Search Results for author:
Found 99 papers, 49 papers with code
Towards Content-Independent Multi-Reference Super-Resolution: Adaptive Pattern Matching and Feature Aggregation
Recovering realistic textures from a largely down-sampled low resolution (LR) image with complicated patterns is a challenging problem in image super-resolution.
6GAN: IPv6 Multi-Pattern Target Generation via Generative Adversarial Nets with Reinforcement Learning
6GAN forces multiple generators to train with a multi-class discriminator and an alias detector to generate non-aliased active targets with different addressing pattern types.
SiamHAN: IPv6 Address Correlation Attacks on TLS Encrypted Traffic via Siamese Heterogeneous Graph Attention Network
To do this, we propose an IPv6 address correlation model - SiamHAN.
CowClip: Reducing CTR Prediction Model Training Time from 12 hours to 10 minutes on 1 GPU
Our experiments show that previous scaling rules fail in the training of CTR prediction neural networks.
CLMLF:A Contrastive Learning and Multi-Layer Fusion Method for Multimodal Sentiment Detection
Compared with unimodal data, multimodal data can provide more features to help the model analyze the sentiment of data.
CholecTriplet2021: A benchmark challenge for surgical action triplet recognition
In this paper, we present the challenge setup and assessment of the state-of-the-art deep learning methods proposed by the participants during the challenge.
Ranked #1 on
Action Triplet Recognition
on CholecT50 (Challenge)
(using extra training data)
Towards An End-to-End Framework for Flow-Guided Video Inpainting
Optical flow, which captures motion information across frames, is exploited in recent video inpainting methods through propagating pixels along its trajectories.
Ranked #1 on
Video Inpainting
on YouTube-VOS 2018 val
Graph Enhanced Contrastive Learning for Radiology Findings Summarization
To address the limitation, we propose a unified framework for exploiting both extra knowledge and the original findings in an integrated way so that the critical information (i. e., key words and their relations) can be extracted in an appropriate way to facilitate impression generation.
Beyond 3D Siamese Tracking: A Motion-Centric Paradigm for 3D Single Object Tracking in Point Clouds
3D single object tracking (3D SOT) in LiDAR point clouds plays a crucial role in autonomous driving.
X-Trans2Cap: Cross-Modal Knowledge Transfer using Transformer for 3D Dense Captioning
Thus, a more faithful caption can be generated only using point clouds during the inference.
ET-BERT: A Contextualized Datagram Representation with Pre-training Transformers for Encrypted Traffic Classification
In this paper, we propose a new traffic representation model called Encrypted Traffic Bidirectional Encoder Representations from Transformer (ET-BERT), which pre-trains deep contextualized datagram-level representation from large-scale unlabeled data.
RoPGen: Towards Robust Code Authorship Attribution via Automatic Coding Style Transformation
Recent studies show that current source code authorship attribution methods can be compromised by attackers exploiting adversarial examples and coding style manipulation.
HEAM: High-Efficiency Approximate Multiplier Optimization for Deep Neural Networks
We propose an optimization method for the automatic design of approximate multipliers, which minimizes the average error according to the operand distributions.
Heuristic Search for Rank Aggregation with Application to Label Ranking
Rank aggregation aims to combine the preference rankings of a number of alternatives from different voters into a single consensus ranking.
CLEVR3D: Compositional Language and Elementary Visual Reasoning for Question Answering in 3D Real-World Scenes
To tackle this problem, the first VQA-3D dataset, namely CLEVR3D, is proposed, which contains 60K questions in 1, 129 real-world scenes.
CO2Sum:Contrastive Learning for Factual-Consistent Abstractive Summarization
We propose CO2Sum (Contrastive for Consistency), a contrastive learning scheme that can be easily applied on sequence-to-sequence models for factual-consistent abstractive summarization, proving that the model can be fact-aware without modifying the architecture.
Active Learning for Event Extraction with Memory-based Loss Prediction Model
During the selection process, we use an internal-external sample loss ranking method to evaluate the sample importance by using local information.
Advancing COVID-19 Diagnosis with Privacy-Preserving Collaboration in Artificial Intelligence
Artificial intelligence (AI) provides a promising substitution for streamlining COVID-19 diagnoses.
Rapid Assessments of Light-Duty Gasoline Vehicle Emissions Using On-Road Remote Sensing and Machine Learning
Our results show that the ORRS measurements, assisted by the machine-learning-based ensemble model developed here, can realize day-to-day supervision of on-road vehicle-specific emissions.
Medical-VLBERT: Medical Visual Language BERT for COVID-19 CT Report Generation With Alternate Learning
Medical imaging technologies, including computed tomography (CT) or chest X-Ray (CXR), are largely employed to facilitate the diagnosis of the COVID-19.
Box-Aware Feature Enhancement for Single Object Tracking on Point Clouds
Current 3D single object tracking approaches track the target based on a feature comparison between the target template and the search area.
Colorectal Polyp Classification from White-light Colonoscopy Images via Domain Alignment
Thus, we propose a novel framework based on a teacher-student architecture for the accurate colorectal polyp classification (CPC) through directly using white-light (WL) colonoscopy images in the examination.
Shallow Feature Matters for Weakly Supervised Object Localization
In practice, our SPOL model first generates the CAMs through a novel element-wise multiplication of shallow and deep feature maps, which filters the background noise and generates sharper boundaries robustly.
Towards Making Deep Learning-based Vulnerability Detectors Robust
Automatically detecting software vulnerabilities in source code is an important problem that has attracted much attention.
Shallow Attention Network for Polyp Segmentation
To address the above issues, we propose the Shallow Attention Network (SANet) for polyp segmentation.
Ranked #8 on
Video Polyp Segmentation
on SUN-SEG-Easy
Inverse Problem of Nonlinear Schrödinger Equation as Learning of Convolutional Neural Network
In this work, we use an explainable convolutional neural network (NLS-Net) to solve an inverse problem of the nonlinear Schr\"odinger equation, which is widely used in fiber-optic communications.
Don't Take It Literally: An Edit-Invariant Sequence Loss for Text Generation
Such training objective is sub-optimal when the target sequence is not perfect, e. g., when the target sequence is corrupted with noises, or when only weak sequence supervision is available.
Multi-Compound Transformer for Accurate Biomedical Image Segmentation
The recent vision transformer(i. e. for image classification) learns non-local attentive interaction of different patch tokens.
An error analysis of generative adversarial networks for learning distributions
This paper studies how well generative adversarial networks (GANs) learn probability distributions from finite samples.
CARLS: Cross-platform Asynchronous Representation Learning System
In this work, we propose CARLS, a novel framework for augmenting the capacity of existing deep learning frameworks by enabling multiple components -- model trainers, knowledge makers and knowledge banks -- to concertedly work together in an asynchronous fashion across hardware platforms.
Combining Supervised and Un-supervised Learning for Automatic Citrus Segmentation
Compared with most of the existing citrus segmentation methods, our method uses a small amount of supervised data and a large number of unsupervised data, while learning the pixel level location information and the temporal information of citrus changes to enhance the segmentation effect.
PointLIE: Locally Invertible Embedding for Point Cloud Sampling and Recovery
In this paper, we address a fundamental problem in PCSR: How to downsample the dense point cloud with arbitrary scales while preserving the local topology of discarding points in a case-agnostic manner (i. e. without additional storage for point relationship)?
Temporal Modulation Network for Controllable Space-Time Video Super-Resolution
To well exploit the temporal information, we propose a Locally-temporal Feature Comparison (LFC) module, along with the Bi-directional Deformable ConvLSTM, to extract short-term and long-term motion cues in videos.
Free-form Description Guided 3D Visual Graph Network for Object Grounding in Point Cloud
There are three main challenges in 3D object grounding: to find the main focus in the complex and diverse description; to understand the point cloud scene; and to locate the target object.
InstanceRefer: Cooperative Holistic Understanding for Visual Grounding on Point Clouds through Instance Multi-level Contextual Referring
Compared with the visual grounding on 2D images, the natural-language-guided 3D object localization on point clouds is more challenging.
Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision
In this paper, we leverage a noisy dataset of over one billion image alt-text pairs, obtained without expensive filtering or post-processing steps in the Conceptual Captions dataset.
Ranked #1 on
Image Classification
on VTAB-1k
(using extra training data)
On the capacity of deep generative networks for approximating distributions
Furthermore, it is shown that the approximation error in Wasserstein distance grows at most linearly on the ambient dimension and that the approximation order only depends on the intrinsic dimension of the target distribution.
GAKP: GRU Association and Kalman Prediction for Multiple Object Tracking
Multiple Object Tracking (MOT) has been a useful yet challenging task in many real-world applications such as video surveillance, intelligent retail, and smart city.
Operator learning for predicting multiscale bubble growth dynamics
Simulating and predicting multiscale problems that couple multiple physics and dynamics across many orders of spatiotemporal scales is a great challenge that has not been investigated systematically by deep neural networks (DNNs).
Computational Physics
Formal modeling and performance evaluation for hybrid systems:a probabilistic hybrid process algebra-based approach
After that, we present a performance evaluation language, CTRML, to reason over probabilistic systems, which extend the results to real number.
Formal Languages and Automata Theory F.4.3
Hierarchically nanostructured thermoelectric materials: Challenges and opportunities for improved power factors
Central to this ZT improvement is the drastic reduction in the material thermal conductivity due to the scattering of phonons on the numerous interfaces, boundaries, dislocations, point defects, phases, etc., which are purposely included.
Materials Science
Sparse Single Sweep LiDAR Point Cloud Segmentation via Learning Contextual Shape Priors from Scene Completion
In practice, an initial semantic segmentation (SS) of a single sweep point cloud can be achieved by any appealing network and then flows into the semantic scene completion (SSC) module as the input.
Ranked #2 on
3D Semantic Scene Completion
on SemanticKITTI
3D Semantic Scene Completion from a single RGB image
Autonomous Driving
+2
DeepSIM: GPS Spoofing Detection on UAVs using Satellite Imagery Matching
To detect GPS spoofing attacks, we investigate different deep neural network models that compare the real-time camera images with the historical satellite images.
Hierarchical Chinese Legal event extraction via Pedal Attention Mechanism
We label a Chinese legal event dataset and evaluate our model on it.
CN-HIT-MI.T at SemEval-2020 Task 8: Memotion Analysis Based on BERT
Internet memes emotion recognition is focused by many researchers.
SelfText Beyond Polygon: Unconstrained Text Detection with Box Supervision and Dynamic Self-Training
Although a polygon is a more accurate representation than an upright bounding box for text detection, the annotations of polygons are extremely expensive and challenging.
Delving Deep into Label Smoothing
Experiments demonstrate that based on the same classification models, the proposed approach can effectively improve the classification performance on CIFAR-100, ImageNet, and fine-grained datasets.
Multi-Modal Active Learning for Automatic Liver Fibrosis Diagnosis based on Ultrasound Shear Wave Elastography
With the development of radiomics, noninvasive diagnosis like ultrasound (US) imaging plays a very important role in automatic liver fibrosis diagnosis (ALFD).
Where to Look and How to Describe: Fashion Image Retrieval with an Attentional Heterogeneous Bilinear Network
Fashion products typically feature in compositions of a variety of styles at different clothing parts.
MedDG: A Large-scale Medical Consultation Dataset for Building Medical Dialogue System
To push forward the future research on building expert-sensitive medical dialogue system, we proposes two kinds of medical dialogue tasks based on MedDG dataset.
UXNet: Searching Multi-level Feature Aggregation for 3D Medical Image Segmentation
Unlike the recent neural architecture search (NAS) methods that typically searched the optimal operators in each network layer, but missed a good strategy to search for feature aggregations, this paper proposes a novel NAS method for 3D medical image segmentation, named UXNet, which searches both the scale-wise feature aggregation strategies as well as the block-wise operators in the encoder-decoder network.
Ultrasound Liver Fibrosis Diagnosis using Multi-indicator guided Deep Neural Networks
An indicator-guided learning mechanism is further proposed to ease the training of the proposed model.
Diagnosing Concept Drift with Visual Analytics
Concept drift is a phenomenon in which the distribution of a data stream changes over time in unforeseen ways, causing prediction models built on historical data to become inaccurate.
IllumiNet: Transferring Illumination from Planar Surfaces to Virtual Objects in Augmented Reality
This paper presents an illumination estimation method for virtual objects in real environment by learning.
Interactive Knowledge Distillation
Knowledge distillation is a standard teacher-student learning framework to train a light-weight student network under the guidance of a well-trained large teacher network.
A Robust Attentional Framework for License Plate Recognition in the Wild
On the other hand, the 2D attentional based license plate recognizer with an Xception-based CNN encoder is capable of recognizing license plates with different patterns under various scenarios accurately and robustly.
Approximation in shift-invariant spaces with deep ReLU neural networks
We also give lower bounds of the $L^p (1\le p \le \infty)$ approximation error for Sobolev spaces, which show that our construction of neural network is asymptotically optimal up to a logarithmic factor.
Exemplar Normalization for Learning Deep Representation
This work investigates a novel dynamic learning-to-normalize (L2N) problem by proposing Exemplar Normalization (EN), which is able to learn different normalization methods for different convolutional layers and image samples of a deep network.
Unifying Specialist Image Embedding into Universal Image Embedding
Therefore, we propose to distill the knowledge in multiple specialists into a universal embedding to solve this problem.
PointASNL: Robust Point Clouds Processing using Nonlocal Neural Networks with Adaptive Sampling
Extensive experiments verify the robustness and superiority of our approach in point clouds processing tasks regardless of synthesis data, indoor data, and outdoor data with or without noise.
Automated classification of stems and leaves of potted plants based on point cloud data
A classification method was proposed to classify the leaves and stems of potted plants automatically based on the point cloud data of the plants, which is a nondestructive acquisition.
BARNet: Bilinear Attention Network with Adaptive Receptive Fields for Surgical Instrument Segmentation
For the scale variation, our adaptive receptive field module aggregates multi-scale features and automatically fuses them with different weights.
$μ$VulDeePecker: A Deep Learning-Based System for Multiclass Vulnerability Detection
Existing vulnerability detection methods based on deep learning can detect the presence of vulnerabilities (i. e., addressing the binary classification or detection problem), but cannot pinpoint types of vulnerabilities (i. e., incapable of addressing multiclass classification).
Progressive Learning Algorithm for Efficient Person Re-Identification
This paper studies the problem of Person Re-Identification (ReID)for large-scale applications.
Attention-Guided Lightweight Network for Real-Time Segmentation of Robotic Surgical Instruments
LWANet adopts encoder-decoder architecture, where the encoder is the lightweight network MobileNetV2, and the decoder consists of depthwise separable convolution, attention fusion block, and transposed convolution.
RAUNet: Residual Attention U-Net for Semantic Segmentation of Cataract Surgical Instruments
To the best of our knowledge, this is the first cataract surgical instrument dataset for semantic segmentation.
PPINN: Parareal Physics-Informed Neural Network for time-dependent PDEs
Consequently, compared to the original PINN approach, the proposed PPINN approach may achieve a significant speedup for long-time integration of PDEs, assuming that the CG solver is fast and can provide reasonable predictions of the solution, hence aiding the PPINN solution to converge in just a few iterations.
Molecule Property Prediction Based on Spatial Graph Embedding
And, multiple C-SGELs are stacked to construct a convolution spatial graph embedding network (C-SGEN) for end-to-end representation learning.
Ranked #2 on
Graph Regression
on Lipophilicity
Semi-Supervised Video Salient Object Detection Using Pseudo-Labels
Specifically, we present an effective video saliency detector that consists of a spatial refinement network and a spatiotemporal module.
Ranked #1 on
Video Salient Object Detection
on VOS-T
(using extra training data)
Salient Object Detection
Unsupervised Video Object Segmentation
+1
Convergence Rates of Posterior Distributions in Markov Decision Process
In this paper, we show the convergence rates of posterior distributions of the model dynamics in a MDP for both episodic and continuous tasks.
Gated Multiple Feedback Network for Image Super-Resolution
The rapid development of deep learning (DL) has driven single image super-resolution (SR) into a new era.
Ranked #11 on
Image Super-Resolution
on Manga109 - 4x upscaling
Influence of Boundaries and Thermostatting on Nonequilibrium Molecular Dynamics Simulations of Heat Conduction in Solids
Conventionally, the thermal conductivity of a finite system is calculated as the ratio between the heat flux and the temperature gradient extracted from the linear part of the temperature profile away from the local thermostats.
Mesoscale and Nanoscale Physics Statistical Mechanics Computational Physics
Efficient hinging hyperplanes neural network and its application in nonlinear system identification
It is proved that for every EHH neural network, there is an equivalent adaptive hinging hyperplanes (AHH) tree, which was also proposed based on the model of HH and find good applications in system identification.
A Holistic Representation Guided Attention Network for Scene Text Recognition
In this work, we propose a simple yet strong approach for scene text recognition.
A GPU-accelerated package for simulation of flow in nanoporous source rocks with many-body dissipative particle dynamics
Lastly, we demonstrate, through a flow simulation in realistic shale pores, that the CPU counterpart requires 840 Power9 cores to rival the performance delivered by our package with four V100 GPUs on ORNL's Summit architecture.
Computational Physics
Feedback Network for Image Super-Resolution
In this paper, we propose an image super-resolution feedback network (SRFBN) to refine low-level representations with high-level information.
Ranked #3 on
Image Super-Resolution
on Manga109 - 3x upscaling
Graph-RISE: Graph-Regularized Image Semantic Embedding
Learning image representations to capture fine-grained semantics has been a challenging and important task enabling many applications such as image search and clustering.
Ranked #8 on
Image Classification
on iNaturalist
Thompson Sampling for Pursuit-Evasion Problems
We propose a variant of Thompson Sampling for pursuit-evasion that allows for the application of existing model-based planning algorithms.
Nonlocal flocking dynamics: Learning the fractional order of PDEs from particle simulations
Instead of specifying the fPDEs with an ad hoc fractional order for nonlocal flocking dynamics, we learn the effective nonlocal influence function in fPDEs directly from particle trajectories generated by the agent-based simulations.
Multivariate Density Estimation with Missing Data
Multivariate density estimation is a popular technique in statistics with wide applications including regression models allowing for heteroskedasticity in conditional variances.
Methodology
SySeVR: A Framework for Using Deep Learning to Detect Software Vulnerabilities
Our experiments with 4 software products demonstrate the usefulness of the framework: we detect 15 vulnerabilities that are not reported in the National Vulnerability Database.
Deep Neural Nets with Interpolating Function as Output Activation
We replace the output layer of deep neural nets, typically the softmax function, by a novel interpolating function.
VulDeePecker: A Deep Learning-Based System for Vulnerability Detection
Since deep learning is motivated to deal with problems that are very different from the problem of vulnerability detection, we need some guiding principles for applying deep learning to vulnerability detection.
Knowledge Concentration: Learning 100K Object Classifiers in a Single CNN
To address these challenges, we propose a Knowledge Concentration method, which effectively transfers the knowledge from dozens of specialists (multiple teacher networks) into one single model (one student network) to classify 100K object categories.
Understanding Hidden Memories of Recurrent Neural Networks
We propose a technique to explain the function of individual hidden state units based on their expected response to input texts.
High-Resolution Shape Completion Using Deep Neural Networks for Global Structure and Local Geometry Inference
Our method is based on a new deep learning architecture consisting of two sub-networks: a global structure inference network and a local geometry refinement network.
Folding membrane proteins by deep transfer learning
Computational elucidation of membrane protein (MP) structures is challenging partially due to lack of sufficient solved structures for homology modeling.
A Flow Model of Neural Networks
Based on a natural connection between ResNet and transport equation or its characteristic equation, we propose a continuous flow model for both ResNet and plain net.
Learning Gaussian Graphical Models Using Discriminated Hub Graphical Lasso
When no hubs are known, we use Graphical Lasso (GL) to provide information of hubs and find that the performance of DHGL will always be better than HGL if correct prior information is given and will seldom degenerate when the prior information is wrong.
Predicting membrane protein contacts from non-membrane proteins by deep transfer learning
Tested on 510 non-redundant MPs, our deep model (learned from only non-MPs) has top L/10 long-range contact prediction accuracy 0. 69, better than our deep model trained by only MPs (0. 63) and much better than a representative DCA method CCMpred (0. 47) and the CASP11 winner MetaPSICOV (0. 55).
GPU-accelerated Red Blood Cells Simulations with Transport Dissipative Particle Dynamics
We observe a speedup of 10. 1 on one GPU over all 16 cores within a single node, and a weak scaling efficiency of 91% across 256 nodes.
Computational Physics Biological Physics
Accurate De Novo Prediction of Protein Contact Map by Ultra-Deep Learning Model
Using our predicted contacts as restraints, we can (ab initio) fold 208 of the 398 membrane proteins with TMscore>0. 5.
Protein Secondary Structure Prediction Using Cascaded Convolutional and Recurrent Neural Networks
Inspired by the recent successes of deep neural networks, in this paper, we propose an end-to-end deep network that predicts protein secondary structures from integrated local and global contextual features.
Towards Better Analysis of Deep Convolutional Neural Networks
Deep convolutional neural networks (CNNs) have achieved breakthrough performance in many pattern recognition tasks such as image classification.
LSTM-CF: Unifying Context Modeling and Fusion with LSTMs for RGB-D Scene Labeling
Another long short-term memorized fusion layer is set up to integrate the contexts along the vertical direction from different channels, and perform bi-directional propagation of the fused vertical contexts along the horizontal direction to obtain true 2D global contexts.
Blockout: Dynamic Model Selection for Hierarchical Deep Networks
Most deep architectures for image classification--even those that are trained to classify a large number of diverse categories--learn shared image representations with a single model.
Learning Semantic Relationships for Better Action Retrieval in Images
Human actions capture a wide variety of interactions between people and objects.
Learning Locally-Adaptive Decision Functions for Person Verification
This paper proposes to learn a decision function for verification that can be viewed as a joint model of a distance metric and a locally adaptive thresholding rule.
Learning to Search Efficiently in High Dimensions
Traditional approaches relied on algorithmic constructions that are often data independent (such as Locality Sensitive Hashing) or weakly dependent (such as kd-trees, k-means trees).
