storage cost makes deep learning hard to be used on resource-constrained devices, and it is not environmental-friendly with much power cost.
Tensorized LSSVMs for Multitask Regression
Multitask learning (MTL) can utilize the relatedness between multiple tasks for performance improvement.
Reduced Reference Quality Assessment for Point Cloud Compression
Specifically, we use the attribute and geometry quantization steps of different compression methods (i. e., V-PCC, G-PCC and AVS) to infer the point cloud quality, assuming that the point clouds have no other distortions before compression.
Tucker-O-Minus Decomposition for Multi-view Tensor Subspace Clustering
To alleviate these problems, we propose a new tensor decomposition called Tucker-O-Minus Decomposition (TOMD) for multi-view clustering.
No-Reference Point Cloud Quality Assessment via Domain Adaptation
We present a novel no-reference quality assessment metric, the image transferred point cloud quality assessment (IT-PCQA), for 3D point clouds.
Ranked #4 on
Point Cloud Quality Assessment
on WPC
Semi-tensor Product-based TensorDecomposition for Neural Network Compression
Tucker decomposition, Tensor Train (TT) and Tensor Ring (TR) are common decomposition for low rank compression of deep neural networks.
Which One is Better: Assessing Objective Metrics for Point Cloud Compression
Point cloud compression (PCC) has made remarkable achievement in recent years.
Performance Evaluation of Adversarial Attacks: Discrepancies and Solutions
Recently, adversarial attack methods have been developed to challenge the robustness of machine learning models.
Low Dimensional Landscape Hypothesis is True: DNNs can be Trained in Tiny Subspaces
Deep neural networks (DNNs) usually contain massive parameters, but there is redundancy such that it is guessed that the DNNs could be trained in low-dimensional subspaces.
Scalable Deep Compressive Sensing
In this paper, we develop a general framework named scalable deep compressive sensing (SDCS) for the scalable sampling and reconstruction (SSR) of all existing end-to-end-trained models.
Point Cloud Quality Assessment: Dataset Construction and Learning-based No-Reference Metric
Full-reference (FR) point cloud quality assessment (PCQA) has achieved impressive progress in recent years.
Ranked #5 on
Point Cloud Quality Assessment
on WPC
Blind Image Quality Assessment
Point Cloud Quality Assessment
Decision-based Universal Adversarial Attack
A single perturbation can pose the most natural images to be misclassified by classifiers.
Revisiting Robust Model Fitting Using Truncated Loss
Furthermore, the new algorithms are applied to various 2D/3D registration problems.
Hyperspectral Image Denoising with Partially Orthogonal Matrix Vector Tensor Factorization
In this paper, we present a HSI restoration method named smooth and robust low rank tensor recovery.
Bayesian Low Rank Tensor Ring Model for Image Completion
Low rank tensor ring model is powerful for image completion which recovers missing entries in data acquisition and transformation.
Frequency-Weighted Robust Tensor Principal Component Analysis
The newly obtained frequency-weighted RTPCA can be solved by alternating direction method of multipliers, and it is the first time that frequency analysis is taken in tensor principal component analysis.
AMP-Net: Denoising based Deep Unfolding for Compressive Image Sensing
By unfolding the iterative optimization algorithm for model-based methods onto networks, deep unfolding methods have the good interpretation of model-based methods and the high speed of classical deep network methods.
Adversarial Imitation Attack
Then, the adversarial examples generated by the imitation model are utilized to fool the attacked model.
DaST: Data-free Substitute Training for Adversarial Attacks
In this paper, we propose a data-free substitute training method (DaST) to obtain substitute models for adversarial black-box attacks without the requirement of any real data.
A Unified Framework for Coupled Tensor Completion
To let coupled tensors help each other for missing component estimation, in this paper we utilize TR for coupled completion by sharing parts of the latent factors.
Robust Low-Rank Tensor Ring Completion
To further deal with its sensitivity to sparse component as it does in tensor principle component analysis, we propose robust tensor ring completion (RTRC), which separates latent low-rank tensor component from sparse component with limited number of measurements.
Low-rank Tensor Grid for Image Completion
The recently proposed methods based on tensor train (TT) and tensor ring (TR) show better performance in image recovery than classical ones.
Provable Tensor Ring Completion
Tensor completion recovers a multi-dimensional array from a limited number of measurements.
Image Ordinal Classification and Understanding: Grid Dropout with Masking Label
Finally we demonstrate the effectiveness of both approaches by visualizing the Class Activation Map (CAM) and discover that grid dropout is more aware of the whole facial areas and more robust than neuron dropout for small training dataset.
Towards thinner convolutional neural networks through Gradually Global Pruning
Deep network pruning is an effective method to reduce the storage and computation cost of deep neural networks when applying them to resource-limited devices.
Attribute-controlled face photo synthesis from simple line drawing
In this paper, we propose a deep generative model to synthesize face photo from simple line drawing controlled by face attributes such as hair color and complexion.
Iterative Block Tensor Singular Value Thresholding for Extraction of Low Rank Component of Image Data
In this paper, we propose a new robust TPCA method to extract the princi- pal components of the multi-way data based on tensor singular value decomposition.
Every Filter Extracts A Specific Texture In Convolutional Neural Networks
We also demonstrate that style of images could be a combination of these texture primitives.
3D Keypoint Detection Based on Deep Neural Network with Sparse Autoencoder
Researchers have proposed various methods to extract 3D keypoints from the surface of 3D mesh models over the last decades, but most of them are based on geometric methods, which lack enough flexibility to meet the requirements for various applications.
Mesh Interest Point Detection Based on Geometric Measures and Sparse Refinement
Three dimensional (3D) interest point detection plays a fundamental role in 3D computer vision and graphics.
Compressed Sensing of Multi-Channel EEG Signals: The Simultaneous Cosparsity and Low Rank Optimization
Significance: The proposed method enables successful compressed sensing of EEG signals even when the signals have no good sparse representation.
Robust Compressed Sensing Under Matrix Uncertainties
Based on the new signal model, a new optimization model for robust sparse signal reconstruction is proposed.
