Search Results for author:
Found 339 papers, 109 papers with code
Efficient Full-Matrix Adaptive Regularization
Due to the large number of parameters of machine learning problems, full-matrix preconditioning methods are prohibitively expensive.
STS Classification with Dual-stream CNN
Inspired by the dual-stream hypothesis in neural science, we propose a novel dual-stream framework for modeling the interweaved spatiotemporal dependency, and develop a convolutional neural network within this framework that aims to achieve high adaptability and flexibility in STS configurations from various diagonals, i. e., sequential order, dependency range and features.
Regularizing Output Distribution of Abstractive Chinese Social Media Text Summarization for Improved Semantic Consistency
Especially, the proposed approach improves the semantic consistency by 4\% in terms of human evaluation.
N2RPP: An Adversarial Network to Rebuild Plantar Pressure for ACLD Patients
Plantar pressure is one of which contains this information and it describes human walking features.
Structure-sensitive Multi-scale Deep Neural Network for Low-Dose CT Denoising
However, the radiation dose reduction compromises the signal-to-noise ratio (SNR), leading to strong noise and artifacts that down-grade CT image quality.
3D Convolutional Encoder-Decoder Network for Low-Dose CT via Transfer Learning from a 2D Trained Network
Based on the transfer learning from 2D to 3D, the 3D network converges faster and achieves a better denoising performance than that trained from scratch.
SampleAhead: Online Classifier-Sampler Communication for Learning from Synthesized Data
But, this raises an important problem in active vision: given an {\bf infinite} data space, how to effectively sample a {\bf finite} subset to train a visual classifier?
Stronger generalization bounds for deep nets via a compression approach
Analysis of correctness of our compression relies upon some newly identified \textquotedblleft noise stability\textquotedblright properties of trained deep nets, which are also experimentally verified.
Spectral Filtering for General Linear Dynamical Systems
We give a polynomial-time algorithm for learning latent-state linear dynamical systems without system identification, and without assumptions on the spectral radius of the system's transition matrix.
LEARN: Learned Experts' Assessment-based Reconstruction Network for Sparse-data CT
Compressive sensing (CS) has proved effective for tomographic reconstruction from sparsely collected data or under-sampled measurements, which are practically important for few-view CT, tomosynthesis, interior tomography, and so on.
ICFVR 2017: 3rd International Competition on Finger Vein Recognition
The development of finger vein recognition algorithms heavily depends on large-scale real-world data sets.
Traffic Flow Forecasting Using a Spatio-Temporal Bayesian Network Predictor
A novel predictor for traffic flow forecasting, namely spatio-temporal Bayesian network predictor, is proposed.
Complex Structure Leads to Overfitting: A Structure Regularization Decoding Method for Natural Language Processing
The decoding of the complex structure model is regularized by the additionally trained simple structure model.
Theoretical limitations of Encoder-Decoder GAN architectures
Encoder-decoder GANs architectures (e. g., BiGAN and ALI) seek to add an inference mechanism to the GANs setup, consisting of a small encoder deep net that maps data-points to their succinct encodings.
Identifying Restaurant Features via Sentiment Analysis on Yelp Reviews
The main approach used in this paper is to use a support vector machine (SVM) model to decipher the sentiment tendency of each review from word frequency.
Do GANs actually learn the distribution? An empirical study
Do GANS (Generative Adversarial Nets) actually learn the target distribution?
Towards Understanding the Invertibility of Convolutional Neural Networks
Several recent works have empirically observed that Convolutional Neural Nets (CNNs) are (approximately) invertible.
Spectrum Monitoring for Radar Bands using Deep Convolutional Neural Networks
The core of our framework is a deep convolutional neural network (CNN) model that enables Measurement Capable Devices to identify the presence of radar signals in the radio spectrum, even when these signals are overlapped with other sources of interference, such as commercial LTE and WLAN.
Deep Embedding Forest: Forest-based Serving with Deep Embedding Features
Built on top of a representative DNN model called Deep Crossing, and two forest/tree-based models including XGBoost and LightGBM, a two-step Deep Embedding Forest algorithm is demonstrated to achieve on-par or slightly better performance as compared with the DNN counterpart, with only a fraction of serving time on conventional hardware.
Effective face landmark localization via single deep network
In this paper, we propose a novel face alignment method using single deep network (SDN) on existing limited training data.
A Fusion Method Based on Decision Reliability Ratio for Finger Vein Verification
Our work is first to define decision reliability ratio to quantify this confidence, and then propose the Maximum Decision Reliability Ratio (MDRR) fusion method incorporating Weighted Voting.
UnrealStereo: Controlling Hazardous Factors to Analyze Stereo Vision
We generate a large synthetic image dataset with automatically computed hazardous regions and analyze algorithms on these regions.
Prediction of Manipulation Actions
In psychophysical experiments, we evaluated human observers' skills in predicting actions from video sequences of different length, depicting the hand movement in the preparation and execution of actions before and after contact with the object.
Low-dose CT denoising with convolutional neural network
To reduce the potential radiation risk, low-dose CT has attracted much attention.
Conversational Recommendation System with Unsupervised Learning
We will explore and demonstrate the effectiveness of the learning solution even when there is no hand written rules or hand labeled training data.
Low-Dose CT via Deep Neural Network
In order to reduce the potential radiation risk, low-dose CT has attracted more and more attention.
Medical Physics
CT Super-resolution GAN Constrained by the Identical, Residual, and Cycle Learning Ensemble(GAN-CIRCLE)
Specifically, with the generative adversarial network (GAN) as the building block, we enforce the cycle-consistency in terms of the Wasserstein distance to establish a nonlinear end-to-end mapping from noisy LR input images to denoised and deblurred HR outputs.
A Deep Reinforced Sequence-to-Set Model for Multi-Label Text Classification
However, the Seq2Seq model is not suitable for the MLTC task in essence.
On Reinforcement Learning for Full-length Game of StarCraft
The reinforcement training algorithm for this architecture is also investigated.
Hierarchical Reinforcement Learning
reinforcement-learning
+4
Sparse-View CT Reconstruction via Convolutional Sparse Coding
Traditional dictionary learning based CT reconstruction methods are patch-based and the features learned with these methods often contain shifted versions of the same features.
Visual Attention Network for Low Dose CT
Noise and artifacts are intrinsic to low dose CT (LDCT) data acquisition, and will significantly affect the imaging performance.
Deep Unfolded Robust PCA with Application to Clutter Suppression in Ultrasound
We compare the performance of the suggested deep network on both simulations and in-vivo rat brain scans, with a commonly practiced deep-network architecture and the fast iterative shrinkage algorithm, and show that our architecture exhibits better image quality and contrast.
Three-dimensional Optical Coherence Tomography Image Denoising through Multi-input Fully-Convolutional Networks
In recent years, there has been a growing interest in applying convolutional neural networks (CNNs) to low-level vision tasks such as denoising and super-resolution.
Low-Dose CT via Deep CNN with Skip Connection and Network in Network
The use of deep convolutional (Conv) neural networks for noise reduction in Low-Dose CT (LDCT) images has recently shown a great potential in this important application.
TechKG: A Large-Scale Chinese Technology-Oriented Knowledge Graph
In this work, we introduce TechKG, a large scale Chinese knowledge graph that is technology-oriented.
Scalable Wide and Deep Learning for Computer Assisted Coding
In recent years the use of electronic medical records has accelerated resulting in large volumes of medical data when a patient visits a healthcare facility.
Deep Visual Analogy-Making
In addition to identifying the content within a single image, relating images and generating related images are critical tasks for image understanding.
Learning Multiple Tasks with a Sparse Matrix-Normal Penalty
In this paper, we propose a matrix-variate normal penalty with sparse inverse covariances to couple multiple tasks.
Learning the Semantic Correlation: An Alternative Way to Gain from Unlabeled Text
In an empirical study, we construct 190 different text classification tasks from a real-world benchmark, and the unlabeled documents are a mixture from all these tasks.
Do GANs learn the distribution? Some Theory and Empirics
Using this evidence is presented that well-known GANs approaches do learn distributions of fairly low support.
Towards Provable Control for Unknown Linear Dynamical Systems
We study the control of symmetric linear dynamical systems with unknown dynamics and a hidden state.
Blur Processing Using Double Discrete Wavelet Transform
We propose a notion of double discrete wavelet transform (DDWT) that is designed to sparsify the blurred image and the blur kernel simultaneously.
Line-Based Multi-Label Energy Optimization for Fisheye Image Rectification and Calibration
Fisheye image rectification and estimation of intrinsic parameters for real scenes have been addressed in the literature by using line information on the distorted images.
Information Extraction from German Patient Records via Hybrid Parsing and Relation Extraction Strategies
In this paper, we report on first attempts and findings to analyzing German patient records, using a hybrid parsing architecture and a combination of two relation extraction strategies.
Joint Grammar and Treebank Development for Mandarin Chinese with HPSG
We present the ongoing development of MCG, a linguistically deep and precise grammar for Mandarin Chinese together with its accompanying treebank, both based on the linguistic framework of HPSG, and using MRS as the semantic representation.
CLIMB grammars: three projects using metagrammar engineering
This paper introduces the CLIMB (Comparative Libraries of Implementations with Matrix Basis) methodology and grammars.
Extreme Tensoring for Low-Memory Preconditioning
State-of-the-art models are now trained with billions of parameters, reaching hardware limits in terms of memory consumption.
Convolutional Sparse Coding for Compressed Sensing CT Reconstruction
Over the past few years, dictionary learning (DL)-based methods have been successfully used in various image reconstruction problems.
Testing Scenario Library Generation for Connected and Automated Vehicles, Part II: Case Studies
In Part I of this study, a general methodology for TSLG is proposed, and theoretical properties are investigated regarding the accuracy and efficiency of CAV evaluation.
Calibration, Entropy Rates, and Memory in Language Models
Building accurate language models that capture meaningful long-term dependencies is a core challenge in natural language processing.
Non-destructive three-dimensional measurement of hand vein based on self-supervised network
At present, supervised stereo methods based on deep neural network have achieved impressive results.
Multi-scale Template Matching with Scalable Diversity Similarity in an Unconstrained Environment
We propose a novel multi-scale template matching method which is robust against both scaling and rotation in unconstrained environments.
Evidence-based Trustworthiness
This paper develops a general framework for estimating the trustworthiness of information sources in an environment where multiple sources provide claims and supporting evidence, and each claim can potentially be produced by multiple sources.
Many could be better than all: A novel instance-oriented algorithm for Multi-modal Multi-label problem
The quality of data collected from different channels are inconsistent and some of them may not benefit for prediction.
Entity Suggestion by Example using a Conceptual Taxonomy
This paper provides a query processing method based on the relevance models between entity sets and concepts.
Sequence-to-sequence Pre-training with Data Augmentation for Sentence Rewriting
We study sequence-to-sequence (seq2seq) pre-training with data augmentation for sentence rewriting.
Goal-Embedded Dual Hierarchical Model for Task-Oriented Dialogue Generation
Hierarchical neural networks are often used to model inherent structures within dialogues.
Amazon at MRP 2019: Parsing Meaning Representations with Lexical and Phrasal Anchoring
This paper describes the system submission of our team Amazon to the shared task on Cross Framework Meaning Representation Parsing (MRP) at the 2019 Conference for Computational Language Learning (CoNLL).
Multi-Domain Goal-Oriented Dialogues (MultiDoGO): Strategies toward Curating and Annotating Large Scale Dialogue Data
With a total of over 81K dialogues harvested across six domains, MultiDoGO is over 8 times the size of MultiWOZ, the other largest comparable dialogue dataset currently available to the public.
RSA: Randomized Simulation as Augmentation for Robust Human Action Recognition
In this paper, we propose the Randomized Simulation as Augmentation (RSA) framework which augments real-world training data with synthetic data to improve the robustness of action recognition networks.
DASZL: Dynamic Action Signatures for Zero-shot Learning
There are many realistic applications of activity recognition where the set of potential activity descriptions is combinatorially large.
Identity Preserve Transform: Understand What Activity Classification Models Have Learnt
This can explain why an activity classification model usually fails to generalize to datasets it is not trained on.
Objects detection for remote sensing images based on polar coordinates
In this article, we introduce the polar coordinate system to the deep learning detector for the first time, and propose an anchor free Polar Remote Sensing Object Detector (P-RSDet), which can achieve competitive detection accuracy via uses simpler object representation model and less regression parameters.
Short-Term Temporal Convolutional Networks for Dynamic Hand Gesture Recognition
Subsequently, in temporal analysis, we use TCNs to extract temporal features and employ improved Squeeze-and-Excitation Networks (SENets) to strengthen the representational power of temporal features from each TCNs' layers.
Optimizing seed inputs in fuzzing with machine learning
Our experiments on a set of widely used PDF viewers demonstrate that the improved seed inputs produced by our framework could significantly increase the code coverage of the target program and the likelihood of detecting program crashes.
Cryptography and Security
No-Regret Prediction in Marginally Stable Systems
This requires a refined regret analysis, including a structural lemma showing the current state of the system to be a small linear combination of past states, even if the state grows polynomially.
Deep Multi-Task Learning via Generalized Tensor Trace Norm
The GTTN is defined as a convex combination of matrix trace norms of all possible tensor flattenings and hence it can discover all the possible low-rank structures.
Context-Aware Cross-Attention for Skeleton-Based Human Action Recognition
To facilitate end-to-end training, we further develop a scenario context information extraction branch to extract context information from raw RGB video directly.
Ranked #83 on
Skeleton Based Action Recognition
on NTU RGB+D
Over-parameterized Adversarial Training: An Analysis Overcoming the Curse of Dimensionality
Our work proves convergence to low robust training loss for \emph{polynomial} width instead of exponential, under natural assumptions and with the ReLU activation.
A Sample Complexity Separation between Non-Convex and Convex Meta-Learning
In contrast, for the non-convex formulation of a two layer linear network on the same instance, we show that both Reptile and multi-task representation learning can have new task sample complexity of $\mathcal{O}(1)$, demonstrating a separation from convex meta-learning.
Diversity, Density, and Homogeneity: Quantitative Characteristic Metrics for Text Collections
Summarizing data samples by quantitative measures has a long history, with descriptive statistics being a case in point.
Learning to Classify Intents and Slot Labels Given a Handful of Examples
Prototypical networks achieves significant gains in IC performance on the ATIS and TOP datasets, while both prototypical networks and MAML outperform the baseline with respect to SF on all three datasets.
Detecting Problem Statements in Peer Assessments
We attempt to automate the process of deciding whether a review comment detects a problem.
Hyper RPCA: Joint Maximum Correntropy Criterion and Laplacian Scale Mixture Modeling On-the-Fly for Moving Object Detection
Robust Principal Component Analysis (RPCA), as one of the most popular moving object modelling methods, aims to separate the temporally varying (i. e., moving) foreground objects from the static background in video, assuming the background frames to be low-rank while the foreground to be spatially sparse.
``Who said it, and Why?'' Provenance for Natural Language Claims
In an era where generating content and publishing it is so easy, we are bombarded with information and are exposed to all kinds of claims, some of which do not always rank high on the truth scale.
Democratizing the Edge: A Pervasive Edge Computing Framework
The needs of emerging applications, such as augmented and virtual reality, federated machine learning, and autonomous driving, have motivated edge computing--the push of computation capabilities to the edge.
Networking and Internet Architecture
Towards Accuracy-Fairness Paradox: Adversarial Example-based Data Augmentation for Visual Debiasing
Our data analysis on facial attribute recognition demonstrates (1) the attribution of model bias from imbalanced training data distribution and (2) the potential of adversarial examples in balancing data distribution.
On Loss Functions and Recurrency Training for GAN-based Speech Enhancement Systems
Recent work has shown that it is feasible to use generative adversarial networks (GANs) for speech enhancement, however, these approaches have not been compared to state-of-the-art (SOTA) non GAN-based approaches.
Audio and Speech Processing Sound
Tactical Decision Making for Emergency Vehicles Based on A Combinational Learning Method
The following approach reveals that DRL could complement rule-based avoiding strategy in generalization, and on the contrary, the rule-based avoiding strategy could complement DRL in stability, and their combination could lead to less response time, lower collision rate and smoother trajectory.
Reinforcement Learning on Computational Resource Allocation of Cloud-based Wireless Networks
This paper models this dynamic computational resource allocation problem into a Markov Decision Process (MDP) and designs a model-based reinforcement-learning agent to optimise the dynamic resource allocation of the CPU usage.
Why Are Convolutional Nets More Sample-Efficient than Fully-Connected Nets?
However, this has not been made mathematically rigorous, and the hurdle is that the fully connected net can always simulate the convolutional net (for a fixed task).
DeepWiPHY: Deep Learning-based Receiver Design and Dataset for IEEE 802.11ax Systems
In this work, we develop DeepWiPHY, a deep learning-based architecture to replace the channel estimation, common phase error (CPE) correction, sampling rate offset (SRO) correction, and equalization modules of IEEE 802. 11ax based orthogonal frequency division multiplexing (OFDM) receivers.
Fourth-Order Nonlocal Tensor Decomposition Model for Spectral Computed Tomography
Spectral computed tomography (CT) can reconstruct spectral images from different energy bins using photon counting detectors (PCDs).
CT Reconstruction with PDF: Parameter-Dependent Framework for Multiple Scanning Geometries and Dose Levels
Current mainstream of CT reconstruction methods based on deep learning usually needs to fix the scanning geometry and dose level, which will significantly aggravate the training cost and need more training data for clinical application.
Construction and application of algebraic dual polynomial representations for finite element methods on quadrilateral and hexahedral meshes
It will be shown that a bilinear form of a primal and a dual representation is equal to the vector inner product of the expansion coefficients (degrees of freedom) of both representations.
Numerical Analysis Numerical Analysis
Three-dimensional cell culture model for hepatocytes opens a new avenue of real world research on liver
3-demensional (3D) culture model is a valuable in vitro tool to study liver biology, metabolism, organogenesis, tissue morphology, drug discovery and cell-based assays.
Testing Scenario Library Generation for Connected and Automated Vehicles: An Adaptive Framework
A customized testing scenario library for a specific CAV model is generated through an adaptive process.
Extension of causal decomposition in the mutual complex dynamic process
Causal decomposition depicts a cause-effect relationship that is not based on the concept of prediction, but based on the phase dependence of time series.
Search for the reaction $e^{+}e^{-} \rightarrow π^{+}π^{-} χ_{cJ}$ and a charmonium-like structure decaying to $χ_{cJ}π^{\pm}$ between 4.18 and 4.60 GeV
We search for the process $e^{+}e^{-}\rightarrow \pi ^{+}\pi ^{-} \chi_{cJ}$ ($J=0, 1, 2$) and for a charged charmonium-like state in the $\pi ^{\pm} \chi_{cJ}$ subsystem.
High Energy Physics - Experiment
Meta learning to classify intent and slot labels with noisy few shot examples
Recently deep learning has dominated many machine learning areas, including spoken language understanding (SLU).
Inflection Point: A New Perspective on Photonic Nanojets
When light propagates through the edge or middle part of microparticle's incoming interface, there is a basic rule that light converges and diverges rapidly or slowly at the output port.
Optics
Exploring Lexical Irregularities in Hypothesis-Only Models of Natural Language Inference
Natural Language Inference (NLI) or Recognizing Textual Entailment (RTE) is the task of predicting the entailment relation between a pair of sentences (premise and hypothesis).
Natural Language Inference
Natural Language Understanding
+1
Adversarial Attacks and Defenses in Physiological Computing: A Systematic Review
Physiological computing uses human physiological data as system inputs in real time.
Cross section measurement of $e^+e^- \to p\bar{p}η$ and $e^+e^- \to p\bar{p}ω$ at center-of-mass energies between 3.773 GeV and 4.6 GeV
Based on $14. 7~\textrm{fb}^{-1}$ of $e^+e^-$ annihilation data collected with the BESIII detector at the BEPCII collider at 17 different center-of-mass energies between $3. 7730~\textrm{GeV}$ and $4. 5995~\textrm{GeV}$, Born cross sections of the two processes $e^+e^- \to p\bar{p}\eta$ and $e^+e^- \to p\bar{p}\omega$ are measured for the first time.
High Energy Physics - Experiment
Measurements of the center-of-mass energies of $e^{+}e^{-}$ collisions at BESIII
During the 2016-17 and 2018-19 running periods, the BESIII experiment collected 7. 5~fb$^{-1}$ of $e^+e^-$ collision data at center-of-mass energies ranging from 4. 13 to 4. 44 GeV.
High Energy Physics - Experiment
Model independent determination of the spin of the $Ω^{-}$ and its polarization alignment in $ψ(3686)\rightarrowΩ^{-}\barΩ^{+}$
We present an analysis of the process $\psi(3686) \to \Omega^- \bar{\Omega}^+$ ($\Omega^-\to K^-\Lambda$, $\bar{\Omega}^+\to K^+\bar{\Lambda}$, $\Lambda\to p\pi^-$, $\bar{\Lambda}\to \bar{p}\pi^+$) based on a data set of $448\times 10^6$ $\psi(3686)$ decays collected with the BESIII detector at the BEPCII electron-positron collider.
High Energy Physics - Experiment
ATCSpeechNet: A multilingual end-to-end speech recognition framework for air traffic control systems
Finally, by integrating the SRL with ASR, an end-to-end multilingual ASR framework is formulated in a supervised manner, which is able to translate the raw wave into text in one model, i. e., wave-to-text.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Measurement of the absolute branching fractions for purely leptonic $D_s^+$ decays
Constraining our measurement to the Standard Model expectation of lepton universality ($R=9. 75$), we find the more precise results $\cal B(D_s^+\to \tau^+\nu_\tau) = (5. 22\pm0. 10\pm 0. 14)\times10^{-2}$ and $A_{\it CP}(\tau^\pm\nu_\tau) = (-0. 1\pm1. 9\pm1. 0)\%$.
High Energy Physics - Experiment
Rip van Winkle's Razor: A Simple Estimate of Overfit to Test Data
Traditional statistics forbids use of test data (a. k. a.
Deep Distribution-preserving Incomplete Clustering with Optimal Transport
Clustering is a fundamental task in the computer vision and machine learning community.
MANAS: Multi-Scale and Multi-Level Neural Architecture Search for Low-Dose CT Denoising
Recent advance on neural network architecture search (NAS) has proved that the network architecture has a dramatic effect on the model performance, which indicates that current network architectures for LDCT may be sub-optimal.
IDOL-Net: An Interactive Dual-Domain Parallel Network for CT Metal Artifact Reduction
Since the dual-domain MAR methods can leverage the hybrid information from both sinogram and image domains, they have significantly improved the performance compared to single-domain methods.
PointShuffleNet: Learning Non-Euclidean Features with Homotopy Equivalence and Mutual Information
In this paper, we introduce the homotopy equivalence relation (HER) to make the neural networks learn the data distribution from a high-dimension manifold.
Distributed Cooperative Driving in Multi-Intersection Road Networks
Cooperative driving at isolated intersections attracted great interest and had been well discussed in recent years.
Provably Convergent Learned Inexact Descent Algorithm for Low-Dose CT Reconstruction
We propose a provably convergent method, called Efficient Learned Descent Algorithm (ELDA), for low-dose CT (LDCT) reconstruction.
Optimal Cooperative Driving at Signal-Free Intersections with Polynomial-Time Complexity
Cooperative driving at signal-free intersections, which aims to improve driving safety and efficiency for connected and automated vehicles, has attracted increasing interest in recent years.
Deformable TDNN with adaptive receptive fields for speech recognition
Time Delay Neural Networks (TDNNs) are widely used in both DNN-HMM based hybrid speech recognition systems and recent end-to-end systems.
Regression Bugs Are In Your Model! Measuring, Reducing and Analyzing Regressions In NLP Model Updates
Behavior of deep neural networks can be inconsistent between different versions.
One Network to Solve Them All: A Sequential Multi-Task Joint Learning Network Framework for MR Imaging Pipeline
Magnetic resonance imaging (MRI) acquisition, reconstruction, and segmentation are usually processed independently in the conventional practice of MRI workflow.
Multi-turn Dialog System on Single-turn Data in Medical Domain
This interest has also been developed in the field of the medical domain where researchers are focusing on building a dialog system in the medical domain.
Alleviating the Knowledge-Language Inconsistency: A Study for Deep Commonsense Knowledge
Knowledge facts are typically represented by relational triples, while we observe that some commonsense facts are represented by the triples whose forms are inconsistent with the expression of language.
Visual Question Rewriting for Increasing Response Rate
Offline experiments and mechanical Turk based evaluations show that it is possible to rewrite bland questions in a more detailed and attractive way to increase the response rate, and images can be helpful.
A Comparative Study on Schema-Guided Dialogue State Tracking
In this paper, we conduct in-depth comparative studies to understand the use of natural language description for schema in dialog state tracking.
Pretrain-KGE: Learning Knowledge Representation from Pretrained Language Models
Conventional knowledge graph embedding (KGE) often suffers from limited knowledge representation, leading to performance degradation especially on the low-resource problem.
Context Analysis for Pre-trained Masked Language Models
Pre-trained language models that learn contextualized word representations from a large un-annotated corpus have become a standard component for many state-of-the-art NLP systems.
Novelty Detection via Contrastive Learning with Negative Data Augmentation
Moreover, our model is more stable for training in a non-adversarial manner, compared to other adversarial based novelty detection methods.
Dizygotic Conditional Variational AutoEncoder for Multi-Modal and Partial Modality Absent Few-Shot Learning
DCVAE conducts feature synthesis via pairing two Conditional Variational AutoEncoders (CVAEs) with the same seed but different modality conditions in a dizygotic symbiosis manner.
DR2L: Surfacing Corner Cases to Robustify Autonomous Driving via Domain Randomization Reinforcement Learning
How to explore corner cases as efficiently and thoroughly as possible has long been one of the top concerns in the context of deep reinforcement learning (DeepRL) autonomous driving.
Team Power Dynamics and Team Impact: New Perspectives on Scientific Collaboration using Career Age as a Proxy for Team Power
In Science of Science, few studies have looked at scientific collaboration from the perspective of team power dynamics.
Dual camera snapshot hyperspectral imaging system via physics informed learning
Various methods using CNNs have been developed in recent years to reconstruct HSIs, but most of the supervised deep learning methods aimed to fit a brute-force mapping relationship between the captured compressed image and standard HSIs.
Semantic Parsing in Task-Oriented Dialog with Recursive Insertion-based Encoder
At the generation time, the model constructs the semantic parse tree by recursively inserting the predicted non-terminal labels at the predicted positions until termination.
What is Your Article Based On? Inferring Fine-grained Provenance
We experiment with a newly created evaluation dataset, Politi-Prov, based on fact-checking articles from \url{www. politifact. com}; our experimental results show that our solution leads to a significant improvement over baselines.
Using Optimal Transport as Alignment Objective for fine-tuning Multilingual Contextualized Embeddings
Recent studies have proposed different methods to improve multilingual word representations in contextualized settings including techniques that align between source and target embedding spaces.
An In-depth Summary of Recent Artificial Intelligence Applications in Drug Design
However, none of them provides an in-depth summary of many applications of the recent AI models in drug design.
Generative Adversarial Network
Molecular Property Prediction
+3
Nuisance-Label Supervision: Robustness Improvement by Free Labels
Nuisance factors are those irrelevant to a task, and an ideal model should be invariant to them.
Unsupervised PET Reconstruction from a Bayesian Perspective
Positron emission tomography (PET) reconstruction has become an ill-posed inverse problem due to low-count projection data, and a robust algorithm is urgently required to improve imaging quality.
ODIST: Open World Classification via Distributionally Shifted Instances
In this work, we address the open-world classification problem with a method called ODIST, open world classification via distributionally shifted instances.
Arbitrary-Oriented Object Detection in Remote Sensing Images Based on Polar Coordinates
In this article, we introduce the polar coordinate system to the deep learning detector for the first time, and propose an anchor free Polar Remote Sensing Object Detector (P-RSDet), which can achieve competitive detection accuracy via using simpler object representation model and less regression parameters.
Ranked #12 on
Oriented Object Detection
on DOTA 1.0
LDP-Net: An Unsupervised Pansharpening Network Based on Learnable Degradation Processes
In addition, a novel hybrid loss function is proposed to constrain both spatial and spectral consistency between the pansharpened image and the PAN and LRMS images at different resolutions.
Nonlinear Multi-Objective Flux Balance Analysis of the Warburg Effect
To extend the applicability of the previous model and model the disparate cellular pathway preferences in different cell types, we built a Nonlinear Multi-Objective FBA (NLMOFBA) model by including three key objective terms (ATP production rate, lactate generation rate and ATP yield) into one objective function through linear scalarization.
Pretrain-KGEs: Learning Knowledge Representation from Pretrained Models for Knowledge Graph Embeddings
Learning knowledge graph embeddings (KGEs) is an efficient approach to knowledge graph completion.
On Predicting Generalization using GANs
Research on generalization bounds for deep networks seeks to give ways to predict test error using just the training dataset and the network parameters.
NFANet: A Novel Method for Weakly Supervised Water Extraction from High-Resolution Remote Sensing Imagery
Therefore, we study how to utilize point labels to extract water bodies and propose a novel method called the neighbor feature aggregation network (NFANet).
Multi-armed Bandits for Link Configuration in Millimeter-wave Networks
As an example, we show that within the MAB framework, the optimal beam sweeping period, beamwidth, and beam directions could be dynamically learned with sample-computational-efficient bandit algorithms.
Measuring and Reducing Model Update Regression in Structured Prediction for NLP
First, we measure and analyze model update regression in different model update settings.
Debiasing Backdoor Attack: A Benign Application of Backdoor Attack in Eliminating Data Bias
Backdoor attack is a new AI security risk that has emerged in recent years.
Physics-/Model-Based and Data-Driven Methods for Low-Dose Computed Tomography: A survey
Since 2016, deep learning (DL) has advanced tomographic imaging with remarkable successes, especially in low-dose computed tomography (LDCT) imaging.
Indoor simultaneous localization and mapping based on fringe projection profilometry
Simultaneous Localization and Mapping (SLAM) plays an important role in outdoor and indoor applications ranging from autonomous driving to indoor robotics.
Efficient Burst Raw Denoising with Variance Stabilization and Multi-frequency Denoising Network
As for each sub-network, we propose an efficient multi-frequency denoising network to remove noise of different frequencies.
DouFu: A Double Fusion Joint Learning Method For Driving Trajectory Representation
The attention fusion module incorporates route features with movement features to create a better spatial-temporal embedding.
Hands-on Wireless Sensing with Wi-Fi: A Tutorial
With the rapid development of wireless communication technology, wireless access points (AP) and internet of things (IoT) devices have been widely deployed in our surroundings.
Explanation-based Counterfactual Retraining(XCR): A Calibration Method for Black-box Models
With the rapid development of eXplainable Artificial Intelligence (XAI), a long line of past work has shown concerns about the Out-of-Distribution (OOD) problem in perturbation-based post-hoc XAI models and explanations are socially misaligned.
Adaptive Testing for Connected and Automated Vehicles with Sparse Control Variates in Overtaking Scenarios
To validate the proposed method, the high-dimensional overtaking scenarios are investigated, and the results demonstrate that our approach can further accelerate the evaluation process by about 30 times.
Two-Stage Fine-Tuning: A Novel Strategy for Learning Class-Imbalanced Data
Owing to this paucity of samples, learning on the tail classes is especially challenging for the fine-tuning when transferring a pretrained model to a downstream task.
Fine-Tuning BERT for Automatic ADME Semantic Labeling in FDA Drug Labeling to Enhance Product-Specific Guidance Assessment
Product-specific guidances (PSGs) recommended by the United States Food and Drug Administration (FDA) are instrumental to promote and guide generic drug product development.
Explicit Occlusion Reasoning for Multi-person 3D Human Pose Estimation
Inspired by the remarkable ability of humans to infer occluded joints from visible cues, we develop a method to explicitly model this process that significantly improves bottom-up multi-person human pose estimation with or without occlusions.
Ranked #10 on
3D Multi-Person Pose Estimation (absolute)
on MuPoTS-3D
3D Human Pose Estimation
3D Multi-Person Pose Estimation (absolute)
+2
Robust Speaker Extraction Network Based on Iterative Refined Adaptation
dataset confirm the superior performance of the proposed method over the network without IRA in terms of SI-SDR and PESQ improvement.
Deep Multi-task Network for Delay Estimation and Echo Cancellation
In this paper, a multi-task network is proposed to address both ref-delay estimation and echo cancellation tasks.
A non-invasive fault location method for modular multilevel converters under light load conditions
The proposed approach of injecting the second-order circulating current will rebuild the bipolar arm current of the MMC and enlarge the capacitor voltage deviations between the healthy and faulty SMs.
Impact of Loss Model Selection on Power Semiconductor Lifetime Prediction in Electric Vehicles
Power loss estimation is an indispensable procedure to conduct lifetime prediction for power semiconductor device.
Research on Multi-Objective Planning of Electric Vehicle Charging Stations Considering the Condition of Urban Traffic Network
How to weigh various factors to construct a reasonable model of charging station location and capacity has become a major difficulty in the field of electric vehicle charging facility planning.
Dense-TNT: Efficient Vehicle Type Classification Neural Network Using Satellite Imagery
Accurate vehicle type classification serves a significant role in the intelligent transportation system.
FairCLIP: Social Bias Elimination based on Attribute Prototype Learning and Representation Neutralization
Although FairCLIP is used to eliminate bias in image retrieval, it achieves the neutralization of the representation which is common to all CLIP downstream tasks.
NAS-PRNet: Neural Architecture Search generated Phase Retrieval Net for Off-axis Quantitative Phase Imaging
Single neural networks have achieved simultaneous phase retrieval with aberration compensation and phase unwrapping in off-axis Quantitative Phase Imaging (QPI).
Fair Visual Recognition via Intervention with Proxy Features
To this end, we propose \emph{Proxy Debiasing}, to first transfer the target task's learning of bias information from bias features to artificial proxy features, and then employ causal intervention to eliminate proxy features in inference.
Efficient and quantum-adaptive machine learning with fermion neural networks
Classical artificial neural networks have witnessed widespread successes in machine-learning applications.
Zero-shot Image Captioning by Anchor-augmented Vision-Language Space Alignment
We further propose Anchor Augment to guide the generative model's attention to the fine-grained information in the representation of CLIP.
Adaptive Safety Evaluation for Connected and Automated Vehicles with Sparse Control Variates
One prevailing way is to design testing scenarios using prior knowledge of CAVs, test CAVs in these scenarios, and then evaluate their safety performances.
HierarchyFL: Heterogeneous Federated Learning via Hierarchical Self-Distillation
Federated learning (FL) has been recognized as a privacy-preserving distributed machine learning paradigm that enables knowledge sharing among various heterogeneous artificial intelligence (AIoT) devices through centralized global model aggregation.
Prototype matching: children's preference for forming scientific concepts
Children have an obvious preference for "prototype matching" in scientific concept learning, which is not only obviously deviated from the current general understanding of science education that emphasizes discovery/inquiry construction, but also points out that there may be a priority relationship among various ways of concept organization (such as definition theory, prototype theory, schema theory, etc.).
AutoPINN: When AutoML Meets Physics-Informed Neural Networks
We then propose a resource-aware search strategy to explore the search space to find the best PINN model under different resource constraints.
Learning threshold neurons via the "edge of stability"
For these models, we provably establish the edge of stability phenomenon and discover a sharp phase transition for the step size below which the neural network fails to learn "threshold-like" neurons (i. e., neurons with a non-zero first-layer bias).
Dialog2API: Task-Oriented Dialogue with API Description and Example Programs
The conversational model interacts with the environment by generating and executing programs triggering a set of pre-defined APIs.
Resilient Containment Control of Heterogeneous Multi-Agent Systems Against Unbounded Sensor and Actuator Attacks
To this end, we consider the resilient containment control problem of general linear heterogeneous MAS in the face of correlated and unbounded sensor attacks, as well as general unbounded actuator attacks.
Backward Compatibility During Data Updates by Weight Interpolation
This method interpolates between the weights of the old and new model and we show in extensive experiments that it reduces negative flips without sacrificing the improved accuracy of the new model.
Optimization and scheduling for a large scale urban transportation system in a fast-changing world
This paper proposes a set of technological solutions to transform existing transport systems into more intelligent, interactive systems by utilizing optimization and control methods that can be implemented in the near future.
Hierarchical Disentangled Representation for Invertible Image Denoising and Beyond
More specifically, we decompose the noisy image into clean low-frequency and hybrid high-frequency parts with an invertible transformation and then disentangle case-specific noise and high-frequency components in the latent space.
Improving Prediction Backward-Compatiblility in NLP Model Upgrade with Gated Fusion
When upgrading neural models to a newer version, new errors that were not encountered in the legacy version can be introduced, known as regression errors.
POSGen: Personalized Opening Sentence Generation for Online Insurance Sales
Such personalized opening sentence generation is challenging because (i) there are limited historical samples for conversation topic recommendation in online insurance sales and (ii) existing text generation schemes often fail to support customized topic ordering based on user preferences.
Conversation Style Transfer using Few-Shot Learning
Conventional text style transfer approaches focus on sentence-level style transfer without considering contextual information, and the style is described with attributes (e. g., formality).
Augmented smartphone bilirubinometer enabled by a mobile app that turns smartphone into multispectral imager
This study highlights the potential of SpeCamX to improve the prediction of bio-chromophores, and its ability to transform an ordinary smartphone into a powerful medical tool without the need for additional investments or expertise.
Synthetic Datasets for Autonomous Driving: A Survey
In this paper, we summarize the evolution of synthetic dataset generation methods and review the work to date in synthetic datasets related to single and multi-task categories for to autonomous driving study.
Measuring and Mitigating Constraint Violations of In-Context Learning for Utterance-to-API Semantic Parsing
In executable task-oriented semantic parsing, the system aims to translate users' utterances in natural language to machine-interpretable programs (API calls) that can be executed according to pre-defined API specifications.
Controllable Text-to-Image Generation with GPT-4
Control-GPT works by querying GPT-4 to write TikZ code, and the generated sketches are used as references alongside the text instructions for diffusion models (e. g., ControlNet) to generate photo-realistic images.
ScienceBenchmark: A Complex Real-World Benchmark for Evaluating Natural Language to SQL Systems
Thus, the challenge is many-fold: creating NL-to-SQL systems for highly complex domains with a small amount of hand-made training data augmented with synthetic data.
Generating Images with 3D Annotations Using Diffusion Models
With explicit 3D geometry control, we can easily change the 3D structures of the objects in the generated images and obtain ground-truth 3D annotations automatically.
Textbooks Are All You Need
Despite this small scale, phi-1 attains pass@1 accuracy 50. 6% on HumanEval and 55. 5% on MBPP.
Ranked #42 on
Code Generation
on HumanEval
A Unified Framework for Solving a General Class of Nonconvexly Regularized Convex Models
Recently, several nonconvex sparse regularizers which can preserve the convexity of the cost function have received increasing attention.
Leveraging GPT-4 for Food Effect Summarization to Enhance Product-Specific Guidance Development via Iterative Prompting
Specifically, we propose a three-turn iterative prompting approach to food effect summarization in which the keyword-focused and length-controlled prompts are respectively provided in consecutive turns to refine the quality of the generated summary.
EVIL: Evidential Inference Learning for Trustworthy Semi-supervised Medical Image Segmentation
Recently, uncertainty-aware methods have attracted increasing attention in semi-supervised medical image segmentation.
Fast and Stable Diffusion Inverse Solver with History Gradient Update
To address this issue, we propose to utilize the history information of the diffusion-based inverse solvers.
Cross-Modal Concept Learning and Inference for Vision-Language Models
Based on these visual concepts, we construct a discriminative representation of images and learn a concept inference network to perform downstream image classification tasks, such as few-shot learning and domain generalization.
DiactTOD: Learning Generalizable Latent Dialogue Acts for Controllable Task-Oriented Dialogue Systems
Dialogue act annotations are important to improve response generation quality in task-oriented dialogue systems.
Benign Shortcut for Debiasing: Fair Visual Recognition via Intervention with Shortcut Features
To this end, we propose \emph{Shortcut Debiasing}, to first transfer the target task's learning of bias attributes from bias features to shortcut features, and then employ causal intervention to eliminate shortcut features during inference.
FocalDreamer: Text-driven 3D Editing via Focal-fusion Assembly
While text-3D editing has made significant strides in leveraging score distillation sampling, emerging approaches still fall short in delivering separable, precise and consistent outcomes that are vital to content creation.
Tackling Vision Language Tasks Through Learning Inner Monologues
Visual language tasks require AI models to comprehend and reason with both visual and textual content.
Unsupervised Prototype Adapter for Vision-Language Models
To leverage the valuable knowledge encoded within these models for downstream tasks, several fine-tuning approaches, including prompt tuning methods and adapter-based methods, have been developed to adapt vision-language models effectively with supervision.
Animal3D: A Comprehensive Dataset of 3D Animal Pose and Shape
Animal3D consists of 3379 images collected from 40 mammal species, high-quality annotations of 26 keypoints, and importantly the pose and shape parameters of the SMAL model.
Ranked #1 on
Animal Pose Estimation
on Animal3D
BDC-Adapter: Brownian Distance Covariance for Better Vision-Language Reasoning
Large-scale pre-trained Vision-Language Models (VLMs), such as CLIP and ALIGN, have introduced a new paradigm for learning transferable visual representations.
Supervised Stochastic Neighbor Embedding Using Contrastive Learning
Stochastic neighbor embedding (SNE) methods $t$-SNE, UMAP are two most popular dimensionality reduction methods for data visualization.
User Simulation with Large Language Models for Evaluating Task-Oriented Dialogue
One of the major impediments to the development of new task-oriented dialogue (TOD) systems is the need for human evaluation at multiple stages and iterations of the development process.
Resilient Model-Free Asymmetric Bipartite Consensus for Nonlinear Multi-Agent Systems against DoS Attacks
In this letter, we study an unified resilient asymmetric bipartite consensus (URABC) problem for nonlinear multi-agent systems with both cooperative and antagonistic interactions under denial-of-service (DoS) attacks.
DeepAdaIn-Net: Deep Adaptive Device-Edge Collaborative Inference for Augmented Reality
Specifically, DeepAdaIn-Net encompasses a partition point selection (PPS) module, a high feature compression learning (HFCL) module, a bandwidth-aware feature configuration (BaFC) module, and a feature consistency compensation (FCC) module.
Privacy-Preserving Encrypted Low-Dose CT Denoising
In this way, the proposed methods can achieve two merits, the data privacy is well protected and the server model is free from the risk of model leakage.
The effect of retirement on healthcare utilization: Evidence from China
We examine the effect of retirement on healthcare utilization in China using longitudinal data.
Learning to Adapt CLIP for Few-Shot Monocular Depth Estimation
When CLIP is used for depth estimation tasks, the patches, divided from the input images, can be combined with a series of semantic descriptions of the depth information to obtain similarity results.
