Search Results for author:
Found 79 papers, 33 papers with code
Online PCB Defect Detector On A New PCB Defect Dataset
To train the deep model, a dataset is established, namely DeepPCB, which contains 1, 500 image pairs with annotations including positions of 6 common types of PCB defects.
Varifocal-Net: A Chromosome Classification Approach using Deep Convolutional Networks
To expedite the diagnosis, we present a novel method named Varifocal-Net for simultaneous classification of chromosome's type and polarity using deep convolutional networks.
Resolve Domain Conflicts for Generalizable Remote Physiological Measurement
Remote photoplethysmography (rPPG) technology has become increasingly popular due to its non-invasive monitoring of various physiological indicators, making it widely applicable in multimedia interaction, healthcare, and emotion analysis.
Online Robust Principal Component Analysis with Change Point Detection
Robust PCA methods are typically batch algorithms which requires loading all observations into memory before processing.
DAmageNet: A Universal Adversarial Dataset
Adversarial samples are similar to the clean ones, but are able to cheat the attacked DNN to produce incorrect predictions in high confidence.
A Generalized Framework for Edge-preserving and Structure-preserving Image Smoothing
In this paper, a non-convex non-smooth optimization framework is proposed to achieve diverse smoothing natures where even contradictive smoothing behaviors can be achieved.
A Generalized Framework for Edge-preserving and Structure-preserving Image Smoothing
The effectiveness and superior performance of our approach are validated through comprehensive experiments in a range of applications.
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.
PCR-CG: Point Cloud Registration via Deep Explicit Color and Geometry
Different from previous methods that only use geometry representation, our module is specifically designed to effectively correlate color into geometry for the point cloud registration task.
Subspace Adversarial Training
Single-step adversarial training (AT) has received wide attention as it proved to be both efficient and robust.
Trainable Weight Averaging: A General Approach for Subspace Training
Training deep neural networks (DNNs) in low-dimensional subspaces is a promising direction for achieving efficient training and better generalization performance.
Learning Tubule-Sensitive CNNs for Pulmonary Airway and Artery-Vein Segmentation in CT
Training convolutional neural networks (CNNs) for segmentation of pulmonary airway, artery, and vein is challenging due to sparse supervisory signals caused by the severe class imbalance between tubular targets and background.
Adversarial Attack on Attackers: Post-Process to Mitigate Black-Box Score-Based Query Attacks
The score-based query attacks (SQAs) pose practical threats to deep neural networks by crafting adversarial perturbations within dozens of queries, only using the model's output scores.
Residual Enhanced Multi-Hypergraph Neural Network
Hypergraphs are a generalized data structure of graphs to model higher-order correlations among entities, which have been successfully adopted into various research domains.
One-Pixel Shortcut: on the Learning Preference of Deep Neural Networks
Based on OPS, we introduce an unlearnable dataset called CIFAR-10-S, which is indistinguishable from CIFAR-10 by humans but induces the trained model to extremely low accuracy.
Efficient Generalization Improvement Guided by Random Weight Perturbation
To fully uncover the great potential of deep neural networks (DNNs), various learning algorithms have been developed to improve the model's generalization ability.
On Multi-head Ensemble of Smoothed Classifiers for Certified Robustness
Randomized Smoothing (RS) is a promising technique for certified robustness, and recently in RS the ensemble of multiple deep neural networks (DNNs) has shown state-of-the-art performances.
Relevance Attack on Detectors
This paper focuses on high-transferable adversarial attacks on detectors, which are hard to attack in a black-box manner, because of their multiple-output characteristics and the diversity across architectures.
Self-Ensemble Protection: Training Checkpoints Are Good Data Protectors
In this paper, we uncover them by model checkpoints' gradients, forming the proposed self-ensemble protection (SEP), which is very effective because (1) learning on examples ignored during normal training tends to yield DNNs ignoring normal examples; (2) checkpoints' cross-model gradients are close to orthogonal, meaning that they are as diverse as DNNs with different architectures.
Towards Robust Neural Networks via Orthogonal Diversity
In this way, the proposed DIO augments the model and enhances the robustness of DNN itself as the learned features can be corrected by these mutually-orthogonal paths.
Query Attack by Multi-Identity Surrogates
Deep Neural Networks (DNNs) are acknowledged as vulnerable to adversarial attacks, while the existing black-box attacks require extensive queries on the victim DNN to achieve high success rates.
End-to-end Kernel Learning via Generative Random Fourier Features
In the second-stage process, a linear learner is conducted with respect to the mapped random features.
Weighted Neural Tangent Kernel: A Generalized and Improved Network-Induced Kernel
In this paper, we introduce the Weighted Neural Tangent Kernel (WNTK), a generalized and improved tool, which can capture an over-parameterized NN's training dynamics under different optimizers.
Towards Unbiased Random Features with Lower Variance For Stationary Indefinite Kernels
Random Fourier Features (RFF) demonstrate wellappreciated performance in kernel approximation for largescale situations but restrict kernels to be stationary and positive definite.
Unifying Gradients to Improve Real-world Robustness for Deep Networks
The wide application of deep neural networks (DNNs) demands an increasing amount of attention to their real-world robustness, i. e., whether a DNN resists black-box adversarial attacks, among which score-based query attacks (SQAs) are most threatening since they can effectively hurt a victim network with the only access to model outputs.
Revisiting Deep Ensemble for Out-of-Distribution Detection: A Loss Landscape Perspective
Motivated by such diversities on OoD loss landscape across modes, we revisit the deep ensemble method for OoD detection through mode ensemble, leading to improved performance and benefiting the OoD detector with reduced variances.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
Friendly Sharpness-Aware Minimization
By decomposing the adversarial perturbation in SAM into full gradient and stochastic gradient noise components, we discover that relying solely on the full gradient component degrades generalization while excluding it leads to improved performance.
One-shot Distibuted Algorithm for PCA with RBF Kernels
This letter proposes a one-shot algorithm for feature-distributed kernel PCA.
Online Continual Learning via Logit Adjusted Softmax
Online continual learning is a challenging problem where models must learn from a non-stationary data stream while avoiding catastrophic forgetting.
Learn What You Need in Personalized Federated Learning
Personalized federated learning aims to address data heterogeneity across local clients in federated learning.
Pinball Loss Minimization for One-bit Compressive Sensing: Convex Models and Algorithms
The one-sided $\ell_1$ loss and the linear loss are two popular loss functions for 1bit-CS.
Scale-Space Anisotropic Total Variation for Limited Angle Tomography
Hence, the main purpose of this paper is to reduce streak artifacts at various scales.
Nonconvex penalties with analytical solutions for one-bit compressive sensing
For several nonconvex penalties, including minimax concave penalty (MCP), $\ell_0$ norm, and sorted $\ell_1$ penalty, we provide fast algorithms for finding the analytical solutions by solving the dual problem.
Indefinite Kernel Logistic Regression with Concave-inexact-convex Procedure
Since the concave-convex procedure has to solve a sub-problem in each iteration, we propose a concave-inexact-convex procedure (CCICP) algorithm with an inexact solving scheme to accelerate the solving process.
Mixed one-bit compressive sensing with applications to overexposure correction for CT reconstruction
Aiming at overexposure correction for computed tomography (CT) reconstruction, we in this paper propose a mixed one-bit compressive sensing (M1bit-CS) to acquire information from both regular and saturated measurements.
Learning Data-adaptive Nonparametric Kernels
Learning this data-adaptive matrix in a formulation-free strategy enlarges the margin between classes and thus improves the model flexibility.
Adversarial Attack Type I: Cheat Classifiers by Significant Changes
Despite the great success of deep neural networks, the adversarial attack can cheat some well-trained classifiers by small permutations.
Generalization Properties of hyper-RKHS and its Applications
This paper generalizes regularized regression problems in a hyper-reproducing kernel Hilbert space (hyper-RKHS), illustrates its utility for kernel learning and out-of-sample extensions, and proves asymptotic convergence results for the introduced regression models in an approximation theory view.
Robust Visual Tracking Revisited: From Correlation Filter to Template Matching
In this paper, we propose a novel matching based tracker by investigating the relationship between template matching and the recent popular correlation filter based trackers (CFTs).
AirwayNet: A Voxel-Connectivity Aware Approach for Accurate Airway Segmentation Using Convolutional Neural Networks
Airway segmentation on CT scans is critical for pulmonary disease diagnosis and endobronchial navigation.
Data Consistent Artifact Reduction for Limited Angle Tomography with Deep Learning Prior
Robustness of deep learning methods for limited angle tomography is challenged by two major factors: a) due to insufficient training data the network may not generalize well to unseen data; b) deep learning methods are sensitive to noise.
Deep Kernel Learning via Random Fourier Features
On small datasets (less than 1000 samples), for which deep learning is generally not suitable due to overfitting, our method achieves superior performance compared to advanced kernel methods.
Random Fourier Features via Fast Surrogate Leverage Weighted Sampling
In this paper, we propose a fast surrogate leverage weighted sampling strategy to generate refined random Fourier features for kernel approximation.
Mixed-Precision Quantized Neural Network with Progressively Decreasing Bitwidth For Image Classification and Object Detection
In addition, the results also demonstrate that the higher-precision bottom layers could boost the 1-bit network performance appreciably due to a better preservation of the original image information while the lower-precision posterior layers contribute to the regularization of $k-$bit networks.
Universal Adversarial Attack on Attention and the Resulting Dataset DAmageNet
AoA enjoys a significant increase in transferability when the traditional cross entropy loss is replaced with the attention loss.
HRFA: High-Resolution Feature-based Attack
Adversarial attacks have long been developed for revealing the vulnerability of Deep Neural Networks (DNNs) by adding imperceptible perturbations to the input.
Double Backpropagation for Training Autoencoders against Adversarial Attack
We restrict the gradient from the reconstruction image to the original one so that the autoencoder is not sensitive to trivial perturbation produced by the adversarial attack.
Type I Attack for Generative Models
To implement the Type I attack, we destroy the original one by increasing the distance in input space while keeping the output similar because different inputs may correspond to similar features for the property of deep neural network.
Stereo Endoscopic Image Super-Resolution Using Disparity-Constrained Parallel Attention
In particular, we incorporate a disparity-based constraint mechanism into the generation of SR images in a deep neural network framework with an additional atrous parallax-attention modules.
Adversarial Imitation Attack
Then, the adversarial examples generated by the imitation model are utilized to fool the attacked model.
Random Features for Kernel Approximation: A Survey on Algorithms, Theory, and Beyond
This survey may serve as a gentle introduction to this topic, and as a users' guide for practitioners interested in applying the representative algorithms and understanding theoretical results under various technical assumptions.
Sparse Generalized Canonical Correlation Analysis: Distributed Alternating Iteration based Approach
To overcome this limitation, in this paper, we propose a sparse generalized canonical correlation analysis (GCCA), which could detect the latent relations of multiview data with sparse structures.
Fast Learning in Reproducing Kernel Krein Spaces via Signed Measures
In this paper, we attempt to solve a long-lasting open question for non-positive definite (non-PD) kernels in machine learning community: can a given non-PD kernel be decomposed into the difference of two PD kernels (termed as positive decomposition)?
Analysis of Regularized Least Squares in Reproducing Kernel Krein Spaces
In this paper, we study the asymptotic properties of regularized least squares with indefinite kernels in reproducing kernel Krein spaces (RKKS).
One-shot Distributed Algorithm for Generalized Eigenvalue Problem
Nowadays, more and more datasets are stored in a distributed way for the sake of memory storage or data privacy.
Towards a Unified Quadrature Framework for Large-Scale Kernel Machines
In this paper, we develop a quadrature framework for large-scale kernel machines via a numerical integration representation.
Measuring the Transferability of $\ell_\infty$ Attacks by the $\ell_2$ Norm
Deep neural networks could be fooled by adversarial examples with trivial differences to original samples.
Adaptive Feature Alignment for Adversarial Training
Based on this observation, we propose the adaptive feature alignment (AFA) to generate features of arbitrary attacking strengths.
Dominant Patterns: Critical Features Hidden in Deep Neural Networks
As the name suggests, for a natural image, if we add the dominant pattern of a DNN to it, the output of this DNN is determined by the dominant pattern instead of the original image, i. e., DNN's prediction is the same with the dominant pattern's.
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.
Learn Robust Features via Orthogonal Multi-Path
To defend adversarial attacks, we design a block containing multiple paths to learn robust features and the parameters of these paths are required to be orthogonal with each other.
Learning with Asymmetric Kernels: Least Squares and Feature Interpretation
Asymmetric kernels naturally exist in real life, e. g., for conditional probability and directed graphs.
Learning Perspective Deformation in X-Ray Transmission Imaging
The complementary view setting provides a practical way to identify perspectively deformed structures by assessing the deviation between the two views.
Piecewise Linear Neural Networks and Deep Learning
To apply PWLNN methods, both the representation and the learning have long been studied.
BYHE: A Simple Framework for Boosting End-to-end Video-based Heart Rate Measurement Network
Heart rate measuring based on remote photoplethysmography (rPPG) plays an important role in health caring, which estimates heart rate from facial video in a non-contact, less-constrained way.
Random Fourier Features for Asymmetric Kernels
The theoretical foundation of RFFs is based on the Bochner theorem that relates symmetric, positive definite (PD) functions to probability measures.
FG-UAP: Feature-Gathering Universal Adversarial Perturbation
Deep Neural Networks (DNNs) are susceptible to elaborately designed perturbations, whether such perturbations are dependent or independent of images.
Investigating Catastrophic Overfitting in Fast Adversarial Training: A Self-fitting Perspective
Based on self-fitting, we provide new insights into the existing methods to mitigate CO and extend CO to multi-step adversarial training.
Multi-Frame Self-Supervised Depth Estimation with Multi-Scale Feature Fusion in Dynamic Scenes
However, the spatial-temporal feature leads to accuracy degradation in dynamic scenes.
Data-Driven Safe Controller Synthesis for Deterministic Systems: A Posteriori Method With Validation Tests
We first formulate the safety synthesis problem as a robust convex program (RCP) based on notion of control barrier function.
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.
Enhancing Kernel Flexibility via Learning Asymmetric Locally-Adaptive Kernels
To enhance kernel flexibility, this paper introduces the concept of Locally-Adaptive-Bandwidths (LAB) as trainable parameters to enhance the Radial Basis Function (RBF) kernel, giving rise to the LAB RBF kernel.
Low-Dimensional Gradient Helps Out-of-Distribution Detection
To bridge this gap, in this paper, we conduct a comprehensive investigation into leveraging the entirety of gradient information for OOD detection.
Self-similarity Prior Distillation for Unsupervised Remote Physiological Measurement
In this paper, we propose a Self-Similarity Prior Distillation (SSPD) framework for unsupervised rPPG estimation, which capitalizes on the intrinsic self-similarity of cardiac activities.
Kernel PCA for Out-of-Distribution Detection
Out-of-Distribution (OoD) detection is vital for the reliability of Deep Neural Networks (DNNs).
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
Machine Unlearning by Suppressing Sample Contribution
Machine Unlearning (MU) is to forget data from a well-trained model, which is practically important due to the "right to be forgotten".
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.
OrthCaps: An Orthogonal CapsNet with Sparse Attention Routing and Pruning
Redundancy is a persistent challenge in Capsule Networks (CapsNet), leading to high computational costs and parameter counts.
Revisiting Random Weight Perturbation for Efficiently Improving Generalization
Improving the generalization ability of modern deep neural networks (DNNs) is a fundamental challenge in machine learning.
