Search Results for author:
Found 287 papers, 95 papers with code
Graph Random Neural Network for Semi-Supervised Learning on Graphs
We study the problem of semi-supervised learning on graphs, for which graph neural networks (GNNs) have been extensively explored.
Accelerating Dataset Distillation via Model Augmentation
Dataset Distillation (DD), a newly emerging field, aims at generating much smaller but efficient synthetic training datasets from large ones.
Towards Efficient Deep Hashing Retrieval: Condensing Your Data via Feature-Embedding Matching
The expenses involved in training state-of-the-art deep hashing retrieval models have witnessed an increase due to the adoption of more sophisticated models and large-scale datasets.
Rethinking Data Distillation: Do Not Overlook Calibration
Neural networks trained on distilled data often produce over-confident output and require correction by calibration methods.
Federated Mutual Learning
The experiments show that FML can achieve better performance than alternatives in typical FL setting, and clients can be benefited from FML with different models and tasks.
DaisyRec 2.0: Benchmarking Recommendation for Rigorous Evaluation
Recently, one critical issue looms large in the field of recommender systems -- there are no effective benchmarks for rigorous evaluation -- which consequently leads to unreproducible evaluation and unfair comparison.
Self-supervised Equivariant Attention Mechanism for Weakly Supervised Semantic Segmentation
Our method is based on the observation that equivariance is an implicit constraint in fully supervised semantic segmentation, whose pixel-level labels take the same spatial transformation as the input images during data augmentation.
Data Augmentation
Weakly supervised Semantic Segmentation
+1
Class-incremental Learning via Deep Model Consolidation
The idea is to first train a separate model only for the new classes, and then combine the two individual models trained on data of two distinct set of classes (old classes and new classes) via a novel double distillation training objective.
Federated Learning with Label Distribution Skew via Logits Calibration
Extensive experiments on federated datasets and real-world datasets demonstrate that FedLC leads to a more accurate global model and much improved performance.
HINet: Half Instance Normalization Network for Image Restoration
Specifically, we present a novel block: Half Instance Normalization Block (HIN Block), to boost the performance of image restoration networks.
Ranked #3 on
Single Image Deraining
on Test2800
Learning to Dispatch for Job Shop Scheduling via Deep Reinforcement Learning
Priority dispatching rule (PDR) is widely used for solving real-world Job-shop scheduling problem (JSSP).
LUAI Challenge 2021 on Learning to Understand Aerial Images
This report summarizes the results of Learning to Understand Aerial Images (LUAI) 2021 challenge held on ICCV 2021, which focuses on object detection and semantic segmentation in aerial images.
The RoboDepth Challenge: Methods and Advancements Towards Robust Depth Estimation
In this paper, we summarize the winning solutions from the RoboDepth Challenge -- an academic competition designed to facilitate and advance robust OoD depth estimation.
Single-Side Domain Generalization for Face Anti-Spoofing
In this work, we propose an end-to-end single-side domain generalization framework (SSDG) to improve the generalization ability of face anti-spoofing.
Graph Random Neural Networks for Semi-Supervised Learning on Graphs
We study the problem of semi-supervised learning on graphs, for which graph neural networks (GNNs) have been extensively explored.
PICASSO: Unleashing the Potential of GPU-centric Training for Wide-and-deep Recommender Systems
However, we observe that GPU devices in training recommender systems are underutilized, and they cannot attain an expected throughput improvement as what it has achieved in CV and NLP areas.
Adaptive Image Transformations for Transfer-based Adversarial Attack
Adversarial attacks provide a good way to study the robustness of deep learning models.
ID-Animator: Zero-Shot Identity-Preserving Human Video Generation
Based on this pipeline, a random face reference training method is further devised to precisely capture the ID-relevant embeddings from reference images, thus improving the fidelity and generalization capacity of our model for ID-specific video generation.
Deep Reinforcement Learning for Solving the Heterogeneous Capacitated Vehicle Routing Problem
To solve those problems, we propose a DRL method based on the attention mechanism with a vehicle selection decoder accounting for the heterogeneous fleet constraint and a node selection decoder accounting for the route construction, which learns to construct a solution by automatically selecting both a vehicle and a node for this vehicle at each step.
Self-supervised Scale Equivariant Network for Weakly Supervised Semantic Segmentation
This regularized CAM can be embedded in most recent advanced weakly supervised semantic segmentation framework.
Multi-granularity Correspondence Learning from Long-term Noisy Videos
Existing video-language studies mainly focus on learning short video clips, leaving long-term temporal dependencies rarely explored due to over-high computational cost of modeling long videos.
Ranked #1 on
Zero-Shot Video Retrieval
on YouCook2
Action Segmentation
Long Video Retrieval (Background Removed)
+2
Semi-supervised Learning on Graphs with Generative Adversarial Nets
We first provide insights on working principles of adversarial learning over graphs and then present GraphSGAN, a novel approach to semi-supervised learning on graphs.
Benchmarking High Bandwidth Memory on FPGAs
FPGAs are starting to be enhanced with High Bandwidth Memory (HBM) as a way to reduce the memory bandwidth bottleneck encountered in some applications and to give the FPGA more capacity to deal with application state.
Hardware Architecture
Learning Improvement Heuristics for Solving Routing Problems
In this paper, we propose a deep reinforcement learning framework to learn the improvement heuristics for routing problems.
Model Watermarking for Image Processing Networks
In this way, when the attacker trains one surrogate model by using the input-output pairs of the target model, the hidden watermark will be learned and extracted afterward.
Deep Model Intellectual Property Protection via Deep Watermarking
By jointly training the target model and watermark embedding, the extra barrier can even be absorbed into the target model.
Real-Fake: Effective Training Data Synthesis Through Distribution Matching
Synthetic training data has gained prominence in numerous learning tasks and scenarios, offering advantages such as dataset augmentation, generalization evaluation, and privacy preservation.
NeuroLKH: Combining Deep Learning Model with Lin-Kernighan-Helsgaun Heuristic for Solving the Traveling Salesman Problem
We present NeuroLKH, a novel algorithm that combines deep learning with the strong traditional heuristic Lin-Kernighan-Helsgaun (LKH) for solving Traveling Salesman Problem.
Pan-Mamba: Effective pan-sharpening with State Space Model
To the best of our knowledge, this work is the first attempt in exploring the potential of the Mamba model and establishes a new frontier in the pan-sharpening techniques.
Multi-Decoder Attention Model with Embedding Glimpse for Solving Vehicle Routing Problems
We present a novel deep reinforcement learning method to learn construction heuristics for vehicle routing problems.
MVMoE: Multi-Task Vehicle Routing Solver with Mixture-of-Experts
In this paper, we aim to develop a unified neural solver that can cope with a range of VRP variants simultaneously.
SelfCF: A Simple Framework for Self-supervised Collaborative Filtering
Collaborative filtering (CF) is widely used to learn informative latent representations of users and items from observed interactions.
Parameterized Knowledge Transfer for Personalized Federated Learning
To deal with such model constraints, we exploit the potentials of heterogeneous model settings and propose a novel training framework to employ personalized models for different clients.
Initiative Defense against Facial Manipulation
To this end, we first imitate the target manipulation model with a surrogate model, and then devise a poison perturbation generator to obtain the desired venom.
Towards Omni-generalizable Neural Methods for Vehicle Routing Problems
Learning heuristics for vehicle routing problems (VRPs) has gained much attention due to the less reliance on hand-crafted rules.
Learning Large Neighborhood Search Policy for Integer Programming
We then design a neural network to learn policies for each variable in parallel, trained by a customized actor-critic algorithm.
Learning to Solve Multiple-TSP with Time Window and Rejections via Deep Reinforcement Learning
We propose a manager-worker framework based on deep reinforcement learning to tackle a hard yet nontrivial variant of Travelling Salesman Problem (TSP), \ie~multiple-vehicle TSP with time window and rejections (mTSPTWR), where customers who cannot be served before the deadline are subject to rejections.
FocusNetv2: Imbalanced Large and Small Organ Segmentation with Adversarial Shape Constraint for Head and Neck CT Images
Radiotherapy is a treatment where radiation is used to eliminate cancer cells.
TARGET: Federated Class-Continual Learning via Exemplar-Free Distillation
This paper focuses on an under-explored yet important problem: Federated Class-Continual Learning (FCCL), where new classes are dynamically added in federated learning.
Watermarking Text Generated by Black-Box Language Models
To allow third-parties to autonomously inject watermarks into generated text, we develop a watermarking framework for black-box language model usage scenarios.
Federated Generative Learning with Foundation Models
Existing federated learning solutions focus on transmitting features, parameters or gadients between clients and server, which suffer from serious low-efficiency and privacy-leakage problems.
Towards Tracing Trustworthiness Dynamics: Revisiting Pre-training Period of Large Language Models
This research provides an initial exploration of trustworthiness modeling during LLM pre-training, seeking to unveil new insights and spur further developments in the field.
Meta Gradient Adversarial Attack
In recent years, research on adversarial attacks has become a hot spot.
DENSE: Data-Free One-Shot Federated Learning
One-shot Federated Learning (FL) has recently emerged as a promising approach, which allows the central server to learn a model in a single communication round.
Deep Reinforcement Learning Guided Improvement Heuristic for Job Shop Scheduling
Recent studies in using deep reinforcement learning (DRL) to solve Job-shop scheduling problems (JSSP) focus on construction heuristics.
Pseudo Label-Guided Model Inversion Attack via Conditional Generative Adversarial Network
At first, a top-n selection strategy is proposed to provide pseudo-labels for public data, and use pseudo-labels to guide the training of the cGAN.
Passport-aware Normalization for Deep Model Protection
Only when the model IP is suspected to be stolen by someone, the private passport-aware branch is added back for ownership verification.
Learning to Solve Routing Problems via Distributionally Robust Optimization
Recent deep models for solving routing problems always assume a single distribution of nodes for training, which severely impairs their cross-distribution generalization ability.
Spectral Network Embedding: A Fast and Scalable Method via Sparsity
In this paper, we propose a $10\times \sim 100\times$ faster network embedding method, called Progle, by elegantly utilizing the sparsity property of online networks and spectral analysis.
IDEAL: Query-Efficient Data-Free Learning from Black-box Models
Knowledge Distillation (KD) is a typical method for training a lightweight student model with the help of a well-trained teacher model.
Learning Large Neighborhood Search for Vehicle Routing in Airport Ground Handling
Dispatching vehicle fleets to serve flights is a key task in airport ground handling (AGH).
Neural Airport Ground Handling
Airport ground handling (AGH) offers necessary operations to flights during their turnarounds and is of great importance to the efficiency of airport management and the economics of aviation.
Towards Efficient Data Free Black-Box Adversarial Attack
The proposed method can efficiently imitate the target model through a small number of queries and achieve high attack success rate.
Poison Ink: Robust and Invisible Backdoor Attack
As the image structure can keep its semantic meaning during the data transformation, such trigger pattern is inherently robust to data transformations.
Multi-Normal Estimation via Pair Consistency Voting
This paper presents a unified definition for point cloud normals of feature and non-feature points, which allows feature points to possess multiple normals.
Learning an Adaptive Meta Model-Generator for Incrementally Updating Recommender Systems
Recommender Systems (RSs) in real-world applications often deal with billions of user interactions daily.
Learning Variable Ordering Heuristics for Solving Constraint Satisfaction Problems
In this paper, we propose a deep reinforcement learning based approach to automatically discover new variable ordering heuristics that are better adapted for a given class of CSP instances.
Attributes Aware Face Generation with Generative Adversarial Networks
Recent studies have shown remarkable success in face image generations.
Pairwise Emotional Relationship Recognition in Drama Videos: Dataset and Benchmark
We expect the ERATO as well as our proposed SMTA to open up a new way for PERR task in video understanding and further improve the research of multi-modal fusion methodology.
Robust Data2vec: Noise-robust Speech Representation Learning for ASR by Combining Regression and Improved Contrastive Learning
Self-supervised pre-training methods based on contrastive learning or regression tasks can utilize more unlabeled data to improve the performance of automatic speech recognition (ASR).
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
Control Risk for Potential Misuse of Artificial Intelligence in Science
In this study, we aim to raise awareness of the dangers of AI misuse in science, and call for responsible AI development and use in this domain.
Sampling Efficient Deep Reinforcement Learning through Preference-Guided Stochastic Exploration
We theoretically prove that the policy improvement theorem holds for the preference-guided $\epsilon$-greedy policy and experimentally show that the inferred action preference distribution aligns with the landscape of corresponding Q-values.
Learning Pseudo Labels for Semi-and-Weakly Supervised Semantic Segmentation
Firstly, we introduce a class-aware cross entropy (CCE) loss for network training.
PGDQN: Preference-Guided Deep Q-Network
Stochastic exploration is the key to the success of the Deep Q-network (DQN) algorithm.
CCLAP: Controllable Chinese Landscape Painting Generation via Latent Diffusion Model
While the style aggregator module is to generate paintings of a style corresponding to a reference image.
Symbol: Generating Flexible Black-Box Optimizers through Symbolic Equation Learning
Recent Meta-learning for Black-Box Optimization (MetaBBO) methods harness neural networks to meta-learn configurations of traditional black-box optimizers.
A Multi-Channel Next POI Recommendation Framework with Multi-Granularity Check-in Signals
Being equipped with three modules (i. e., global user behavior encoder, local multi-channel encoder, and region-aware weighting strategy), MCMG is capable of capturing both fine- and coarse-grained sequential regularities as well as exploring the dynamic impact of multi-channel by differentiating the region check-in patterns.
CBVS: A Large-Scale Chinese Image-Text Benchmark for Real-World Short Video Search Scenarios
Differently, video covers in short video search scenarios are presented as user-originated contents that provide important visual summaries of videos.
Ranked #1 on
Image Retrieval
on CBVS
Class-Incremental Learning via Knowledge Amalgamation
Catastrophic forgetting has been a significant problem hindering the deployment of deep learning algorithms in the continual learning setting.
Active Sampling for Min-Max Fairness
We propose simple active sampling and reweighting strategies for optimizing min-max fairness that can be applied to any classification or regression model learned via loss minimization.
BASEN: Time-Domain Brain-Assisted Speech Enhancement Network with Convolutional Cross Attention in Multi-talker Conditions
In this paper, we thus propose a novel time-domain brain-assisted SE network (BASEN) incorporating electroencephalography (EEG) signals recorded from the listener for extracting the target speaker from monaural speech mixtures.
Toward stochastic neural computing
To account for the propagation of correlated neural variability, we derive from first principles a moment embedding for spiking neural network (SNN).
Data-Free Hard-Label Robustness Stealing Attack
In response to these identified gaps, we introduce a novel Data-Free Hard-Label Robustness Stealing (DFHL-RS) attack in this paper, which enables the stealing of both model accuracy and robustness by simply querying hard labels of the target model without the help of any natural data.
ACDC: Online Unsupervised Cross-Domain Adaptation
We consider the problem of online unsupervised cross-domain adaptation, where two independent but related data streams with different feature spaces -- a fully labeled source stream and an unlabeled target stream -- are learned together.
MGC: A Complex-Valued Graph Convolutional Network for Directed Graphs
We test our model on several graph datasets including directed homogeneous and heterogeneous graphs.
SAME: Sample Reconstruction against Model Extraction Attacks
While deep learning models have shown significant performance across various domains, their deployment needs extensive resources and advanced computing infrastructure.
Pre-trained Model Guided Fine-Tuning for Zero-Shot Adversarial Robustness
Specifically, PMG-AFT minimizes the distance between the features of adversarial examples in the target model and those in the pre-trained model, aiming to preserve the generalization features already captured by the pre-trained model.
A Critical Study on Data Leakage in Recommender System Offline Evaluation
To evaluate recommendation systems in a realistic manner in offline setting, we propose a timeline scheme, which calls for a revisit of the recommendation model design.
TGCN: Time Domain Graph Convolutional Network for Multiple Objects Tracking
Multiple object tracking is to give each object an id in the video.
BridgeDPI: A Novel Graph Neural Network for Predicting Drug-Protein Interactions
Therefore, we hope to develop a novel supervised learning method to learn the PPAs and DDAs effectively and thereby improve the prediction performance of the specific task of DPI.
Adversarial Examples for Good: Adversarial Examples Guided Imbalanced Learning
Adversarial examples are inputs for machine learning models that have been designed by attackers to cause the model to make mistakes.
Frequency-Adaptive Pan-Sharpening with Mixture of Experts
Pan-sharpening involves reconstructing missing high-frequency information in multi-spectral images with low spatial resolution, using a higher-resolution panchromatic image as guidance.
PRIME: Protect Your Videos From Malicious Editing
With the development of generative models, the quality of generated content keeps increasing.
STAN-CT: Standardizing CT Image using Generative Adversarial Network
Computed tomography (CT) plays an important role in lung malignancy diagnostics and therapy assessment and facilitating precision medicine delivery.
From Deterioration to Acceleration: A Calibration Approach to Rehabilitating Step Asynchronism in Federated Optimization
In the setting of federated optimization, where a global model is aggregated periodically, step asynchronism occurs when participants conduct model training by efficiently utilizing their computational resources.
Do Loyal Users Enjoy Better Recommendations? Understanding Recommender Accuracy from a Time Perspective
Our study offers a different perspective to understand recommender accuracy, and our findings could trigger a revisit of recommender model design.
Reinforcement Learning Enhanced Weighted Sampling for Accurate Subgraph Counting on Fully Dynamic Graph Streams
Specifically, we propose a weighted sampling algorithm called WSD for estimating the subgraph count in a fully dynamic graph stream, which samples the edges based on their weights that indicate their importance and reflect their properties.
Enhancing RAW-to-sRGB with Decoupled Style Structure in Fourier Domain
However, current methods often ignore the difference between cell phone RAW images and DSLR camera RGB images, a difference that goes beyond the color matrix and extends to spatial structure due to resolution variations.
Multichannel AV-wav2vec2: A Framework for Learning Multichannel Multi-Modal Speech Representation
Considering that visual information helps to improve speech recognition performance in noisy scenes, in this work we propose a multichannel multi-modal speech self-supervised learning framework AV-wav2vec2, which utilizes video and multichannel audio data as inputs.
Audio-Visual Speech Recognition
Automatic Speech Recognition
+7
Towards Cross-Domain Continual Learning
In this work, we introduce a novel approach called Cross-Domain Continual Learning (CDCL) that addresses the limitations of being limited to single supervised domains.
Dynamically Hierarchy Revolution: DirNet for Compressing Recurrent Neural Network on Mobile Devices
Recurrent neural networks (RNNs) achieve cutting-edge performance on a variety of problems.
Inference Aided Reinforcement Learning for Incentive Mechanism Design in Crowdsourcing
Incentive mechanisms for crowdsourcing are designed to incentivize financially self-interested workers to generate and report high-quality labels.
An Unsupervised Clustering-Based Short-Term Solar Forecasting Methodology Using Multi-Model Machine Learning Blending
This methodology consists of three parts: GHI time series unsupervised clustering, pattern recognition, and UC-based forecasting.
Hourly-Similarity Based Solar Forecasting Using Multi-Model Machine Learning Blending
The final optimal model is a combination of MMFF models with the best-performed blending algorithm at every hour.
Interacting Attention-gated Recurrent Networks for Recommendation
In particular, we propose a novel attention scheme to learn the attention scores of user and item history in an interacting way, thus to account for the dependencies between user and item dynamics in shaping user-item interactions.
Multi-task Dictionary Learning based Convolutional Neural Network for Computer aided Diagnosis with Longitudinal Images
Firstly, we pre-train CNN on the ImageNet dataset and transfer the knowledge from the pre-trained model to the medical imaging progression representation, generating the features for different tasks.
Intensity Video Guided 4D Fusion for Improved Highly Dynamic 3D Reconstruction
The availability of high-speed 3D video sensors has greatly facilitated 3D shape acquisition of dynamic and deformable objects, but high frame rate 3D reconstruction is always degraded by spatial noise and temporal fluctuations.
Large-scale Feature Selection of Risk Genetic Factors for Alzheimer's Disease via Distributed Group Lasso Regression
Then we select the relevant group features by performing the group Lasso feature selection process in a sequence of parameters.
Seeing the Forest from the Trees in Two Looks: Matrix Sketching by Cascaded Bilateral Sampling
Given a matrix A of size m by n, state-of-the-art randomized algorithms take O(m * n) time and space to obtain its low-rank decomposition.
Scaling POMDPs For Selecting Sellers in E-markets-Extended Version
In multiagent e-marketplaces, buying agents need to select good sellers by querying other buyers (called advisors).
Reinforcement Learning based Dynamic Model Selection for Short-Term Load Forecasting
The optimal DMS policy is applied to select the best model at each time step with a moving window.
An Operation Network for Abstractive Sentence Compression
Delete-based models have the strong ability to delete undesired words, while generate-based models are able to reorder or rephrase the words, which are more coherent to human sentence compression.
Geometric Constrained Joint Lane Segmentation and Lane Boundary Detection
The main contributions of the proposed frame- work are highlighted in two facets: (1) We put forward a multiple-task learning framework with mutually interlinked sub-structures between lane segmentation and lane boundary detection to improve overall performance.
Occlusion-Free Face Alignment: Deep Regression Networks Coupled With De-Corrupt AutoEncoders
Face alignment or facial landmark detection plays an important role in many computer vision applications, e. g., face recognition, facial expression recognition, face animation, etc.
Leveraging Datasets With Varying Annotations for Face Alignment via Deep Regression Network
Facial landmark detection, as a vital topic in computer vision, has been studied for many decades and lots of datasets have been collected for evaluation.
MICIK: MIning Cross-Layer Inherent Similarity Knowledge for Deep Model Compression
State-of-the-art deep model compression methods exploit the low-rank approximation and sparsity pruning to remove redundant parameters from a learned hidden layer.
Generative Visual Dialogue System via Adaptive Reasoning and Weighted Likelihood Estimation
The key challenge of generative Visual Dialogue (VD) systems is to respond to human queries with informative answers in natural and contiguous conversation flow.
Regularize, Expand and Compress: Multi-task based Lifelong Learning via NonExpansive AutoML
Lifelong learning, the problem of continual learning where tasks arrive in sequence, has been lately attracting more attention in the computer vision community.
Correlative Multi-Label Multi-Instance Image Annotation
The cross-level label coherence en-codes the consistency between the labels at the image leveland the labels at the region level.
Average-case Analysis of the Assignment Problem with Independent Preferences
Recently, [Deng, Gao, Zhang 2017] show that when the agents' preferences are drawn from a uniform distribution, its \textit{average-case approximation ratio} is upper bounded by 3. 718.
Transferrable Operative Difficulty Assessment in Robot-assisted Teleoperation: A Domain Adaptation Approach
Providing an accurate and efficient assessment of operative difficulty is important for designing robot-assisted teleoperation interfaces that are easy and natural for human operators to use.
Imbalanced Learning-based Automatic SAR Images Change Detection by Morphologically Supervised PCA-Net
Change detection is a quite challenging task due to the imbalance between unchanged and changed class.
Method of diagnosing heart disease based on deep learning ECG signal
Some have tried to combine expertise and signal processing to classify ECG signal by heart disease type.
FocusNet: Imbalanced Large and Small Organ Segmentation with an End-to-End Deep Neural Network for Head and Neck CT Images
In this paper, we propose an end-to-end deep neural network for solving the problem of imbalanced large and small organ segmentation in head and neck (HaN) CT images.
Video Affective Effects Prediction with Multi-modal Fusion and Shot-Long Temporal Context
We select the most suitable modalities for valence and arousal tasks respectively and each modal feature is extracted using the modality-specific pre-trained deep model on large generic dataset.
Research Commentary on Recommendations with Side Information: A Survey and Research Directions
This Research Commentary aims to provide a comprehensive and systematic survey of the recent research on recommender systems with side information.
Hierarchical Attentive Knowledge Graph Embedding for Personalized Recommendation
Knowledge graphs (KGs) have proven to be effective for high-quality recommendation, where the connectivities between users and items provide rich and complementary information to user-item interactions.
Bilinear Constraint based ADMM for Mixed Poisson-Gaussian Noise Removal
In this paper, we propose new operator-splitting algorithms for the total variation regularized infimal convolution (TV-IC) model [4] in order to remove mixed Poisson-Gaussian(MPG) noise.
Which Channel to Ask My Question? Personalized Customer Service RequestStream Routing using DeepReinforcement Learning
These observations suggest that our proposed method can seek the trade-off where both channel resources and customers' satisfaction are optimal.
COBRA: Context-aware Bernoulli Neural Networks for Reputation Assessment
Trust and reputation management (TRM) plays an increasingly important role in large-scale online environments such as multi-agent systems (MAS) and the Internet of Things (IoT).
Bounded Incentives in Manipulating the Probabilistic Serial Rule
In this paper, we characterize the extent to which an individual agent can increase its utility by strategic manipulation.
Application of Structural Similarity Analysis of Visually Salient Areas and Hierarchical Clustering in the Screening of Similar Wireless Capsule Endoscopic Images
Small intestinal capsule endoscopy is the mainstream method for inspecting small intestinal lesions, but a single small intestinal capsule endoscopy will produce 60, 000 - 120, 000 images, the majority of which are similar and have no diagnostic value.
Multiform Fonts-to-Fonts Translation via Style and Content Disentangled Representations of Chinese Character
The main purpose of this paper is to design a network framework that can extract and recombine the content and style of the characters.
Reconstructing normal section profiles of 3D revolving structures via pose-unconstrained multi-line structured-light vision
First, we establish a model to estimate the axis of 3D revolving geometrical structure and the normal section profile using corresponding points.
A Convolutional Neural Network with Parallel Multi-Scale Spatial Pooling to Detect Temporal Changes in SAR Images
Furthermore, to verify the generalization of the proposed method, we apply our proposed method to the cross-dataset bitemporal SAR image change detection, where the MSSP network (MSSP-Net) is trained on a dataset and then applied to an unknown testing dataset.
A Re-visit of the Popularity Baseline in Recommender Systems
On the widely used MovieLens dataset, we show that the performance of popularity could be significantly improved by 70% or more, if we consider the popular items at the time point when a user interacts with the system.
Structural Landmarking and Interaction Modelling: on Resolution Dilemmas in Graph Classification
Graph neural networks are promising architecture for learning and inference with graph-structured data.
Attentive Fusion Enhanced Audio-Visual Encoding for Transformer Based Robust Speech Recognition
The proposed method can sufficiently combine the two streams and weaken the over-reliance on the audio modality.
Low-Rank Reorganization via Proportional Hazards Non-negative Matrix Factorization Unveils Survival Associated Gene Clusters
Towards the goal of precision health and cancer treatments, the proposed algorithm can help understand and interpret high-dimensional heterogeneous genomics data with accurate identification of survival-associated gene clusters.
Adaptive Structural Fingerprints for Graph Attention Networks
Yet, how to fully exploit rich structural information in the attention mechanism remains a challenge.
Cascaded Semantic and Positional Self-Attention Network for Document Classification
In this work, we propose a new architecture to aggregate the two sources of information using cascaded semantic and positional self-attention network (CSPAN) in the context of document classification.
FrUITeR: A Framework for Evaluating UI Test Reuse
UI testing is tedious and time-consuming due to the manual effort required.
Software Engineering
Digital Twins: State of the Art Theory and Practice, Challenges, and Open Research Questions
This work explores the various DT features and current approaches, the shortcomings and reasons behind the delay in the implementation and adoption of digital twin.
Low-frequency whistler waves excited by relativistic laser pulses
It is shown by multi-dimensional particle-in-cell simulations that intense secondary whistler waves with special vortex-like field topology can be excited by a relativistic laser pulse in the highly magnetized, near-critical density plasma.
Plasma Physics
Delayed Feedback Modeling for the Entire Space Conversion Rate Prediction
In this paper, we propose a novel neural network framework ESDF to tackle the above three challenges simultaneously.
Wireless Performance Evaluation of Building Layouts: Closed-Form Computation of Figures of Merit
This paper presents a part of our ground-breaking work on evaluation of buildings in terms of wireless friendliness in the building-design stage.
Estimation of the Laser Frequency Nosie Spectrum by Continuous Dynamical Decoupling
Decoherence induced by the laser frequency noise is one of the most important obstacles in the quantum information processing.
Quantum Physics
Multiclass Spinal Cord Tumor Segmentation on MRI with Deep Learning
To the best of our knowledge, this is the first fully automatic deep learning model for spinal cord tumor segmentation.
Optical manipulation of electronic dimensionality in a quantum material
Exotic phenomenon can be achieved in quantum materials by confining electronic states into two dimensions.
Strongly Correlated Electrons Materials Science Superconductivity
An Improvement for Quantum Tunneling Radiation of Fermions in a Stationary Kerr-Newman Black Hole Spacetime
By introducing a specific etheric-like vector in the Dirac equation with Lorentz Invariance Violation (LIV) in the curved spacetime, an improved method for quantum tunneling radiation of fermions is proposed.
General Relativity and Quantum Cosmology High Energy Physics - Theory
Spin and polarization effects on the nonlinear Breit-Wheeler pair production in laser-plasma interaction
The spin effect of electrons/positrons ($e^-$/$e^+$) and polarization effect of $\gamma$ photons are investigated in the interaction of two counter-propagating linearly polarized 10-PW-class laser pulses with a thin foil target.
Plasma Physics
Spatio-Temporal Multi-step Prediction of Influenza Outbreaks
We compared the MAPEs of SVM, RF, LSTM models of predicting flu data of the 1-4 weeks ahead with and without other countries' flu data.
Dynamic Virtual Graph Significance Networks for Predicting Influenza
In this study, we develop a novel method, Dynamic Virtual Graph Significance Networks (DVGSN), which can supervisedly and dynamically learn from similar "infection situations" in historical timepoints.
Meta-Path-Free Representation Learning on Heterogeneous Networks
To the best of our knowledge, this is the first attempt to break out of the confinement of meta-paths for representation learning on heterogeneous networks.
M6: A Chinese Multimodal Pretrainer
In this work, we construct the largest dataset for multimodal pretraining in Chinese, which consists of over 1. 9TB images and 292GB texts that cover a wide range of domains.
Reversible Watermarking in Deep Convolutional Neural Networks for Integrity Authentication
Specifically, we present the reversible watermarking problem of deep convolutional neural networks and utilize the pruning theory of model compression technology to construct a host sequence used for embedding watermarking information by histogram shift.
M6-T: Exploring Sparse Expert Models and Beyond
Mixture-of-Experts (MoE) models can achieve promising results with outrageous large amount of parameters but constant computation cost, and thus it has become a trend in model scaling.
Diversify Question Generation with Continuous Content Selectors and Question Type Modeling
However, question generation is actually a one-to-many problem, as it is possible to raise questions with different focuses on contexts and various means of expression.
MFR 2021: Masked Face Recognition Competition
These teams successfully submitted 18 valid solutions.
From Personalized Medicine to Population Health: A Survey of mHealth Sensing Techniques
Mobile Sensing Apps have been widely used as a practical approach to collect behavioral and health-related information from individuals and provide timely intervention to promote health and well-beings, such as mental health and chronic cares.
CT Image Harmonization for Enhancing Radiomics Studies
While remarkable advances have been made in Computed Tomography (CT), capturing CT images with non-standardized protocols causes low reproducibility regarding radiomic features, forming a barrier on CT image analysis in a large scale.
Impact of Rotary-Wing UAV Wobbling on Millimeter-wave Air-to-Ground Wireless Channel
Our contributions of this paper lie in: i) modeling the wobbling process of a hovering RW UAV; ii) developing an analytical model to derive the channel temporal autocorrelation function (ACF) for the millimeter-wave RW UAV A2G link in a closed-form expression; and iii) investigating how RW UAV wobbling impacts the Doppler effect on the millimeter-wave RW UAV A2G link.
Locality-aware Channel-wise Dropout for Occluded Face Recognition
Furthermore, by randomly dropping out several feature channels, our method can well simulate the occlusion of larger area.
Supply Chain Digital Twin Framework Design: An Approach of Supply Chain Operations Reference Model and System of Systems
This paper explains what is 'twined' in supply chain digital twin and how to 'twin' them to handle the spatio-temporal dynamic issue.
Exploring Structure Consistency for Deep Model Watermarking
However, little attention has been devoted to the protection of DNNs in image processing tasks.
Data Augmentation for Multiclass Utterance Classification -- A Systematic Study
Utterance classification is a key component in many conversational systems.
Heterogeneous Attentions for Solving Pickup and Delivery Problem via Deep Reinforcement Learning
In particular, the heterogeneous attention mechanism specifically prescribes attentions for each role of the nodes while taking into account the precedence constraint, i. e., the pickup node must precede the pairing delivery node.
M6-10T: A Sharing-Delinking Paradigm for Efficient Multi-Trillion Parameter Pretraining
Recent expeditious developments in deep learning algorithms, distributed training, and even hardware design for large models have enabled training extreme-scale models, say GPT-3 and Switch Transformer possessing hundreds of billions or even trillions of parameters.
Generative Adversarial Training for Neural Combinatorial Optimization Models
Recent studies show that deep neural networks can be trained to learn good heuristics for various Combinatorial Optimization Problems (COPs).
Learning Scenario Representation for Solving Two-stage Stochastic Integer Programs
Many practical combinatorial optimization problems under uncertainty can be modeled as stochastic integer programs (SIPs), which are extremely challenging to solve due to the high complexity.
Cross-Vendor CT Image Data Harmonization Using CVH-CT
We propose a novel deep learning approach called CVH-CT for harmonizing CT images captured using scanners from different vendors.
SenseMag: Enabling Low-Cost Traffic Monitoring using Non-invasive Magnetic Sensing
Extensive experiment based on real-word field deployment (on the highways in Shenzhen, China) shows that SenseMag significantly outperforms the existing methods in both classification accuracy and the granularity of vehicle types (i. e., 7 types by SenseMag versus 4 types by the existing work in comparisons).
ICDM 2020 Knowledge Graph Contest: Consumer Event-Cause Extraction
To this end, we introduce a fresh perspective to revisit the relational event-cause extraction task and propose a novel sequence tagging framework, instead of extracting event types and events-causes separately.
3D Lip Event Detection via Interframe Motion Divergence at Multiple Temporal Resolutions
We define a motion divergence measure using 3D lip landmarks to quantify the interframe dynamics of a 3D speaking lip.
VIDEO AFFECTIVE IMPACT PREDICTION WITH MULTIMODAL FUSION AND LONG-SHORT TEMPORAL CONTEXT
Feature extraction, multi-modal fusion and temporal context fusion are crucial stages for predicting valence and arousal values in the emotional impact, but have not been successfully exploited.
Diagonal Graph Convolutional Networks with Adaptive Neighborhood Aggregation
In this paper, we revisit the mathematical foundation of GCNs and study how to extend their representation capacity.
Adaptive Perturbation for Adversarial Attack
Instead of using the sign function, we propose to directly utilize the exact gradient direction with a scaling factor for generating adversarial perturbations, which improves the attack success rates of adversarial examples even with fewer perturbations.
Deep Auto-encoder with Neural Response
In this study, we propose an integrated framework called Deep Autoencoder with Neural Response (DAE-NR), which incorporates information from ANN and the visual cortex to achieve better image reconstruction performance and higher neural representation similarity between biological and artificial neurons.
Tracing Text Provenance via Context-Aware Lexical Substitution
Tracing text provenance can help claim the ownership of text content or identify the malicious users who distribute misleading content like machine-generated fake news.
GIMIRec: Global Interaction Information Aware Multi-Interest Framework for Sequential Recommendation
Sequential recommendation based on multi-interest framework models the user's recent interaction sequence into multiple different interest vectors, since a single low-dimensional vector cannot fully represent the diversity of user interests.
FedDTG:Federated Data-Free Knowledge Distillation via Three-Player Generative Adversarial Networks
This technique mitigates the user heterogeneity problem and better protects user privacy.
Supervised and Self-supervised Pretraining Based COVID-19 Detection Using Acoustic Breathing/Cough/Speech Signals
By using the acoustic signals to train the network, respectively, we can build individual models for three tasks, whose parameters are averaged to obtain an average model, which is then used as the initialization for the BiLSTM model training of each task.
A Noise-Robust Self-supervised Pre-training Model Based Speech Representation Learning for Automatic Speech Recognition
In this work, we therefore first analyze the noise robustness of wav2vec2. 0 via experiments.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
A Coalition Formation Game Approach for Personalized Federated Learning
Facing the challenge of statistical diversity in client local data distribution, personalized federated learning (PFL) has become a growing research hotspot.
Learning Contextually Fused Audio-visual Representations for Audio-visual Speech Recognition
The proposed approach explores both the complementarity of audio-visual modalities and long-term context dependency using a transformer-based fusion module and a flexible masking strategy.
Spectral Graph Clustering for Intentional Islanding Operations in Resilient Hybrid Energy Systems
Establishing cleaner energy generation therefore improving the sustainability of the power system is a crucial task in this century, and one of the key strategies being pursued is to shift the dependence on fossil fuel to renewable technologies such as wind, solar, and nuclear.
Collaborative Intelligent Reflecting Surface Networks with Multi-Agent Reinforcement Learning
Intelligent reflecting surface (IRS) is envisioned to be widely applied in future wireless networks.
Multi-agent Reinforcement Learning
reinforcement-learning
+1
A Complementary Joint Training Approach Using Unpaired Speech and Text for Low-Resource Automatic Speech Recognition
Unpaired data has shown to be beneficial for low-resource automatic speech recognition~(ASR), which can be involved in the design of hybrid models with multi-task training or language model dependent pre-training.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Sign Bit is Enough: A Learning Synchronization Framework for Multi-hop All-reduce with Ultimate Compression
Traditional one-bit compressed stochastic gradient descent can not be directly employed in multi-hop all-reduce, a widely adopted distributed training paradigm in network-intensive high-performance computing systems such as public clouds.
Adaptive Modulation for Wobbling UAV Air-to-Ground Links in Millimeter-wave Bands
Based on the designed detectors, we propose an adaptive modulation scheme to maximize the average transmission rate under imperfect CSI by optimizing the data transmission time subject to the maximum tolerable BEP.
On Scheduling Mechanisms Beyond the Worst Case
That is, mechanism K is pointwise better than mechanism P. Next, for each task $j$, when machines' execution costs $t_i^j$ are independent and identically drawn from a task-specific distribution $F^j(t)$, we show that the average-case approximation ratio of mechanism K converges to a constant.
Boosting Pruned Networks with Linear Over-parameterization
To address this challenge, we propose a novel method that first linearly over-parameterizes the compact layers in pruned networks to enlarge the number of fine-tuning parameters and then re-parameterizes them to the original layers after fine-tuning.
Snake net and balloon force with a neural network for detecting multiple phases
In order to obtain a physical phase diagram, the snake model with an artificial neural network is applied in an unsupervised learning way by the authors of [Phys. Rev. Lett.
Joint Training of Speech Enhancement and Self-supervised Model for Noise-robust ASR
Speech enhancement (SE) is usually required as a front end to improve the speech quality in noisy environments, while the enhanced speech might not be optimal for automatic speech recognition (ASR) systems due to speech distortion.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Enhancing Face Recognition With Self-Supervised 3D Reconstruction
In this paper, we propose to enhance face recognition with a bypass of self-supervised 3D reconstruction, which enforces the neural backbone to focus on the identity-related depth and albedo information while neglects the identity-irrelevant pose and illumination information.
On the Performance of Data Compression in Clustered Fog Radio Access Networks
The fog-radio-access-network (F-RAN) has been proposed to address the strict latency requirements, which offloads computation tasks generated in user equipments (UEs) to the edge to reduce the processing latency.
Physics-informed Deep Learning for Musculoskeletal Modelling: Predicting Muscle Forces and Joint Kinematics from Surface EMG
At the same time, the physics law between muscle forces and joint kinematics is used the soft constraint.
An IRS Backscatter Enabled Integrated Sensing, Communication and Computation System
This paper proposes to leverage intelligent reflecting surface (IRS) backscatter to realize radio-frequency-chain-free uplink-transmissions (RFCF-UT).
Microwave QR Code: An IRS-Based Solution
This letter proposes to employ intelligent reflecting surface (IRS) as an information media to display a microwave quick response (QR) code for Internet-of-Things applications.
Multi-modal Transformer Path Prediction for Autonomous Vehicle
To better utilize the lane information, the lanes which are in opposite direction to target agent are not likely to be taken by the target agent and are consequently filtered out.
Hierarchical Compositional Representations for Few-shot Action Recognition
Recently action recognition has received more and more attention for its comprehensive and practical applications in intelligent surveillance and human-computer interaction.
Fed-FSNet: Mitigating Non-I.I.D. Federated Learning via Fuzzy Synthesizing Network
Concretely, we maintain an edge-agnostic hidden model in the cloud server to estimate a less-accurate while direction-aware inversion of the global model.
Speech Enhancement Using Self-Supervised Pre-Trained Model and Vector Quantization
Specifically, the encoder and bottleneck layer of the DEMUCS model are initialized using the self-supervised pretrained WavLM model, the convolution in the encoder is replaced by causal convolution, and the transformer encoder in the bottleneck layer is based on causal attention mask.
From Intelligent Agents to Trustworthy Human-Centred Multiagent Systems
The Agents, Interaction and Complexity research group at the University of Southampton has a long track record of research in multiagent systems (MAS).
A Comparative Study on Multichannel Speaker-Attributed Automatic Speech Recognition in Multi-party Meetings
Speaker-attributed automatic speech recognition (SA-ASR) in multi-party meeting scenarios is one of the most valuable and challenging ASR task.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
Feature Correlation-guided Knowledge Transfer for Federated Self-supervised Learning
We prove that FedFoA is a model-agnostic training framework and can be easily compatible with state-of-the-art unsupervised FL methods.
FedTune: A Deep Dive into Efficient Federated Fine-Tuning with Pre-trained Transformers
Federated Learning (FL) is an emerging paradigm that enables distributed users to collaboratively and iteratively train machine learning models without sharing their private data.
Demystify Self-Attention in Vision Transformers from a Semantic Perspective: Analysis and Application
In contrast, visual data exhibits a fundamentally different structure: Its basic unit (pixel) is a natural low-level representation with significant redundancies in the neighbourhood, which poses obvious challenges to the interpretability of MSA mechanism in ViT.
VATLM: Visual-Audio-Text Pre-Training with Unified Masked Prediction for Speech Representation Learning
Although speech is a simple and effective way for humans to communicate with the outside world, a more realistic speech interaction contains multimodal information, e. g., vision, text.
Exploiting Personalized Invariance for Better Out-of-distribution Generalization in Federated Learning
Recently, data heterogeneity among the training datasets on the local clients (a. k. a., Non-IID data) has attracted intense interest in Federated Learning (FL), and many personalized federated learning methods have been proposed to handle it.
Out-of-Distribution Generalization
Personalized Federated Learning
