Search Results for author:
Found 104 papers, 41 papers with code
PCBERT: Parent and Child BERT for Chinese Few-shot NER
Achieving good performance on few-shot or zero-shot datasets has been a long-term challenge for NER.
Recovery from Adversarial Attacks in Cyber-physical Systems: Shallow, Deep and Exploratory Works
Cyber-physical systems (CPS) have experienced rapid growth in recent decades.
AgentGroupChat: An Interactive Group Chat Simulacra For Better Eliciting Emergent Behavior
Language significantly influences the formation and evolution of Human emergent behavior, which is crucial in understanding collective intelligence within human societies.
Audio-Synchronized Visual Animation
We hope our established benchmark can open new avenues for controllable visual generation.
Decentralised, Collaborative, and Privacy-preserving Machine Learning for Multi-Hospital Data
In addition, the ML models trained with DeCaPH framework in general outperform those trained solely with the private datasets from individual parties, showing that DeCaPH enhances the model generalizability.
D3GU: Multi-Target Active Domain Adaptation via Enhancing Domain Alignment
Unsupervised domain adaptation (UDA) for image classification has made remarkable progress in transferring classification knowledge from a labeled source domain to an unlabeled target domain, thanks to effective domain alignment techniques.
Dig-CSI: A Distributed and Generative Model Assisted CSI Feedback Training Framework
The advent of deep learning (DL)-based models has significantly advanced Channel State Information (CSI) feedback mechanisms in wireless communication systems.
Concept-free Causal Disentanglement with Variational Graph Auto-Encoder
Existing approaches often rely on Variational Auto-Encoder (VAE) or its causal structure learning-based refinement, which suffer from sub-optimality in VAEs due to the independence factor assumption and unavailability of concept labels, respectively.
EALM: Introducing Multidimensional Ethical Alignment in Conversational Information Retrieval
Artificial intelligence (AI) technologies should adhere to human norms to better serve our society and avoid disseminating harmful or misleading information, particularly in Conversational Information Retrieval (CIR).
Specializing Small Language Models towards Complex Style Transfer via Latent Attribute Pre-Training
In this work, we introduce the concept of complex text style transfer tasks, and constructed complex text datasets based on two widely applicable scenarios.
Packet Header Recognition Utilizing an All-Optical Reservoir Based on Reinforcement-Learning-Optimized Double-Ring Resonator
Optical packet header recognition is an important signal processing task of optical communication networks.
LoRA-FA: Memory-efficient Low-rank Adaptation for Large Language Models Fine-tuning
The low-rank adaptation (LoRA) method can largely reduce the amount of trainable parameters for fine-tuning large language models (LLMs), however, it still requires expensive activation memory to update low-rank weights.
Eva: A General Vectorized Approximation Framework for Second-order Optimization
Second-order optimization algorithms exhibit excellent convergence properties for training deep learning models, but often incur significant computation and memory overheads.
Piecing Together Clues: A Benchmark for Evaluating the Detective Skills of Large Language Models
We introduces the DetectBench, a reading comprehension dataset designed to assess a model's ability to jointly ability in key information detection and multi-hop reasoning when facing complex and implicit information.
Evaluation and Optimization of Gradient Compression for Distributed Deep Learning
To accelerate distributed training, many gradient compression methods have been proposed to alleviate the communication bottleneck in synchronous stochastic gradient descent (S-SGD), but their efficacy in real-world applications still remains unclear.
D2Match: Leveraging Deep Learning and Degeneracy for Subgraph Matching
Subgraph matching is a fundamental building block for graph-based applications and is challenging due to its high-order combinatorial nature.
Xiezhi: An Ever-Updating Benchmark for Holistic Domain Knowledge Evaluation
New Natural Langauge Process~(NLP) benchmarks are urgently needed to align with the rapid development of large language models (LLMs).
Progression Cognition Reinforcement Learning with Prioritized Experience for Multi-Vehicle Pursuit
For the more challenging problem of pursuing multiple evading vehicles, these algorithms typically select a fixed target evading vehicle for pursuing vehicles without considering dynamic traffic situation, which significantly reduces pursuing success rate.
Range-Based Equal Error Rate for Spoof Localization
To properly measure misclassified ranges and better evaluate spoof localization performance, we upgrade point-based EER to range-based EER.
A Diffusion Model for Event Skeleton Generation
Event skeleton generation, aiming to induce an event schema skeleton graph with abstracted event nodes and their temporal relations from a set of event instance graphs, is a critical step in the temporal complex event schema induction task.
Do Not Train It: A Linear Neural Architecture Search of Graph Neural Networks
Neural architecture search (NAS) for Graph neural networks (GNNs), called NAS-GNNs, has achieved significant performance over manually designed GNN architectures.
Feature Expansion for Graph Neural Networks
Graph neural networks aim to learn representations for graph-structured data and show impressive performance, particularly in node classification.
Detection of Pavement Cracks by Deep Learning Models of Transformer and UNet
In this study, we investigated nine promising models to evaluate their performance in pavement surface crack detection by model accuracy, computational complexity, and model stability.
Domain Mastery Benchmark: An Ever-Updating Benchmark for Evaluating Holistic Domain Knowledge of Large Language Model--A Preliminary Release
Domain knowledge refers to the in-depth understanding, expertise, and familiarity with a specific subject, industry, field, or area of special interest.
H2TNE: Temporal Heterogeneous Information Network Embedding in Hyperbolic Spaces
Temporal heterogeneous information network (temporal HIN) embedding, aiming to represent various types of nodes of different timestamps into low dimensional spaces while preserving structural and semantic information, is of vital importance in diverse real-life tasks.
HybridCVLNet: A Hybrid CSI Feedback System and its Domain Adaptation
Deep Learning (DL)-based channel state information (CSI) feedback is a promising technique for the transmitter to accurately acquire the CSI of massive multiple-input multiple-output (MIMO) systems.
LMR: A Large-Scale Multi-Reference Dataset for Reference-based Super-Resolution
To this end, we construct a large-scale, multi-reference super-resolution dataset, named LMR.
Artificial Intelligence: 70 Years Down the Road
Artificial intelligence (AI) has a history of nearly a century from its inception to the present day.
DeAR: Accelerating Distributed Deep Learning with Fine-Grained All-Reduce Pipelining
Communication scheduling has been shown to be effective in accelerating distributed training, which enables all-reduce communications to be overlapped with backpropagation computations.
Unpaired Translation from Semantic Label Maps to Images by Leveraging Domain-Specific Simulations
We introduce a contrastive learning framework for generating photorealistic images from simulated label maps, by learning from unpaired sets of both.
A Large-scale Friend Suggestion Architecture
There has been little work on designing friend suggestion when facing these difficulties, and for the first time we aim to tackle this in large scale online games.
Unsupervised Instance and Subnetwork Selection for Network Data
We address these challenges within an unsupervised framework for joint subnetwork and instance selection in network data, called UISS, via a convex self-representation objective.
An Information-Theoretic Approach to Transferability in Task Transfer Learning
Task transfer learning is a popular technique in image processing applications that uses pre-trained models to reduce the supervision cost of related tasks.
RRSR:Reciprocal Reference-based Image Super-Resolution with Progressive Feature Alignment and Selection
While previous state-of-the-art RefSR methods mainly focus on improving the efficacy and robustness of reference feature transfer, it is generally overlooked that a well reconstructed SR image should enable better SR reconstruction for its similar LR images when it is referred to as.
Solving Math Word Problems via Cooperative Reasoning induced Language Models
This inspires us to develop a cooperative reasoning-induced PLM for solving MWPs, called Cooperative Reasoning (CoRe), resulting in a human-like reasoning architecture with system 1 as the generator and system 2 as the verifier.
Ranked #103 on
Arithmetic Reasoning
on GSM8K
Graded-Q Reinforcement Learning with Information-Enhanced State Encoder for Hierarchical Collaborative Multi-Vehicle Pursuit
However, existing works on MVP pay little attention to the importance of information exchange and cooperation among pursuing vehicles under the complex urban traffic environment.
Zero-Shot Learners for Natural Language Understanding via a Unified Multiple Choice Perspective
We propose a new paradigm for zero-shot learners that is format agnostic, i. e., it is compatible with any format and applicable to a list of language tasks, such as text classification, commonsense reasoning, coreference resolution, and sentiment analysis.
Improving Your Graph Neural Networks: A High-Frequency Booster
Graph neural networks (GNNs) hold the promise of learning efficient representations of graph-structured data, and one of its most important applications is semi-supervised node classification.
Deep Spectro-temporal Artifacts for Detecting Synthesized Speech
The Audio Deep Synthesis Detection (ADD) Challenge has been held to detect generated human-like speech.
MAP: Multimodal Uncertainty-Aware Vision-Language Pre-training Model
Multimodal semantic understanding often has to deal with uncertainty, which means the obtained messages tend to refer to multiple targets.
Learning "O" Helps for Learning More: Handling the Concealed Entity Problem for Class-incremental NER
In this work, we conduct an empirical study on the "Unlabeled Entity Problem" and find that it leads to severe confusion between "O" and entities, decreasing class discrimination of old classes and declining the model's ability to learn new classes.
Provably Uncertainty-Guided Universal Domain Adaptation
It fully utilizes the relationship between a target sample and its neighbors in the source domain to avoid the influence of domain misalignment.
Fengshenbang 1.0: Being the Foundation of Chinese Cognitive Intelligence
We hope that this project will be the foundation of Chinese cognitive intelligence.
Spoofing-Aware Attention based ASV Back-end with Multiple Enrollment Utterances and a Sampling Strategy for the SASV Challenge 2022
Current state-of-the-art automatic speaker verification (ASV) systems are vulnerable to presentation attacks, and several countermeasures (CMs), which distinguish bona fide trials from spoofing ones, have been explored to protect ASV.
AIM 2022 Challenge on Super-Resolution of Compressed Image and Video: Dataset, Methods and Results
The homepage of this challenge is at https://github. com/RenYang-home/AIM22_CompressSR.
Exploiting Inter-Sample Affinity for Knowability-Aware Universal Domain Adaptation
Specifically, we introduce a knowability-based labeling scheme which can be divided into two steps: 1) Knowability-guided detection of known and unknown samples based on the intrinsic structure of the neighborhoods of samples, where we leverage the first singular vectors of the affinity matrices to obtain the knowability of every target sample.
Safe Reinforcement Learning for a Robot Being Pursued but with Objectives Covering More Than Capture-avoidance
Reinforcement Learning (RL) algorithms show amazing performance in recent years, but placing RL in real-world applications such as self-driven vehicles may suffer safety problems.
Scalable K-FAC Training for Deep Neural Networks with Distributed Preconditioning
The second-order optimization methods, notably the D-KFAC (Distributed Kronecker Factored Approximate Curvature) algorithms, have gained traction on accelerating deep neural network (DNN) training on GPU clusters.
SsciBERT: A Pre-trained Language Model for Social Science Texts
The academic literature of social sciences records human civilization and studies human social problems.
WHU-Stereo: A Challenging Benchmark for Stereo Matching of High-Resolution Satellite Images
The WHU-Stereo dataset can serve as a challenging benchmark for stereo matching of high-resolution satellite images, and performance evaluation of deep learning models.
Multi-task Deep Neural Networks for Massive MIMO CSI Feedback
Deep learning has been widely applied for the channel state information (CSI) feedback in frequency division duplexing (FDD) massive multiple-input multiple-output (MIMO) system.
The PartialSpoof Database and Countermeasures for the Detection of Short Fake Speech Segments Embedded in an Utterance
Since the short spoofed speech segments to be embedded by attackers are of variable length, six different temporal resolutions are considered, ranging from as short as 20 ms to as large as 640 ms. Third, we propose a new CM that enables the simultaneous use of the segment-level labels at different temporal resolutions as well as utterance-level labels to execute utterance- and segment-level detection at the same time.
Confidence Estimation Transformer for Long-term Renewable Energy Forecasting in Reinforcement Learning-based Power Grid Dispatching
The expansion of renewable energy could help realizing the goals of peaking carbon dioxide emissions and carbon neutralization.
Fine-tuning Global Model via Data-Free Knowledge Distillation for Non-IID Federated Learning
Instead, we propose a data-free knowledge distillation method to fine-tune the global model in the server (FedFTG), which relieves the issue of direct model aggregation.
TMS: A Temporal Multi-scale Backbone Design for Speaker Embedding
Therefore, in the most current state-of-the-art network architectures, only a few branches corresponding to a limited number of temporal scales could be designed for speaker embeddings.
BEATS: An Open-Source, High-Precision, Multi-Channel EEG Acquisition Tool System
Commonly used EEG acquisition system's hardware and software are usually closed-source.
$ \text{T}^3 $OMVP: A Transformer-based Time and Team Reinforcement Learning Scheme for Observation-constrained Multi-Vehicle Pursuit in Urban Area
Although there are some achievements in the field of MVP in the open space environment, the urban area brings complicated road structures and restricted moving spaces as challenges to the resolution of MVP games.
Deep Reinforcement Learning-Based Joint Satellite Scheduling and Resource Allocation in Satellite-Terrestrial Integrated Networks
Our purpose is to maximize the utility of the data offloaded from satellites to BSs while considering the load balance of BSs.
Self-Augmented Unpaired Image Dehazing via Density and Depth Decomposition
With estimated scene depth, our method is capable of re-rendering hazy images with different thicknesses which further benefits the training of the dehazing network.
Learning from Temporal Gradient for Semi-supervised Action Recognition
Our method achieves the state-of-the-art performance on three video action recognition benchmarks (i. e., Kinetics-400, UCF-101, and HMDB-51) under several typical semi-supervised settings (i. e., different ratios of labeled data).
CdtGRN: Construction of qualitative time-delayed gene regulatory networks with a deep learning method
Therefore, it is of great significance to elucidate the regulation mechanism over time points.
CS-Rep: Making Speaker Verification Networks Embracing Re-parameterization
Automatic speaker verification (ASV) systems, which determine whether two speeches are from the same speaker, mainly focus on verification accuracy while ignoring inference speed.
FLBoost: On-the-Fly Fine-tuning Boosts Federated Learning via Data-free Distillation
On the contrary, we propose a new solution: on-the-fly fine-tuning the global model in server via data-free distillation to boost its performance, dubbed FLBoost to relieve the issue of direct model aggregation.
Estimating Mean Speed-of-Sound from Sequence-Dependent Geometric Disparities
We demonstrate the effectiveness of our proposed method for tomographic SoS reconstruction.
Maximum Likelihood Estimation for Multimodal Learning with Missing Modality
Moreover, we develop a generalized form of the softmax function to effectively implement maximum likelihood estimation in an end-to-end manner.
MT-ORL: Multi-Task Occlusion Relationship Learning
Retrieving occlusion relation among objects in a single image is challenging due to sparsity of boundaries in image.
A Credibility-aware Swarm-Federated Deep Learning Framework in Internet of Vehicles
This paper proposes a Swarm-Federated Deep Learning framework in the IoV system (IoV-SFDL) that integrates SL into the FDL framework.
Edge of chaos as a guiding principle for modern neural network training
Motivated by the edge of chaos principle behind the optimal performance of neural networks, we study the role of various hyperparameters in modern neural network training algorithms in terms of the order-chaos phase diagram.
Accelerating Distributed K-FAC with Smart Parallelism of Computing and Communication Tasks
Specifically, 1) we first characterize the performance bottlenecks of D-KFAC, 2) we design and implement a pipelining mechanism for Kronecker factors computation and communication with dynamic tensor fusion, and 3) we develop a load balancing placement for inverting multiple matrices on GPU clusters.
Inter-intra Variant Dual Representations forSelf-supervised Video Recognition
Contrastive learning applied to self-supervised representation learning has seen a resurgence in deep models.
Temporal Graph Signal Decomposition
We propose a general, dictionary-based framework for temporal graph signal decomposition (TGSD).
A One-Shot Texture-Perceiving Generative Adversarial Network for Unsupervised Surface Inspection
Visual surface inspection is a challenging task owing to the highly diverse appearance of target surfaces and defective regions.
Causal Discovery of Flight Service Process Based on Event Sequence
In the existing ground support research, there has not yet been a process model that directly obtains support from the ground support log to study the causal relationship between service nodes and flight delays.
An Initial Investigation for Detecting Partially Spoofed Audio
By definition, partially-spoofed utterances contain a mix of both spoofed and bona fide segments, which will likely degrade the performance of countermeasures trained with entirely spoofed utterances.
A Dynamics Perspective of Pursuit-Evasion Games of Intelligent Agents with the Ability to Learn
It is shown that, in a pursuit-evasion game with a dynamics formulation, an evader is not able to escape from a slightly faster pursuer with an effective learned pursuit strategy, based on agile maneuvers and an effective learned evasion strategy.
Content-Preserving Unpaired Translation from Simulated to Realistic Ultrasound Images
Interactive simulation of ultrasound imaging greatly facilitates sonography training.
Learning Ultrasound Rendering from Cross-Sectional Model Slices for Simulated Training
Given the high level of expertise required for navigation and interpretation of ultrasound images, computational simulations can facilitate the training of such skills in virtual reality.
Federated Learning for Non-IID Data via Unified Feature Learning and Optimization Objective Alignment
Federated Learning (FL) aims to establish a shared model across decentralized clients under the privacy-preserving constraint.
A Multi-intersection Vehicular Cooperative Control based on End-Edge-Cloud Computing
In particular, we propose a Multi-intersection Vehicular Cooperative Control (MiVeCC) to enable cooperation among vehicles in a large area with multiple unsignalized intersections.
Penalized model-based clustering of fMRI data
To this end, we propose a random covariance clustering model (RCCM) to concurrently cluster subjects based on their FC networks, estimate the unique FC networks of each subject, and to infer shared network features.
ConvGRU in Fine-grained Pitching Action Recognition for Action Outcome Prediction
Considering that the different outcomes are closely connected to the subtle differences in actions, fine-grained action recognition is a practical method for action outcome prediction.
Mask Detection and Breath Monitoring from Speech: on Data Augmentation, Feature Representation and Modeling
This paper introduces our approaches for the Mask and Breathing Sub-Challenge in the Interspeech COMPARE Challenge 2020.
Multi-resolution Super Learner for Voxel-wise Classification of Prostate Cancer Using Multi-parametric MRI
While current research has shown the importance of Multi-parametric MRI (mpMRI) in diagnosing prostate cancer (PCa), further investigation is needed for how to incorporate the specific structures of the mpMRI data, such as the regional heterogeneity and between-voxel correlation within a subject.
Deep Image Translation for Enhancing Simulated Ultrasound Images
To incorporate anatomical information potentially lost in low quality images, we additionally provide segmentation maps to image translation.
Deep Network for Scatterer Distribution Estimation for Ultrasound Image Simulation
Simulation-based ultrasound training can be an essential educational tool.
One-Shot Object Detection without Fine-Tuning
Deep learning has revolutionized object detection thanks to large-scale datasets, but their object categories are still arguably very limited.
Towards Palmprint Verification On Smartphones
First, to facilitate the study of palmprint verification on smartphones, we established an annotated palmprint dataset named MPD, which was collected by multi-brand smartphones in two separate sessions with various backgrounds and illumination conditions.
Learning Global and Local Consistent Representations for Unsupervised Image Retrieval via Deep Graph Diffusion Networks
Diffusion has shown great success in improving accuracy of unsupervised image retrieval systems by utilizing high-order structures of image manifold.
Phase Contrast Microscopy Cell PopulationSegmentation: A Survey
Phase contrast microscopy (PCM) has been widely used in biomedicine research, which allows users to observe objectives without staining or killing them.
Optimal Machine Intelligence at the Edge of Chaos
It has long been suggested that the biological brain operates at some critical point between two different phases, possibly order and chaos.
An Information-Theoretic Metric of Transferability for Task Transfer Learning
An important question in task transfer learning is to determine task transferability, i. e. given a common input domain, estimating to what extent representations learned from a source task can help in learning a target task.
An Efficient Approach for Cell Segmentation in Phase Contrast Microscopy Images
In this paper, we propose a new model to segment cells in phase contrast microscopy images.
DSL: Discriminative Subgraph Learning via Sparse Self-Representation
In this work we propose an optimization framework for discriminative subgraph learning (DSL) which simultaneously enforces (i) sparsity, (ii) connectivity and (iii) high discriminative power of the resulting subgraphs of features.
An Efficient Approach to Informative Feature Extraction from Multimodal Data
We further generalize the framework to handle more than two modalities and missing modalities.
Implicit Modeling with Uncertainty Estimation for Intravoxel Incoherent Motion Imaging
Intravoxel incoherent motion (IVIM) imaging allows contrast-agent free in vivo perfusion quantification with magnetic resonance imaging (MRI).
An empirical learning-based validation procedure for simulation workflow
Simulation workflow is a top-level model for the design and control of simulation process.
Deep Smoke Segmentation
According to results of our deep segmentation method, we can easily and accurately perform smoke detection from videos.
Temporal Interpolation via Motion Field Prediction
Temporal interpolation of navigator slices an be used to reduce the number of navigator acquisitions without degrading specificity in stacking.
Self-Supervised Siamese Learning on Stereo Image Pairs for Depth Estimation in Robotic Surgery
Robotic surgery has become a powerful tool for performing minimally invasive procedures, providing advantages in dexterity, precision, and 3D vision, over traditional surgery.
Real-time 3D Tracking of Articulated Tools for Robotic Surgery
The proposed method is based on the CAD model of the tools as well as robot kinematics to generate online part-based templates for efficient 2D matching and 3D pose estimation.
Simulation of X-ray diffraction profiles for bent anisotropic crystals
The equations for calculating diffraction profiles for bent crystals are revisited for both meridional and sagittal bending.
Materials Science Optics
VSI: A Visual Saliency-Induced Index for Perceptual Image Quality Assessment
First, VS is used as a feature when computing the local quality map of the distorted image.
Ranked #7 on
Video Quality Assessment
on MSU FR VQA Database
SR-SIM: A fast and high performance IQA index based on spectral residual
Automatic image quality assessment (IQA) attempts to use computational models to measure the image quality in consistency with subjective ratings.
Ranked #9 on
Video Quality Assessment
on MSU FR VQA Database
FSIM: A Feature Similarity Index for Image Quality Assessment
Image quality assessment (IQA) aims to use computational models to measure the image quality consistently with subjective evaluations.
Ranked #2 on
Image Quality Assessment
on MSU FR VQA Database
