Search Results for author:
Found 75 papers, 30 papers with code
Efficient PDE-Constrained optimization under high-dimensional uncertainty using derivative-informed neural operators
We propose a novel machine learning framework for solving optimization problems governed by large-scale partial differential equations (PDEs) with high-dimensional random parameters.
PRODIGY: Enabling In-context Learning Over Graphs
In-context learning is the ability of a pretrained model to adapt to novel and diverse downstream tasks by conditioning on prompt examples, without optimizing any parameters.
Cramer-Rao Lower Bound Analysis for OTFS and OFDM Modulation Systems
The orthogonal time frequency space (OTFS) modulation as a promising signal representation attracts growingcinterest for integrated sensing and communication (ISAC), yet its merits over orthogonal frequency division multiplexing (OFDM) remain controversial.
Universal Adversarial Backdoor Attacks to Fool Vertical Federated Learning in Cloud-Edge Collaboration
To this end, we define a threat model for backdoor attacks in VFL and introduce a universal adversarial backdoor (UAB) attack to poison the predictions of VFL.
LiDAR-NeRF: Novel LiDAR View Synthesis via Neural Radiance Fields
To evaluate the effectiveness of our approach, we establish an object-centric multi-view LiDAR dataset, dubbed NeRF-MVL.
Internal Structure Attention Network for Fingerprint Presentation Attack Detection from Optical Coherence Tomography
As a non-invasive optical imaging technique, optical coherence tomography (OCT) has proven promising for automatic fingerprint recognition system (AFRS) applications.
BEVHeight: A Robust Framework for Vision-based Roadside 3D Object Detection
In essence, instead of predicting the pixel-wise depth, we regress the height to the ground to achieve a distance-agnostic formulation to ease the optimization process of camera-only perception methods.
Ranked #1 on
3D Object Detection
on DAIR-V2X-I
DEHRFormer: Real-time Transformer for Depth Estimation and Haze Removal from Varicolored Haze Scenes
Varicolored haze caused by chromatic casts poses haze removal and depth estimation challenges.
A General Visual Representation Guided Framework with Global Affinity for Weakly Supervised Salient Object Detection
Fully supervised salient object detection (SOD) methods have made considerable progress in performance, yet these models rely heavily on expensive pixel-wise labels.
Artificial Intelligence Security Competition (AISC)
The security of artificial intelligence (AI) is an important research area towards safe, reliable, and trustworthy AI systems.
Synthesize Boundaries: A Boundary-aware Self-consistent Framework for Weakly Supervised Salient Object Detection
BAB aims to help predict accurate boundaries, whose input is the synthetic image.
$α$ DARTS Once More: Enhancing Differentiable Architecture Search by Masked Image Modeling
Differentiable architecture search (DARTS) has been a mainstream direction in automatic machine learning.
Low-Cost Beamforming and DOA Estimation Based on One-Bit Reconfigurable Intelligent Surface
In this work, we consider the Direction-of-Arrival (DOA) estimation problem in a low-cost architecture where only one antenna as the receiver is aided by a reconfigurable intelligent surface (RIS).
A Joint Framework Towards Class-aware and Class-agnostic Alignment for Few-shot Segmentation
Few-shot segmentation (FSS) aims to segment objects of unseen classes given only a few annotated support images.
URGLQ: An Efficient Covariance Matrix Reconstruction Method for Robust Adaptive Beamforming
The computational complexity of the conventional adaptive beamformer is relatively large, and the performance degrades significantly due to the model mismatch errors and the unwanted signals in received data.
MSP-Former: Multi-Scale Projection Transformer for Single Image Desnowing
Snow removal causes challenges due to its characteristic of complex degradations.
Derivative-Informed Neural Operator: An Efficient Framework for High-Dimensional Parametric Derivative Learning
We propose derivative-informed neural operators (DINOs), a general family of neural networks to approximate operators as infinite-dimensional mappings from input function spaces to output function spaces or quantities of interest.
Optimal Neural Network Approximation of Wasserstein Gradient Direction via Convex Optimization
We study the variational problem in the family of two-layer networks with squared-ReLU activations, towards which we derive a semi-definite programming (SDP) relaxation.
RIS-ADMM: An ADMM-Based Passive and Sparse Sensing Method with Interference Removal
The reconfigurable intelligent surface (RIS) has been a potential technology for future radar and wireless communication applications.
Scalable Multi-view Clustering with Graph Filtering
With the explosive growth of multi-source data, multi-view clustering has attracted great attention in recent years.
Image Gradient Decomposition for Parallel and Memory-Efficient Ptychographic Reconstruction
In this paper, we propose a novel image gradient decomposition method that significantly reduces the memory footprint for ptychographic reconstruction by tessellating image gradients and diffraction measurements into tiles.
A RIS-Based Vehicle DOA Estimation Method With Integrated Sensing and Communication System
A novel atomic norm-based method is proposed to remove the interference signals by sparse reconstruction, which can improve the DOA estimation efficiently.
Learning Video Salient Object Detection Progressively from Unlabeled Videos
Recent deep learning-based video salient object detection (VSOD) has achieved some breakthrough, but these methods rely on expensive annotated videos with pixel-wise annotations, weak annotations, or part of the pixel-wise annotations.
Reconfigurable Intelligent Surface Aided Sparse DOA Estimation Method With Non-ULA
The direction of arrival (DOA) estimation problem is addressed in this letter.
Efficient DOA Estimation Method for Reconfigurable Intelligent Surfaces Aided UAV Swarm
Specifically, considering the position perturbation of UAVs, a new atomic norm-based DOA estimation method is proposed, where an atomic norm is defined with the parameter of the position perturbation.
SDOAnet: An Efficient Deep Learning-Based DOA Estimation Network for Imperfect Array
Simulation results show that the proposed SDOAnet outperforms the existing DOA estimation methods with the effect of the imperfect array.
Mesa: A Memory-saving Training Framework for Transformers
While Transformers have delivered significant performance improvements, training such networks is extremely memory intensive owing to storing all intermediate activations that are needed for gradient computation during backpropagation, especially for long sequences.
Looper: An end-to-end ML platform for product decisions
Modern software systems and products increasingly rely on machine learning models to make data-driven decisions based on interactions with users, infrastructure and other systems.
Efficient Re-parameterization Residual Attention Network For Nonhomogeneous Image Dehazing
This paper proposes an end-to-end Efficient Re-parameterizationResidual Attention Network(ERRA-Net) to directly restore the nonhomogeneous hazy image.
PermuteFormer: Efficient Relative Position Encoding for Long Sequences
Based on the analysis, we propose PermuteFormer, a Performer-based model with relative position encoding that scales linearly on long sequences.
A SPA-based Manifold Learning Framework for Motor Imagery EEG Data Classification
The electroencephalography (EEG) signal is a non-stationary, stochastic, and highly non-linear bioelectric signal for which achieving high classification accuracy is challenging, especially when the number of subjects is limited.
Smoothed Multi-View Subspace Clustering
In recent years, multi-view subspace clustering has achieved impressive performance due to the exploitation of complementary imformation across multiple views.
ABCNet v2: Adaptive Bezier-Curve Network for Real-time End-to-end Text Spotting
Previous methods can be roughly categorized into two groups: character-based and segmentation-based, which often require character-level annotations and/or complex post-processing due to the unstructured output.
LI-Net: Large-Pose Identity-Preserving Face Reenactment Network
Face reenactment is a challenging task, as it is difficult to maintain accurate expression, pose and identity simultaneously.
Projected Wasserstein gradient descent for high-dimensional Bayesian inference
We propose a projected Wasserstein gradient descent method (pWGD) for high-dimensional Bayesian inference problems.
An efficient method for goal-oriented linear Bayesian optimal experimental design: Application to optimal sensor placemen
Optimal experimental design (OED) plays an important role in the problem of identifying uncertainty with limited experimental data.
Optimization and Control Numerical Analysis Numerical Analysis
$SU(5)$ GUTs with $A_4$ modular symmetry
We combine $SU(5)$ Grand Unified Theories (GUTs) with $A_4$ modular symmetry and present a comprehensive analysis of the resulting quark and lepton mass matrices for all the simplest cases.
High Energy Physics - Phenomenology
Single-path Bit Sharing for Automatic Loss-aware Model Compression
By jointly training the binary gates in conjunction with network parameters, the compression configurations of each layer can be automatically determined.
Explainable Subgraph Reasoning for Forecasting on Temporal Knowledge Graphs
We evaluate our model on four benchmark temporal knowledge graphs for the link forecasting task.
xERTE: Explainable Reasoning on Temporal Knowledge Graphs for Forecasting Future Links
We evaluate our model on four benchmark temporal knowledge graphs for the link forecasting task.
Derivative-Informed Projected Neural Networks for High-Dimensional Parametric Maps Governed by PDEs
We use the projection basis vectors in the active subspace as well as the principal output subspace to construct the weights for the first and last layers of the neural network, respectively.
Fully Quantized Image Super-Resolution Networks
With the rising popularity of intelligent mobile devices, it is of great practical significance to develop accurate, realtime and energy-efficient image Super-Resolution (SR) inference methods.
DyERNIE: Dynamic Evolution of Riemannian Manifold Embeddings for Temporal Knowledge Graph Completion
Product manifolds enable our approach to better reflect a wide variety of geometric structures on temporal KGs.
Tag and Correct: Question aware Open Information Extraction with Two-stage Decoding
The semi-structured answer has two advantages which are more readable and falsifiable compared to span answer.
FATNN: Fast and Accurate Ternary Neural Networks
Ternary Neural Networks (TNNs) have received much attention due to being potentially orders of magnitude faster in inference, as well as more power efficient, than full-precision counterparts.
AQD: Towards Accurate Quantized Object Detection
Network quantization allows inference to be conducted using low-precision arithmetic for improved inference efficiency of deep neural networks on edge devices.
Deep Neural Network-Based Quantized Signal Reconstruction for DOA Estimation
In this letter, a direction of angle (DOA) estimation problem is investigated with low-cost ADC in IRS, and we propose a deep neural network (DNN) as a recovery method for the low-resolution sampled signal.
Predictions from warped flavordynamics based on the $T'$ family group
We propose a realistic theory of fermion masses and mixings using a five-dimensional warped scenario where all fermions propagate in the bulk and the Higgs field is localized on the IR brane.
High Energy Physics - Phenomenology
Argus: Efficient Activity Detection System for Extended Video Analysis
We propose an Efficient Activity Detection System, Argus, for Extended Video Analysis in the surveillance scenario.
Tensor train construction from tensor actions, with application to compression of large high order derivative tensors
We present a method for converting tensors into tensor train format based on actions of the tensor as a vector-valued multilinear function.
Numerical Analysis Numerical Analysis
Projected Stein Variational Gradient Descent
The curse of dimensionality is a longstanding challenge in Bayesian inference in high dimensions.
Training-free Monocular 3D Event Detection System for Traffic Surveillance
To deal with the aforementioned problems, in this paper, we propose a training-free monocular 3D event detection system for traffic surveillance.
Physics-Based Iterative Reconstruction for Dual Source and Flying Focal Spot Computed Tomography
Our algorithm uses precise physics models to reconstruct from the native cone-beam geometry and interleaved dual source helical trajectory of a DS-FFS CT. To do so, we construct a noise physics model to represent data acquisition noise and a prior image model to represent image noise and texture.
Audio-based automatic mating success prediction of giant pandas
Giant pandas, stereotyped as silent animals, make significantly more vocal sounds during breeding season, suggesting that sounds are essential for coordinating their reproduction and expression of mating preference.
One-Shot Imitation Filming of Human Motion Videos
Imitation learning has been applied to mimic the operation of a human cameraman in several autonomous cinematography systems.
Projected Stein Variational Newton: A Fast and Scalable Bayesian Inference Method in High Dimensions
We propose a projected Stein variational Newton (pSVN) method for high-dimensional Bayesian inference.
DLA: Dense-Layer-Analysis for Adversarial Example Detection
In this paper, we present a novel end-to-end framework to detect such attacks during classification without influencing the target model's performance.
A New Atomic Norm for DOA Estimation With Gain-Phase Errors
The problem of direction of arrival (DOA) estimation has been studied for decades as an essential technology in enabling radar, wireless communications, and array signal processing related applications.
Structured Binary Neural Networks for Image Recognition
Experiments on both classification, semantic segmentation and object detection tasks demonstrate the superior performance of the proposed methods over various quantized networks in the literature.
Learning Deep Representations by Mutual Information for Person Re-identification
Most existing person re-identification (ReID) methods have good feature representations to distinguish pedestrians with deep convolutional neural network (CNN) and metric learning methods.
Distinguishing Individual Red Pandas from Their Faces
We are going to release our database and model in the public domain to promote the research on automatic animal identification and particularly on the technique for protecting red pandas.
MAAM: A Morphology-Aware Alignment Model for Unsupervised Bilingual Lexicon Induction
The task of unsupervised bilingual lexicon induction (UBLI) aims to induce word translations from monolingual corpora in two languages.
Dense Procedure Captioning in Narrated Instructional Videos
Understanding narrated instructional videos is important for both research and real-world web applications.
Matryoshka: Fuzzing Deeply Nested Branches
Our evaluation also uncovered the key technique contributing to Matryoshka's impressive performance: it collects only the nesting constraints that may cause the target conditional statements unreachable, which greatly simplifies the constraints that it has to solve.
Cryptography and Security
Giant Panda Face Recognition Using Small Dataset
Cameras have been widely installed in the regions where pandas live.
Knowledgeable Storyteller: A Commonsense-Driven Generative Model for Visual Storytelling
The visual storytelling (VST) task aims at generating a reasonable and coherent paragraph-level story with the image stream as input.
Power Allocation in Multi-User Cellular Networks: Deep Reinforcement Learning Approaches
The model-based power allocation algorithm has been investigated for decades, but it requires the mathematical models to be analytically tractable and it usually has high computational complexity.
Information Theory Information Theory
Power Allocation in Multi-user Cellular Networks With Deep Q Learning Approach
Nowadays, the data-driven model-free machine learning-based approaches are rapidly developed in this field, and among them the deep reinforcement learning (DRL) is proved to be of great promising potential.
Information Theory Information Theory
Style Transfer as Unsupervised Machine Translation
Language style transferring rephrases text with specific stylistic attributes while preserving the original attribute-independent content.
Ranked #3 on
Unsupervised Text Style Transfer
on GYAFC
Question Generation from SQL Queries Improves Neural Semantic Parsing
We study how to learn a semantic parser of state-of-the-art accuracy with less supervised training data.
Off-Grid DOA Estimation Using Sparse Bayesian Learning in MIMO Radar With Unknown Mutual Coupling
With regard to the DOA estimation performance, the proposed SBLMC method can outperform state-of-the-art methods in the MIMO radar with unknown mutual coupling effect, while keeping the acceptable computational complexity.
Angora: Efficient Fuzzing by Principled Search
On the LAVA-M data set, Angora found almost all the injected bugs, found more bugs than any other fuzzer that we compared with, and found eight times as many bugs as the second-best fuzzer in the program who.
Cryptography and Security
Question Generation for Question Answering
This paper presents how to generate questions from given passages using neural networks, where large scale QA pairs are automatically crawled and processed from Community-QA website, and used as training data.
Recurrent Attention Network on Memory for Aspect Sentiment Analysis
We propose a novel framework based on neural networks to identify the sentiment of opinion targets in a comment/review.
