Search Results for author:
Found 118 papers, 33 papers with code
SwiftAvatar: Efficient Auto-Creation of Parameterized Stylized Character on Arbitrary Avatar Engines
To this end, we propose SwiftAvatar, a novel avatar auto-creation framework that is evidently superior to previous works.
Mixed Near- and Far-Field Communications for Extremely Large-Scale Array: An Interference Perspective
For this scenario, we first obtain a closed-form expression for the inter-user interference at the near-field user caused by the far-field beam by using Fresnel functions, based on which the effects of the number of BS antennas, far-field user (FU) angle, near-field user (NU) angle and distance are analyzed.
Policy Pre-training for End-to-end Autonomous Driving via Self-supervised Geometric Modeling
To this end, we propose PPGeo (Policy Pre-training via Geometric modeling), an intuitive and straightforward fully self-supervised framework curated for the policy pretraining in visuomotor driving.
Goal-oriented Autonomous Driving
Modern autonomous driving system is characterized as modular tasks in sequential order, i. e., perception, prediction and planning.
You Only Need a Good Embeddings Extractor to Fix Spurious Correlations
With experiments on a wide range of pre-trained models and pre-training datasets, we show that the capacity of the pre-training model and the size of the pre-training dataset matters.
Respecting priorities versus respecting preferences in school choice: When is there a trade-off?
We identify a new condition on school choice markets under which DA is efficient and there is a unique allocation that respects priorities.
On the Power of Learning-Augmented BSTs
In this paper, we present a simple BST maintenance scheme that benefits from learned advice.
Deep Learning is Provably Robust to Symmetric Label Noise
We conjecture that for general label noise, mitigation strategies that make use of the noisy data will outperform those that ignore the noisy data.
Oscillatory cooperation prevalence emerges from misperception
Here we show that oscillatory behaviors naturally emerge if incomplete information is incorporated into the cooperation evolution of a non-Markov model.
Delving into the Devils of Bird's-eye-view Perception: A Review, Evaluation and Recipe
As sensor configurations get more complex, integrating multi-source information from different sensors and representing features in a unified view come of vital importance.
Time-constrained Dynamic Mechanisms for College Admissions
Recent literature shows that dynamic matching mechanisms may outperform the standard mechanisms to deliver desirable results.
Robust Landmark-based Stent Tracking in X-ray Fluoroscopy
Even though angioplasty devices are designed to have radiopaque markers for the ease of tracking, current methods struggle to deliver satisfactory results due to the small marker size and complex scenes in angioplasty.
ST-P3: End-to-end Vision-based Autonomous Driving via Spatial-Temporal Feature Learning
In particular, we propose a spatial-temporal feature learning scheme towards a set of more representative features for perception, prediction and planning tasks simultaneously, which is called ST-P3.
CRB for a Generic Near-Field Positioning System Using Three Electric Field Types
The CRBs using various electric fields in this case are derived and the effect of different numbers of receiving antennas on estimation accuracy is investigated.
Enhanced Deep Animation Video Interpolation
With AutoFI and SktFI, the interpolated animation frames show high perceptual quality.
Trajectory-guided Control Prediction for End-to-end Autonomous Driving: A Simple yet Strong Baseline
The two branches are connected so that the control branch receives corresponding guidance from the trajectory branch at each time step.
Ranked #2 on
Autonomous Driving
on CARLA Leaderboard
Level 2 Autonomous Driving on a Single Device: Diving into the Devils of Openpilot
Equipped with a wide span of sensors, predominant autonomous driving solutions are becoming more modular-oriented for safe system design.
Deep Learning with Label Noise: A Hierarchical Approach
Our hierarchical approach improves upon regular deep neural networks in learning with label noise.
HDGT: Heterogeneous Driving Graph Transformer for Multi-Agent Trajectory Prediction via Scene Encoding
One essential task for autonomous driving is to encode the information of a driving scene into vector representations so that the downstream task such as trajectory prediction could perform well.
Hierarchical-Absolute Reciprocity Calibration for Millimeter-wave Hybrid Beamforming Systems
The results reveal that the estimation errors of mismatch coefficients of digital and analog chains are uncorrelated, and that the mismatch coefficients of receive digital chains can be estimated perfectly.
ERNIE-SPARSE: Learning Hierarchical Efficient Transformer Through Regularized Self-Attention
We argue that two factors, information bottleneck sensitivity and inconsistency between different attention topologies, could affect the performance of the Sparse Transformer.
PersFormer: 3D Lane Detection via Perspective Transformer and the OpenLane Benchmark
Methods for 3D lane detection have been recently proposed to address the issue of inaccurate lane layouts in many autonomous driving scenarios (uphill/downhill, bump, etc.).
Ranked #1 on
3D Lane Detection
on OpenLane
Conversational Recommendation: A Grand AI Challenge
Animated avatars, which look and talk like humans, are iconic visions of the future of AI-powered systems.
A Survey of Surface Defect Detection of Industrial Products Based on A Small Number of Labeled Data
Therefore, this paper reviews the methods of surface defect detection of industrial products based on a small number of labeled data, and this method is divided into traditional image processing-based industrial product surface defect detection methods and deep learning-based industrial product surface defect detection methods suitable for a small number of labeled data.
Personalized Prompt Learning for Explainable Recommendation
In the latter case, ID vectors are randomly initialized but the model is trained in advance on large corpora, so they are actually in different learning stages.
Probabilistic fair behaviors spark its boost in the Ultimatum Game: the strength of good Samaritans
Behavioral experiments on the Ultimatum Game have shown that we human beings have remarkable preference in fair play, contradicting the predictions by the game theory.
A Coding Framework and Benchmark towards Compressed Video Understanding
However, in real-world scenarios, the videos are first compressed before the transportation and then decompressed for understanding.
SoftCollage: A Differentiable Probabilistic Tree Generator for Image Collage
While several recent works exploit tree-based algorithm to preserve image content better, all of them resort to hand-crafted adjustment rules to optimize the collage tree structure, leading to the failure of fully exploring the structure space of collage tree.
Finding Optimal Tangent Points for Reducing Distortions of Hard-label Attacks
In this paper, we propose a novel geometric-based approach called Tangent Attack (TA), which identifies an optimal tangent point of a virtual hemisphere located on the decision boundary to reduce the distortion of the attack.
Aesthetic Photo Collage with Deep Reinforcement Learning
To overcome the lack of training data, we pretrain our deep aesthetic network on a large scale image aesthetic dataset (CPC) for general aesthetic feature extraction and propose an attention fusion module for structural collage feature representation.
Cloning one's voice using very limited data in the wild
(2) How to clone a person's voice while controlling the style and prosody.
Reversible Attack based on Local Visual Adversarial Perturbation
Adding perturbations to images can mislead classification models to produce incorrect results.
Meta-learning an Intermediate Representation for Few-shot Block-wise Prediction of Landslide Susceptibility
Then, the critical problem is that in each block with limited samples, conducting training and testing a model is impossible for a satisfactory LSM prediction, especially in dangerous mountainous areas where landslide surveying is expensive.
ERNIE-SPARSE: Robust Efficient Transformer Through Hierarchically Unifying Isolated Information
The first factor is information bottleneck sensitivity, which is caused by the key feature of Sparse Transformer — only a small number of global tokens can attend to all other tokens.
Extracting all Aspect-polarity Pairs Jointly in a Text with Relation Extraction Approach
Extracting aspect-polarity pairs from texts is an important task of fine-grained sentiment analysis.
Alpha at SemEval-2021 Task 6: Transformer Based Propaganda Classification
This paper describes our system participated in Task 6 of SemEval-2021: the task focuses on multimodal propaganda technique classification and it aims to classify given image and text into 22 classes.
Decentralized Federated Learning: Balancing Communication and Computing Costs
The performance of decentralized SGD is jointly influenced by inter-node communications and local updates.
Deep Open Snake Tracker for Vessel Tracing
Vessel tracing by modeling vascular structures in 3D medical images with centerlines and radii can provide useful information for vascular health.
An Efficient Cervical Whole Slide Image Analysis Framework Based on Multi-scale Semantic and Location Deep Features
Digital gigapixel whole slide image (WSI) is widely used in clinical diagnosis, and automated WSI analysis is key for computer-aided diagnosis.
Task Transformer Network for Joint MRI Reconstruction and Super-Resolution
Then, a task transformer module is designed to embed and synthesize the relevance between the two tasks.
Ranked #9 on
Super-Resolution
on IXI
$\ell_2$-norm Flow Diffusion in Near-Linear Time
Diffusion is a fundamental graph procedure and has been a basic building block in a wide range of theoretical and empirical applications such as graph partitioning and semi-supervised learning on graphs.
Towards a Better Understanding of Linear Models for Recommendation
Through the derivation and analysis of the closed-form solutions for two basic regression and matrix factorization approaches, we found these two approaches are indeed inherently related but also diverge in how they "scale-down" the singular values of the original user-item interaction matrix.
Personalized Transformer for Explainable Recommendation
Transformer, which is demonstrated with strong language modeling capability, however, is not personalized and fails to make use of the user and item IDs since the ID tokens are not even in the same semantic space as the words.
Improving Robustness for Pose Estimation via Stable Heatmap Regression
Deep learning methods have achieved excellent performance in pose estimation, but the lack of robustness causes the keypoints to change drastically between similar images.
Designing Heaven's Will: The job assignment in the Chinese imperial civil service
We provide an original analysis of historical documents to describe the assignment procedures used to allocate entry-level civil service jobs in China from the tenth to the early twentieth century.
Cascade Image Matting with Deformable Graph Refinement
Image matting refers to the estimation of the opacity of foreground objects.
Hermite Polynomial-based Valuation of American Options with General Jump-Diffusion Processes
We present a new approximation scheme for the price and exercise policy of American options.
On the Robustness of Monte Carlo Dropout Trained with Noisy Labels
The memorization effect of deep learning hinders its performance to effectively generalize on test set when learning with noisy labels.
EXTRA: Explanation Ranking Datasets for Explainable Recommendation
To achieve a standard way of evaluating recommendation explanations, we provide three benchmark datasets for EXplanaTion RAnking (denoted as EXTRA), on which explainability can be measured by ranking-oriented metrics.
On the Relationship between Explanation and Recommendation: Learning to Rank Explanations for Improved Performance
Explaining to users why some items are recommended is critical, as it can help users to make better decisions, increase their satisfaction, and gain their trust in recommender systems (RS).
Blind Diagnosis for Millimeter-wave Large-scale Antenna Systems
Millimeter-wave (mmWave) communication systems rely on large-scale antenna arrays to combat large path-loss at mmWave band.
Diagnosis of Intelligent Reflecting Surface in Millimeter-wave Communication Systems
In the second case where only partial CSI is available, we jointly exploit the sparsity of the millimeter-wave channel and the failure, and adopt compressed sparse and low-rank matrix recovery algorithm to decouple channel and failure.
Robust Deep Learning with Active Noise Cancellation for Spatial Computing
This paper proposes CANC, a Co-teaching Active Noise Cancellation method, applied in spatial computing to address deep learning trained with extreme noisy labels.
CS2-Net: Deep Learning Segmentation of Curvilinear Structures in Medical Imaging
Automated detection of curvilinear structures, e. g., blood vessels or nerve fibres, from medical and biomedical images is a crucial early step in automatic image interpretation associated to the management of many diseases.
Automatic Label Correction for the Accurate Edge Detection of Overlapping Cervical Cells
The experiments on the dataset for training show that our automatic label correction algorithm can improve the accuracy of manual labels and further improve the positioning accuracy of overlapping cells with deep learning models.
RS-MetaNet: Deep meta metric learning for few-shot remote sensing scene classification
On the one hand, RS-MetaNet raises the level of learning from the sample to the task by organizing training in a meta way, and it learns to learn a metric space that can well classify remote sensing scenes from a series of tasks.
Generative Model without Prior Distribution Matching
Variational Autoencoder (VAE) and its variations are classic generative models by learning a low-dimensional latent representation to satisfy some prior distribution (e. g., Gaussian distribution).
Switching Transferable Gradient Directions for Query-Efficient Black-Box Adversarial Attacks
In each iteration, SWITCH first tries to update the current sample along the direction of $\hat{\mathbf{g}}$, but considers switching to its opposite direction $-\hat{\mathbf{g}}$ if our algorithm detects that it does not increase the value of the attack objective function.
Simulating Unknown Target Models for Query-Efficient Black-box Attacks
The meta-gradients of this loss are then computed and accumulated from multiple tasks to update the Simulator and subsequently improve generalization.
Xiaomingbot: A Multilingual Robot News Reporter
This paper proposes the building of Xiaomingbot, an intelligent, multilingual and multimodal software robot equipped with four integral capabilities: news generation, news translation, news reading and avatar animation.
Automated Intracranial Artery Labeling using a Graph Neural Network and Hierarchical Refinement
Automatically labeling intracranial arteries (ICA) with their anatomical names is beneficial for feature extraction and detailed analysis of intracranial vascular structures.
Noise Robust TTS for Low Resource Speakers using Pre-trained Model and Speech Enhancement
Firstly, the speech synthesis model is pre-trained with both multi-speaker clean data and noisy augmented data; then the pre-trained model is adapted on noisy low-resource new speaker data; finally, by setting the clean speech condition, the model can synthesize the new speaker's clean voice.
DAPnet: A Double Self-attention Convolutional Network for Point Cloud Semantic Labeling
The incorporation of the double self-attention module has an average of 7\% improvement on the pre-class accuracy.
Large-scale Real-time Personalized Similar Product Recommendations
Similar product recommendation is one of the most common scenes in e-commerce.
A Survey on Conversational Recommender Systems
Recommender systems are software applications that help users to find items of interest in situations of information overload.
Content Adaptive and Error Propagation Aware Deep Video Compression
Therefore, the encoder is adaptive to different video contents and achieves better compression performance by reducing the domain gap between the training and testing datasets.
DASNet: Dual attentive fully convolutional siamese networks for change detection of high resolution satellite images
However, the available methods focus mainly on the difference information between multitemporal remote sensing images and lack robustness to pseudo-change information.
Blurry Video Frame Interpolation
Existing works reduce motion blur and up-convert frame rate through two separate ways, including frame deblurring and frame interpolation.
Uniform Interpolation Constrained Geodesic Learning on Data Manifold
Based on this defined Riemannian metric, we introduce a constant speed loss and a minimizing geodesic loss to regularize the interpolation network to generate uniform interpolation along the learned geodesic on the manifold.
Stable Sparse Subspace Embedding for Dimensionality Reduction
Although they adopt uniform sampling with replacement, due to large sampling variance, the number of non-zeros is uneven among rows of the projection matrix which is generated in one trial, and more data information may be lost after dimension reduction.
Fast Kernel k-means Clustering Using Incomplete Cholesky Factorization
The key idea of the proposed kernel $k$-means clustering using incomplete Cholesky factorization is that we approximate the entire kernel matrix by the product of a low-rank matrix and its transposition.
Kalibre: Knowledge-based Neural Surrogate Model Calibration for Data Center Digital Twins
However, in the context of CFD, each search step requires long-lasting CFD model's iterated solving, rendering these approaches impractical with increased model complexity.
Convolution Neural Network Architecture Learning for Remote Sensing Scene Classification
The feature-learning procedure of CNN largely depends on the architecture of CNN.
FFusionCGAN: An end-to-end fusion method for few-focus images using conditional GAN in cytopathological digital slides
However, although existing image fusion techniques, including traditional algorithms and deep learning-based algorithms, can generate high-quality fused images, they need multiple images with different focus depths in the same field of view.
SCAttNet: Semantic Segmentation Network with Spatial and Channel Attention Mechanism for High-Resolution Remote Sensing Images
High-resolution remote sensing images (HRRSIs) contain substantial ground object information, such as texture, shape, and spatial location.
Reversible Adversarial Attack based on Reversible Image Transformation
In order to prevent illegal or unauthorized access of image data such as human faces and ensure legitimate users can use authorization-protected data, reversible adversarial attack technique is rise.
Robust Federated Learning with Noisy Communication
Nevertheless, it is impractical to achieve a perfect acquisition of the local models in wireless communication due to noise, which also brings serious effects on federated learning.
Adversarial Example in Remote Sensing Image Recognition
This added adversarial perturbation image is called an adversarial example, which poses a serious security problem for systems based on CNN model recognition results.
Dense Dilated Network with Probability Regularized Walk for Vessel Detection
Many methods have been proposed for vessel detection.
Accelerating Federated Learning via Momentum Gradient Descent
The proposed momentum federated learning (MFL) uses momentum gradient descent (MGD) in the local update step of FL system.
Self-Paced Video Data Augmentation with Dynamic Images Generated by Generative Adversarial Networks
The dynamic image compresses the motion information of video into a still image, removing the interference factors such as the background.
Multi-stage domain adversarial style reconstruction for cytopathological image stain normalization
This article proposes a new framework that normalizes the stain style for cytopathological images through a stain removal module and a multi-stage domain adversarial style reconstruction module.
Adaptive Wasserstein Hourglass for Weakly Supervised Hand Pose Estimation from Monocular RGB
During training, based on the relation between these common characteristics and 3D pose learned from fully-annotated synthetic datasets, it is beneficial for the network to restore the 3D pose of weakly labeled real-world datasets with the aid of 2D annotations and depth images.
MetaAdvDet: Towards Robust Detection of Evolving Adversarial Attacks
To solve such few-shot problem with the evolving attack, we propose a meta-learning based robust detection method to detect new adversarial attacks with limited examples.
User Validation of Recommendation Serendipity Metrics
Though it has been recognized that recommending serendipitous (i. e., surprising and relevant) items can be helpful for increasing users' satisfaction and behavioral intention, how to measure serendipity in the offline environment is still an open issue.
An End-to-End Block Autoencoder For Physical Layer Based On Neural Networks
Deep Learning has been widely applied in the area of image processing and natural language processing.
Information Theory Signal Processing Information Theory
Sparse Representation Classification via Screening for Graphs
The sparse representation classifier (SRC) is shown to work well for image recognition problems that satisfy a subspace assumption.
Privacy Preserving Adjacency Spectral Embedding on Stochastic Blockmodels
For graphs generated from stochastic blockmodels, adjacency spectral embedding is asymptotically consistent.
BiRA-Net: Bilinear Attention Net for Diabetic Retinopathy Grading
Diabetic retinopathy (DR) is a common retinal disease that leads to blindness.
To believe or not to believe: Validating explanation fidelity for dynamic malware analysis
For both case studies, we first train deep learning models via transfer learning on malware images, demonstrate high classification effectiveness, apply an explanation method on the images, and correlate the results back to the samples to validate whether the algorithmic insights are consistent with security domain expertise.
Ranking-Based Autoencoder for Extreme Multi-label Classification
Extreme Multi-label classification (XML) is an important yet challenging machine learning task, that assigns to each instance its most relevant candidate labels from an extremely large label collection, where the numbers of labels, features and instances could be thousands or millions.
Understanding the efficacy, reliability and resiliency of computer vision techniques for malware detection and future research directions
My research lies in the intersection of security and machine learning.
The Efficacy of SHIELD under Different Threat Models
To evaluate the robustness of the defense against an adaptive attacker, we consider the targeted-attack success rate of the Projected Gradient Descent (PGD) attack, which is a strong gradient-based adversarial attack proposed in adversarial machine learning research.
Understanding the Importance of Single Directions via Representative Substitution
Understanding the internal representations of deep neural networks (DNNs) is crucal to explain their behavior.
A Data-driven Adversarial Examples Recognition Framework via Adversarial Feature Genome
In this regard, we propose the Adversarial Feature Genome (AFG), a novel type of data that contains both the differences and features about classes.
Towards resilient machine learning for ransomware detection
In this case study, we propose to use GAN to automatically produce dynamic features that exhibit generalized malicious behaviors that can reduce the efficacy of black-box ransomware classifiers.
Deep Transfer Learning for Static Malware Classification
In the transfer learning scheme, we borrow knowledge from natural images or objects and apply to the target domain of static malware detection.
AU R-CNN: Encoding Expert Prior Knowledge into R-CNN for Action Unit Detection
(2) We integrate various dynamic models (including convolutional long short-term memory, two stream network, conditional random field, and temporal action localization network) into AU R-CNN and then investigate and analyze the reason behind the performance of dynamic models.
Ranked #1 on
Action Unit Detection
on BP4D
Post: Device Placement with Cross-Entropy Minimization and Proximal Policy Optimization
It is critical to place operations in a neural network on these devices in an optimal way, so that the training process can complete within the shortest amount of time.
Understanding the Importance of Single Directions via Representative Substitution
Understanding the internal representations of deep neural networks (DNNs) is crucal to explain their behavior.
Spotlight: Optimizing Device Placement for Training Deep Neural Networks
Training deep neural networks (DNNs) requires an increasing amount of computation resources, and it becomes typical to use a mixture of GPU and CPU devices.
ADAGIO: Interactive Experimentation with Adversarial Attack and Defense for Audio
Adversarial machine learning research has recently demonstrated the feasibility to confuse automatic speech recognition (ASR) models by introducing acoustically imperceptible perturbations to audio samples.
Shield: Fast, Practical Defense and Vaccination for Deep Learning using JPEG Compression
The rapidly growing body of research in adversarial machine learning has demonstrated that deep neural networks (DNNs) are highly vulnerable to adversarially generated images.
Vertex nomination: The canonical sampling and the extended spectral nomination schemes
There are vertex nomination schemes in the literature, including the optimally precise canonical nomination scheme~$\mathcal{L}^C$ and the consistent spectral partitioning nomination scheme~$\mathcal{L}^P$.
HeNet: A Deep Learning Approach on Intel$^\circledR$ Processor Trace for Effective Exploit Detection
The low-level model is a per-application behavior model, trained via transfer learning on a time-series of images generated from control flow trace of an execution.
Y-net: 3D intracranial artery segmentation using a convolutional autoencoder
Automated segmentation of intracranial arteries on magnetic resonance angiography (MRA) allows for quantification of cerebrovascular features, which provides tools for understanding aging and pathophysiological adaptations of the cerebrovascular system.
Stochastic Variance Reduction Gradient for a Non-convex Problem Using Graduated Optimization
Graduated Optimization Algorithm (GOA) is a popular heuristic method to obtain global optimums of nonconvex problems through progressively minimizing a series of convex approximations to the nonconvex problems more and more accurate.
Keeping the Bad Guys Out: Protecting and Vaccinating Deep Learning with JPEG Compression
Deep neural networks (DNNs) have achieved great success in solving a variety of machine learning (ML) problems, especially in the domain of image recognition.
Semi-supervised classification for dynamic Android malware detection
When this similarity is strong, MBSS and SVM with linear kernel maintain 90\% detection rate while $k$NN and LDA suffer great performance degradation.
Sparse Algorithm for Robust LSSVM in Primal Space
Then approximating the kernel matrix by a low-rank matrix and smoothing the loss function by entropy penalty function, we propose a convergent sparse R-LSSVM (SR-LSSVM) algorithm to achieve the sparse solution of primal R-LSSVM, which overcomes two drawbacks of LSSVM simultaneously.
On Study of the Binarized Deep Neural Network for Image Classification
Unlike those trials, in this paper, we focused on the basic propagation function of the artificial neural network and proposed the binarized deep neural network.
Sparse Representation Classification Beyond L1 Minimization and the Subspace Assumption
The results are demonstrated via simulations and real data experiments, where the new algorithm achieves comparable numerical performance and significantly faster.
Stochastic Blockmodeling for Online Advertising
Online advertising is an important and huge industry.
Robust Vertex Classification
For random graphs distributed according to stochastic blockmodels, a special case of latent position graphs, adjacency spectral embedding followed by appropriate vertex classification is asymptotically Bayes optimal; but this approach requires knowledge of and critically depends on the model dimension.
Spectral Clustering for Divide-and-Conquer Graph Matching
We present a parallelized bijective graph matching algorithm that leverages seeds and is designed to match very large graphs.
Unsupervised deconvolution of dynamic imaging reveals intratumor vascular heterogeneity
Intratumor heterogeneity is often manifested by vascular compartments with distinct pharmacokinetics that cannot be resolved directly by in vivo dynamic imaging.
