Search Results for author:
Found 80 papers, 32 papers with code
When Digital Twin Meets 6G: Concepts, Obstacles, and Research Prospects
The convergence of digital twin technology and the emerging 6G network presents both challenges and numerous research opportunities.
A Refreshed Similarity-based Upsampler for Direct High-Ratio Feature Upsampling
These shortcomings make the existing methods along this pipeline primarily applicable to hierarchical network architectures with iterative features as guidance and they are not readily extended to a broader range of structures, especially for a direct high-ratio upsampling.
Advancing DRL Agents in Commercial Fighting Games: Training, Integration, and Agent-Human Alignment
Sh\=ukai quantifies the state to enhance generalizability, introducing Heterogeneous League Training (HELT) to achieve balanced competence, generalizability, and training efficiency.
Perturbation-Restrained Sequential Model Editing
In this paper, we first theoretically analyze that the factor affecting the general abilities in sequential model editing lies in the condition number of the edited matrix.
A New Method in Facial Registration in Clinics Based on Structure Light Images
To abundant traditional image methods with depth information, a method in registering with depth images and traditional clinical images was investigated.
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.
Towards Safe and Reliable Autonomous Driving: Dynamic Occupancy Set Prediction
In the rapidly evolving field of autonomous driving, reliable prediction is pivotal for vehicular safety.
Accelerating PDE Data Generation via Differential Operator Action in Solution Space
It applies differential operators on these solutions, a process we call 'operator action', to efficiently generate precise PDE data points.
Accelerating Data Generation for Neural Operators via Krylov Subspace Recycling
To the best of our knowledge, SKR is the first attempt to address the time-consuming nature of data generation for learning neural operators.
A Physics-informed Machine Learning-based Control Method for Nonlinear Dynamic Systems with Highly Noisy Measurements
This study presents a physics-informed machine learning-based control method for nonlinear dynamic systems with highly noisy measurements.
MonoGAE: Roadside Monocular 3D Object Detection with Ground-Aware Embeddings
We discover that most existing monocular 3D object detectors rely on the ego-vehicle prior assumption that the optical axis of the camera is parallel to the ground.
RSF-Conv: Rotation-and-Scale Equivariant Fourier Parameterized Convolution for Retinal Vessel Segmentation
Retinal vessel segmentation is of great clinical significance for the diagnosis of many eye-related diseases, but it is still a formidable challenge due to the intricate vascular morphology.
Recursive Counterfactual Deconfounding for Object Recognition
Image recognition is a classic and common task in the computer vision field, which has been widely applied in the past decade.
Exploring Robust Features for Improving Adversarial Robustness
In this paper, we strive to explore the robust features which are not affected by the adversarial perturbations, i. e., invariant to the clean image and its adversarial examples, to improve the model's adversarial robustness.
Complementary Frequency-Varying Awareness Network for Open-Set Fine-Grained Image Recognition
Open-set image recognition is a challenging topic in computer vision.
MEPNet: A Model-Driven Equivariant Proximal Network for Joint Sparse-View Reconstruction and Metal Artifact Reduction in CT Images
Sparse-view computed tomography (CT) has been adopted as an important technique for speeding up data acquisition and decreasing radiation dose.
Evolving Testing Scenario Generation Method and Intelligence Evaluation Framework for Automated Vehicles
Current testing scenarios typically employ predefined or scripted BVs, which inadequately reflect the complexity of human-like social behaviors in real-world driving scenarios, and also lack a systematic metric for evaluating the comprehensive intelligence of AVs.
STEPS: A Benchmark for Order Reasoning in Sequential Tasks
Therefore, to verify the order reasoning capability of current neural models in sequential tasks, we propose a challenging benchmark , named STEPS.
Cross-Modal Vertical Federated Learning for MRI Reconstruction
To this end, we formulate this practical-yet-challenging cross-modal vertical federated learning task, in which shape data from multiple hospitals have different modalities with a small amount of multi-modality data collected from the same individuals.
Predicting Token Impact Towards Efficient Vision Transformer
Token filtering to reduce irrelevant tokens prior to self-attention is a straightforward way to enable efficient vision Transformer.
Self-Aware Trajectory Prediction for Safe Autonomous Driving
Trajectory prediction is one of the key components of the autonomous driving software stack.
Bot or Human? Detecting ChatGPT Imposters with A Single Question
Large language models (LLMs) like GPT-4 have recently demonstrated impressive capabilities in natural language understanding and generation.
Interactive Segmentation as Gaussian Process Classification
Against this issue, in this paper, we propose to formulate the IS task as a Gaussian process (GP)-based pixel-wise binary classification model on each image.
XFL: A High Performace, Lightweighted Federated Learning Framework
This paper introduces XFL, an industrial-grade federated learning project.
Planning Automated Driving with Accident Experience Referencing and Common-sense Inferencing
In this work, we present the concept of an Automated Driving Strategical Brain (ADSB): a framework of a scene perception and scene safety evaluation system that works at a higher abstraction level, incorporating experience referencing, common-sense inferring and goal-and-value judging capabilities, to provide a contextual perspective for decision making within automated driving planning.
Chaos to Order: A Label Propagation Perspective on Source-Free Domain Adaptation
Inspired by this insight, we present Chaos to Order (CtO), a novel approach for SFDA that strives to constrain semantic credibility and propagate label information among target subpopulations.
How Does Traffic Environment Quantitatively Affect the Autonomous Driving Prediction?
The results indicate that the deep ensemble-based method has advantages in improving prediction robustness and estimating epistemic uncertainty.
Failure Detection for Motion Prediction of Autonomous Driving: An Uncertainty Perspective
Motion prediction is essential for safe and efficient autonomous driving.
Interactive Segmentation As Gaussion Process Classification
Against this issue, in this paper, we propose to formulate the IS task as a Gaussian process (GP)-based pixel-wise binary classification model on each image.
SemiCVT: Semi-Supervised Convolutional Vision Transformer for Semantic Segmentation
Semi-supervised learning improves data efficiency of deep models by leveraging unlabeled samples to alleviate the reliance on a large set of labeled samples.
Orientation-Shared Convolution Representation for CT Metal Artifact Learning
During X-ray computed tomography (CT) scanning, metallic implants carrying with patients often lead to adverse artifacts in the captured CT images and then impair the clinical treatment.
No driver, No Regulation? --Online Legal Driving Behavior Monitoring for Self-driving Vehicles
To address these challenges, this paper aims to digitize traffic law comprehensively and provide an application for online monitoring of legal driving behavior for autonomous vehicles.
Spatial-Temporal Attention Network for Open-Set Fine-Grained Image Recognition
To address this problem, motivated by the temporal attention mechanism in brains, we propose a spatial-temporal attention network for learning fine-grained feature representations, called STAN, where the features learnt by implementing a sequence of spatial self-attention operations corresponding to multiple moments are aggregated progressively.
SOTIF Entropy: Online SOTIF Risk Quantification and Mitigation for Autonomous Driving
Therefore, this paper proposes the "Self-Surveillance and Self-Adaption System" as a systematic approach to online minimize the SOTIF risk, which aims to provide a systematic solution for monitoring, quantification, and mitigation of inherent and external risks.
PeSOTIF: a Challenging Visual Dataset for Perception SOTIF Problems in Long-tail Traffic Scenarios
Perception algorithms in autonomous driving systems confront great challenges in long-tail traffic scenarios, where the problems of Safety of the Intended Functionality (SOTIF) could be triggered by the algorithm performance insufficiencies and dynamic operational environment.
Explanations from Large Language Models Make Small Reasoners Better
Integrating free-text explanations to in-context learning of large language models (LLM) is shown to elicit strong reasoning capabilities along with reasonable explanations.
Towards Theoretically Inspired Neural Initialization Optimization
With NIO, we improve the classification performance of a variety of neural architectures on CIFAR-10, CIFAR-100, and ImageNet.
Controllable Dialogue Simulation with In-Context Learning
Experimental results on the MultiWOZ dataset demonstrate that training a model on the simulated dialogues leads to even better performance than using the same amount of human-generated dialogues under the challenging low-resource settings, with as few as 85 dialogues as a seed.
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.
SIND: A Drone Dataset at Signalized Intersection in China
Then, the behaviors of traffic light violations in SIND are recorded.
CAMO-MOT: Combined Appearance-Motion Optimization for 3D Multi-Object Tracking with Camera-LiDAR Fusion
As such, we propose a novel camera-LiDAR fusion 3D MOT framework based on the Combined Appearance-Motion Optimization (CAMO-MOT), which uses both camera and LiDAR data and significantly reduces tracking failures caused by occlusion and false detection.
Limitations of Language Models in Arithmetic and Symbolic Induction
LMs with tutor is able to deliver 100% accuracy in situations of OOD and repeating symbols, shedding new insights on the boundary of large LMs in induction.
Context-Consistent Semantic Image Editing with Style-Preserved Modulation
Semantic image editing utilizes local semantic label maps to generate the desired content in the edited region.
A Holistic Robust Motion Controller Framework for Autonomous Platooning
The output from UCL will be delivered to the lower-level motion-planning layer (LML) as reference signals.
Adaptive Convolutional Dictionary Network for CT Metal Artifact Reduction
By unfolding every iterative substep of the proposed algorithm into a network module, we explicitly embed the prior structure into a deep network, \emph{i. e.,} a clear interpretability for the MAR task.
Designing thermal radiation metamaterials via hybrid adversarial autoencoder and Bayesian optimization
Designing thermal radiation metamaterials is challenging especially for problems with high degrees of freedom and complex objective.
Low-light Image Enhancement by Retinex Based Algorithm Unrolling and Adjustment
Besides, to avoid manually parameter tuning, we also propose a self-supervised fine-tuning strategy, which can always guarantee a promising performance.
InDuDoNet+: A Deep Unfolding Dual Domain Network for Metal Artifact Reduction in CT Images
To alleviate these issues, in the paper, we construct a novel deep unfolding dual domain network, termed InDuDoNet+, into which CT imaging process is finely embedded.
InDuDoNet: An Interpretable Dual Domain Network for CT Metal Artifact Reduction
For the task of metal artifact reduction (MAR), although deep learning (DL)-based methods have achieved promising performances, most of them suffer from two problems: 1) the CT imaging geometry constraint is not fully embedded into the network during training, leaving room for further performance improvement; 2) the model interpretability is lack of sufficient consideration.
AGKD-BML: Defense Against Adversarial Attack by Attention Guided Knowledge Distillation and Bi-directional Metric Learning
The attention knowledge is obtained from a weight-fixed model trained on a clean dataset, referred to as a teacher model, and transferred to a model that is under training on adversarial examples (AEs), referred to as a student model.
RCDNet: An Interpretable Rain Convolutional Dictionary Network for Single Image Deraining
To handle such an ill-posed single image deraining task, in this paper, we specifically build a novel deep architecture, called rain convolutional dictionary network (RCDNet), which embeds the intrinsic priors of rain streaks and has clear interpretability.
Lifelong Learning of Hate Speech Classification on Social Media
In this work, we propose lifelong learning of hate speech classification on social media.
Symmetric Reduction of Regular Controlled Lagrangian System with Momentum Map
Then we give a good expression of the dynamical vector field of the RCL system, such that we can describe the RCL-equivalence for the RCL systems.
Symplectic Geometry Differential Geometry Dynamical Systems 53D20, 70H33, 70Q05
Predicting Kidney Transplant Survival using Multiple Feature Representations for HLAs
Kidney transplantation can significantly enhance living standards for people suffering from end-stage renal disease.
From Rain Generation to Rain Removal
For the single image rain removal (SIRR) task, the performance of deep learning (DL)-based methods is mainly affected by the designed deraining models and training datasets.
Digital Quadruplets for Cyber-Physical-Social Systems based Parallel Driving: From Concept to Applications
The three virtual vehicles (descriptive, predictive, and prescriptive) dynamically interact with the real one in order to enhance the safety and performance of the real vehicle.
Dueling Deep Q Network for Highway Decision Making in Autonomous Vehicles: A Case Study
This work optimizes the highway decision making strategy of autonomous vehicles by using deep reinforcement learning (DRL).
Transferred Energy Management Strategies for Hybrid Electric Vehicles Based on Driving Conditions Recognition
Energy management strategies (EMSs) are the most significant components in hybrid electric vehicles (HEVs) because they decide the potential of energy conservation and emission reduction.
Structural Residual Learning for Single Image Rain Removal
Such a structural residual setting guarantees the rain layer extracted by the network finely comply with the prior knowledge of general rain streaks, and thus regulates sound rain shapes capable of being well extracted from rainy images in both training and predicting stages.
A Model-driven Deep Neural Network for Single Image Rain Removal
Specifically, based on the convolutional dictionary learning mechanism for representing rain, we propose a novel single image deraining model and utilize the proximal gradient descent technique to design an iterative algorithm only containing simple operators for solving the model.
Progressively Pretrained Dense Corpus Index for Open-Domain Question Answering
In this work, we propose a simple and resource-efficient method to pretrain the paragraph encoder.
HybridQA: A Dataset of Multi-Hop Question Answering over Tabular and Textual Data
3) a hybrid model that combines heterogeneous information to find the answer.
Ranked #4 on
Question Answering
on HybridQA
Knowledge Federation: A Unified and Hierarchical Privacy-Preserving AI Framework
With strict protections and regulations of data privacy and security, conventional machine learning based on centralized datasets is confronted with significant challenges, making artificial intelligence (AI) impractical in many mission-critical and data-sensitive scenarios, such as finance, government, and health.
Optimal Analysis of Subset-Selection Based L_p Low-Rank Approximation
We show that this algorithm has an approximation ratio of $O((k+1)^{1/p})$ for $1\le p\le 2$ and $O((k+1)^{1-1/p})$ for $p\ge 2$.
Optimal Analysis of Subset-Selection Based L_p Low Rank Approximation
We show that this algorithm has an approximation ratio of $O((k+1)^{1/p})$ for $1\le p\le 2$ and $O((k+1)^{1-1/p})$ for $p\ge 2$.
Fine-tune Bert for DocRED with Two-step Process
Modelling relations between multiple entities has attracted increasing attention recently, and a new dataset called DocRED has been collected in order to accelerate the research on the document-level relation extraction.
Ranked #55 on
Relation Extraction
on DocRED
A Survey on Rain Removal from Video and Single Image
The investigations on rain removal from video or a single image has thus been attracting much research attention in the field of computer vision and pattern recognition, and various methods have been proposed against this task in the recent years.
Simple yet Effective Bridge Reasoning for Open-Domain Multi-Hop Question Answering
To resolve this issue, we introduce a new sub-problem of open-domain multi-hop QA, which aims to recognize the bridge (\emph{i. e.}, the anchor that links to the answer passage) from the context of a set of start passages with a reading comprehension model.
TabFact: A Large-scale Dataset for Table-based Fact Verification
To this end, we construct a large-scale dataset called TabFact with 16k Wikipedia tables as the evidence for 118k human-annotated natural language statements, which are labeled as either ENTAILED or REFUTED.
Ranked #11 on
Table-based Fact Verification
on TabFact
Inverse Structural Design of Graphene/Boron Nitride Hybrids by Regressional GAN
A significant novelty of the proposed RGAN is that it combines the supervised and regressional convolutional neural network (CNN) with the traditional unsupervised GAN, thus overcoming the common technical barrier in the traditional GANs, which cannot generate data associated with given continuous quantitative labels.
Computational Physics Materials Science Applied Physics
Meta Reasoning over Knowledge Graphs
The ability to reason over learned knowledge is an innate ability for humans and humans can easily master new reasoning rules with only a few demonstrations.
TWEETQA: A Social Media Focused Question Answering Dataset
With social media becoming increasingly pop-ular on which lots of news and real-time eventsare reported, developing automated questionanswering systems is critical to the effective-ness of many applications that rely on real-time knowledge.
Improving Branch Prediction By Modeling Global History with Convolutional Neural Networks
CPU branch prediction has hit a wall--existing techniques achieve near-perfect accuracy on 99% of static branches, and yet the mispredictions that remain hide major performance gains.
Self-Supervised Learning for Contextualized Extractive Summarization
Existing models for extractive summarization are usually trained from scratch with a cross-entropy loss, which does not explicitly capture the global context at the document level.
Sentence Embedding Alignment for Lifelong Relation Extraction
We formulate such a challenging problem as lifelong relation extraction and investigate memory-efficient incremental learning methods without catastrophically forgetting knowledge learned from previous tasks.
Adversarial Structured Prediction for Multivariate Measures
Many predicted structured objects (e. g., sequences, matchings, trees) are evaluated using the F-score, alignment error rate (AER), or other multivariate performance measures.
Arbitrary-Oriented Scene Text Detection via Rotation Proposals
This paper introduces a novel rotation-based framework for arbitrary-oriented text detection in natural scene images.
Evolving Boxes for Fast Vehicle Detection
We perform fast vehicle detection from traffic surveillance cameras.
Adversarial Prediction Games for Multivariate Losses
Multivariate loss functions are used to assess performance in many modern prediction tasks, including information retrieval and ranking applications.
