Search Results for author:
Found 95 papers, 32 papers with code
Sequence-aware Pre-training for Echocardiography Probe Guidance
Specifically, our approach learns personalized 2D and 3D cardiac structural features by predicting the masked-out images and actions in a scanning sequence.
AdapMoE: Adaptive Sensitivity-based Expert Gating and Management for Efficient MoE Inference
Mixture-of-Experts (MoE) models are designed to enhance the efficiency of large language models (LLMs) without proportionally increasing the computational demands.
HG-PIPE: Vision Transformer Acceleration with Hybrid-Grained Pipeline
With a VCK190 FPGA, HG-PIPE realizes end-to-end ViT acceleration on a single device and achieves 7118 images/s, which is 2. 81 times faster than a V100 GPU.
Real-Time Summarization of Twitter
In this paper, we describe our approaches to TREC Real-Time Summarization of Twitter.
Structure-aware World Model for Probe Guidance via Large-scale Self-supervised Pre-train
The complex structure of the heart leads to significant challenges in echocardiography, especially in acquisition cardiac ultrasound images.
Online Learning of Multiple Tasks and Their Relationships : Testing on Spam Email Data and EEG Signals Recorded in Construction Fields
This paper examines an online multi-task learning (OMTL) method, which processes data sequentially to predict labels across related tasks.
Cardiac Copilot: Automatic Probe Guidance for Echocardiography with World Model
However, there is a severe shortage of experienced cardiac sonographers, due to the heart's complex structure and significant operational challenges.
Insect Diversity Estimation in Polarimetric Lidar
Identification of insects in flight is a particular challenge for ecologists in several settings with no other method able to count and classify insects at the pace of entomological lidar.
FastQuery: Communication-efficient Embedding Table Query for Private LLM Inference
We observe the overhead mainly comes from the neglect of 1) the one-hot nature of user queries and 2) the robustness of the embedding table to low bit-width quantization noise.
PrivCirNet: Efficient Private Inference via Block Circulant Transformation
At the protocol level, PrivCirNet customizes the HE encoding algorithm that is fully compatible with the block circulant transformation and reduces the computation latency in proportion to the block size.
DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model
MLA guarantees efficient inference through significantly compressing the Key-Value (KV) cache into a latent vector, while DeepSeekMoE enables training strong models at an economical cost through sparse computation.
Stochastic Multivariate Universal-Radix Finite-State Machine: a Theoretically and Practically Elegant Nonlinear Function Approximator
Nonlinearities are crucial for capturing complex input-output relationships especially in deep neural networks.
vMCU: Coordinated Memory Management and Kernel Optimization for DNN Inference on MCUs
The key idea is to virtualize the limited memory of MCU as a large memory pool.
Evaluating Concept-based Explanations of Language Models: A Study on Faithfulness and Readability
Based on this, we quantify faithfulness via the difference in the output upon perturbation.
Operators' cognitive performance under extreme hot-humid exposure and its physiological-psychological mechanism based on ECG, fNIRS, and Eye Tracking
The best performance in a suitable environment was due to more effective activation in the prefrontal cortex (PFC).
ProPD: Dynamic Token Tree Pruning and Generation for LLM Parallel Decoding
Additionally, it introduces a dynamic token tree generation algorithm to balance the computation and parallelism of the verification phase in real-time and maximize the overall efficiency across different batch sizes, sequence lengths, and tasks, etc.
ASCEND: Accurate yet Efficient End-to-End Stochastic Computing Acceleration of Vision Transformer
To overcome the compatibility challenges, ASCEND proposes a novel deterministic SC block for GELU and leverages an SC-friendly iterative approximate algorithm to design an accurate and efficient softmax circuit.
BrainWave: A Brain Signal Foundation Model for Clinical Applications
Neural electrical activity is fundamental to brain function, underlying a range of cognitive and behavioral processes, including movement, perception, decision-making, and consciousness.
HEQuant: Marrying Homomorphic Encryption and Quantization for Communication-Efficient Private Inference
Compared with prior-art HE-based protocols, e. g., CrypTFlow2, Cheetah, Iron, etc, HEQuant achieves $3. 5\sim 23. 4\times$ communication reduction and $3. 0\sim 9. 3\times$ latency reduction.
DenseNet and Support Vector Machine classifications of major depressive disorder using vertex-wise cortical features
Based on the hypothesis that integration of vertex-wise cortical features can improve classification performance, we evaluated the classification of a DenseNet and a Support Vector Machine (SVM), with the expectation that the former would outperform the latter.
Zero-knowledge Proof Meets Machine Learning in Verifiability: A Survey
However, in practice, due to various challenges such as limited computational resources and data privacy concerns, users in need of models often cannot train machine learning models locally.
Distractor-aware Event-based Tracking
We demonstrate that our tracker has superior performance against the state-of-the-art trackers in terms of both accuracy and efficiency.
High Visual-Fidelity Learned Video Compression
With the growing demand for video applications, many advanced learned video compression methods have been developed, outperforming traditional methods in terms of objective quality metrics such as PSNR.
TransCC: Transformer Network for Coronary Artery CCTA Segmentation
The accurate segmentation of Coronary Computed Tomography Angiography (CCTA) images holds substantial clinical value for the early detection and treatment of Coronary Heart Disease (CHD).
Memory-aware Scheduling for Complex Wired Networks with Iterative Graph Optimization
Memory-aware network scheduling is becoming increasingly important for deep neural network (DNN) inference on resource-constrained devices.
Falcon: Accelerating Homomorphically Encrypted Convolutions for Efficient Private Mobile Network Inference
Efficient networks, e. g., MobileNetV2, EfficientNet, etc, achieves state-of-the-art (SOTA) accuracy with lightweight computation.
Stroke Extraction of Chinese Character Based on Deep Structure Deformable Image Registration
In this paper, we propose a deep learning-based character stroke extraction method that takes semantic features and prior information of strokes into consideration.
Mixture-of-Supernets: Improving Weight-Sharing Supernet Training with Architecture-Routed Mixture-of-Experts
In NLP tasks like machine translation and pre-trained language modeling, there is a significant performance gap between supernet and training from scratch for the same model architecture, necessitating retraining post optimal architecture identification.
Frame-Event Alignment and Fusion Network for High Frame Rate Tracking
The alignment module is responsible for cross-style and cross-frame-rate alignment between frame and event modalities under the guidance of the moving cues furnished by events.
ALT: An Automatic System for Long Tail Scenario Modeling
In this paper, we consider the problem of long tail scenario modeling with budget limitation, i. e., insufficient human resources for model training stage and limited time and computing resources for model inference stage.
EBSR: Enhanced Binary Neural Network for Image Super-Resolution
While the performance of deep convolutional neural networks for image super-resolution (SR) has improved significantly, the rapid increase of memory and computation requirements hinders their deployment on resource-constrained devices.
${S}^{2}$Net: Accurate Panorama Depth Estimation on Spherical Surface
In this paper, we propose an end-to-end deep network for monocular panorama depth estimation on a unit spherical surface.
End to End Generative Meta Curriculum Learning For Medical Data Augmentation
The teacher learns to generate curriculum to feed into the student model for data augmentation and guides the student to improve performance in a meta-learning style.
Conditioned Generative Transformers for Histopathology Image Synthetic Augmentation
Extensive experiments on the histopathology datasets show that leveraging our synthetic augmentation framework results in significant and consistent improvements in classification performance.
PathFusion: Path-consistent Lidar-Camera Deep Feature Fusion
Fusing 3D LiDAR features with 2D camera features is a promising technique for enhancing the accuracy of 3D detection, thanks to their complementary physical properties.
MPCViT: Searching for Accurate and Efficient MPC-Friendly Vision Transformer with Heterogeneous Attention
Secure multi-party computation (MPC) enables computation directly on encrypted data and protects both data and model privacy in deep learning inference.
The solution set of fuzzy relation equations with addition-min composition
This paper deals with the resolutions of fuzzy relation equations with addition-min composition.
Multilevel Transformer For Multimodal Emotion Recognition
Inspired by Transformer TTS, we propose a multilevel transformer model to perform fine-grained multimodal emotion recognition.
Few-Shot Class-Incremental Learning from an Open-Set Perspective
The continual appearance of new objects in the visual world poses considerable challenges for current deep learning methods in real-world deployments.
Content-oriented learned image compression
In recent years, with the development of deep neural networks, end-to-end optimized image compression has made significant progress and exceeded the classic methods in terms of rate-distortion performance.
Multi-site benchmark classification of major depressive disorder using machine learning on cortical and subcortical measures
Machine learning (ML) techniques have gained popularity in the neuroimaging field due to their potential for classifying neuropsychiatric disorders.
DepthShrinker: A New Compression Paradigm Towards Boosting Real-Hardware Efficiency of Compact Neural Networks
Efficient deep neural network (DNN) models equipped with compact operators (e. g., depthwise convolutions) have shown great potential in reducing DNNs' theoretical complexity (e. g., the total number of weights/operations) while maintaining a decent model accuracy.
BiT: Robustly Binarized Multi-distilled Transformer
Modern pre-trained transformers have rapidly advanced the state-of-the-art in machine learning, but have also grown in parameters and computational complexity, making them increasingly difficult to deploy in resource-constrained environments.
SplitNets: Designing Neural Architectures for Efficient Distributed Computing on Head-Mounted Systems
We design deep neural networks (DNNs) and corresponding networks' splittings to distribute DNNs' workload to camera sensors and a centralized aggregator on head mounted devices to meet system performance targets in inference accuracy and latency under the given hardware resource constraints.
Resilience-Motivated Distribution System Restoration Considering Electricity-Water-Gas Interdependency
In this paper, a distribution system service restoration method considering the electricity-water-gas interdependency is proposed.
Decentralized Unsupervised Learning of Visual Representations
To tackle this problem, we propose a collaborative contrastive learning framework consisting of two approaches: feature fusion and neighborhood matching, by which a unified feature space among clients is learned for better data representations.
PyTorchVideo: A Deep Learning Library for Video Understanding
We introduce PyTorchVideo, an open-source deep-learning library that provides a rich set of modular, efficient, and reproducible components for a variety of video understanding tasks, including classification, detection, self-supervised learning, and low-level processing.
Low-Rank+Sparse Tensor Compression for Neural Networks
Low-rank tensor compression has been proposed as a promising approach to reduce the memory and compute requirements of neural networks for their deployment on edge devices.
Multi-Scale High-Resolution Vision Transformer for Semantic Segmentation
Therefore, we propose HRViT, which enhances ViTs to learn semantically-rich and spatially-precise multi-scale representations by integrating high-resolution multi-branch architectures with ViTs.
Ranked #25 on
Semantic Segmentation
on Cityscapes val
LSTM-RPA: A Simple but Effective Long Sequence Prediction Algorithm for Music Popularity Prediction
The traditional trend prediction models can better predict the short trend than the long trend.
Omni-sparsity DNN: Fast Sparsity Optimization for On-Device Streaming E2E ASR via Supernet
From wearables to powerful smart devices, modern automatic speech recognition (ASR) models run on a variety of edge devices with different computational budgets.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Contrastive Quant: Quantization Makes Stronger Contrastive Learning
Contrastive learning, which learns visual representations by enforcing feature consistency under different augmented views, has emerged as one of the most effective unsupervised learning methods.
Federated Contrastive Representation Learning with Feature Fusion and Neighborhood Matching
Federated learning (FL) enables distributed clients to learn a shared model for prediction while keeping the training data local on each client.
NASViT: Neural Architecture Search for Efficient Vision Transformers with Gradient Conflict aware Supernet Training
In this work, we observe that the poor performance is due to a gradient conflict issue: the gradients of different sub-networks conflict with that of the supernet more severely in ViTs than CNNs, which leads to early saturation in training and inferior convergence.
Ranked #7 on
Neural Architecture Search
on ImageNet
Noisy Training Improves E2E ASR for the Edge
We apply noisy training to improve both dense and sparse state-of-the-art Emformer models and observe consistent WER reduction.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
A Rigid Registration Method in TEVAR
Since the mapping relationship between definitized intra-interventional X-ray and undefined pre-interventional Computed Tomography(CT) is uncertain, auxiliary positioning devices or body markers, such as medical implants, are commonly used to determine this relationship.
Vision Transformers with Patch Diversification
To alleviate this problem, in this work, we introduce novel loss functions in vision transformer training to explicitly encourage diversity across patch representations for more discriminative feature extraction.
Ranked #20 on
Semantic Segmentation
on Cityscapes val
Incorporating VAD into ASR System by Multi-task Learning
When we use End-to-end automatic speech recognition (E2E-ASR) system for real-world applications, a voice activity detection (VAD) system is usually needed to improve the performance and to reduce the computational cost by discarding non-speech parts in the audio.
AlphaNet: Improved Training of Supernets with Alpha-Divergence
Weight-sharing NAS builds a supernet that assembles all the architectures as its sub-networks and jointly trains the supernet with the sub-networks.
Ranked #12 on
Neural Architecture Search
on ImageNet
Aggregate Modeling and Equilibrium Analysis of the Crowdsourcing Market for Autonomous Vehicles
We call such a mobility market with AV renting options the "AV crowdsourcing market".
CPT: Efficient Deep Neural Network Training via Cyclic Precision
In this paper, we attempt to explore low-precision training from a new perspective as inspired by recent findings in understanding DNN training: we conjecture that DNNs' precision might have a similar effect as the learning rate during DNN training, and advocate dynamic precision along the training trajectory for further boosting the time/energy efficiency of DNN training.
Electronic transport properties and hydrostatic pressure effect of FeSe$_{0.67}$Te$_{0.33}$ single crystals free of phase separation
FeSe$_{1-x}$Te$_{x}$ superconductors manifest some intriguing electronic properties depending on the value of $x$.
Superconductivity Materials Science
SID: Incremental Learning for Anchor-Free Object Detection via Selective and Inter-Related Distillation
Incremental learning requires a model to continually learn new tasks from streaming data.
Exploring wav2vec 2.0 on speaker verification and language identification
Then we demonstrate the effectiveness of wav2vec 2. 0 on the two tasks respectively.
ScaleNAS: One-Shot Learning of Scale-Aware Representations for Visual Recognition
We use ScaleNAS to create high-resolution models for two different tasks, ScaleNet-P for human pose estimation and ScaleNet-S for semantic segmentation.
Ranked #5 on
Multi-Person Pose Estimation
on COCO test-dev
Equivalence of Convergence Rates of Posterior Distributions and Bayes Estimators for Functions and Nonparametric Functionals
For a general class of kernels, we establish convergence rates of the posterior measure of the regression function and its derivatives, which are both minimax optimal up to a logarithmic factor for functions in certain classes.
KeepAugment: A Simple Information-Preserving Data Augmentation Approach
Data augmentation (DA) is an essential technique for training state-of-the-art deep learning systems.
AttentiveNAS: Improving Neural Architecture Search via Attentive Sampling
Our discovered model family, AttentiveNAS models, achieves top-1 accuracy from 77. 3% to 80. 7% on ImageNet, and outperforms SOTA models, including BigNAS and Once-for-All networks.
Ranked #21 on
Neural Architecture Search
on ImageNet
DNA: Differentiable Network-Accelerator Co-Search
Powerful yet complex deep neural networks (DNNs) have fueled a booming demand for efficient DNN solutions to bring DNN-powered intelligence into numerous applications.
Towards High-Performance Solid-State-LiDAR-Inertial Odometry and Mapping
LiLi-OM (Livox LiDAR-inertial odometry and mapping) is real-time capable and achieves superior accuracy over state-of-the-art systems for both LiDAR types on public data sets of mechanical LiDARs and in experiments using the Livox Horizon.
Robotics
NASGEM: Neural Architecture Search via Graph Embedding Method
To preserve graph correlation information in encoding, we propose NASGEM which stands for Neural Architecture Search via Graph Embedding Method.
SACNN: Self-Attention Convolutional Neural Network for Low-Dose CT Denoising With Self-Supervised Perceptual Loss Network
We combine these two methods and demonstrate their effectiveness on both CNN-based neural networks and WGAN-based neural networks with comprehensive experiments.
Functional Group Bridge for Simultaneous Regression and Support Estimation
In particular, we show that the estimated coefficient functions are rate optimal in the minimax sense under the $L_2$ norm and resemble a phase transition phenomenon.
Methodology Statistics Theory Statistics Theory
On the Estimation of Derivatives Using Plug-in Kernel Ridge Regression Estimators
We study the problem of estimating the derivatives of a regression function, which has a wide range of applications as a key nonparametric functional of unknown functions.
Multi-branch and Multi-scale Attention Learning for Fine-Grained Visual Categorization
Therefore, our multi-branch and multi-scale learning network(MMAL-Net) has good classification ability and robustness for images of different scales.
Ranked #4 on
Fine-Grained Image Classification
on FGVC Aircraft
Fine-Grained Image Classification
Fine-Grained Image Recognition
+3
SAFE: Scalable Automatic Feature Engineering Framework for Industrial Tasks
Machine learning techniques have been widely applied in Internet companies for various tasks, acting as an essential driving force, and feature engineering has been generally recognized as a crucial tache when constructing machine learning systems.
Multi-Vehicle Routing Problems with Soft Time Windows: A Multi-Agent Reinforcement Learning Approach
Multi-vehicle routing problem with soft time windows (MVRPSTW) is an indispensable constituent in urban logistics distribution systems.
Improving Efficiency in Neural Network Accelerator Using Operands Hamming Distance optimization
Neural network accelerator is a key enabler for the on-device AI inference, for which energy efficiency is an important metric.
Co-Exploration of Neural Architectures and Heterogeneous ASIC Accelerator Designs Targeting Multiple Tasks
Neural Architecture Search (NAS) has demonstrated its power on various AI accelerating platforms such as Field Programmable Gate Arrays (FPGAs) and Graphic Processing Units (GPUs).
Bayesian Median Autoregression for Robust Time Series Forecasting
We develop a Bayesian median autoregressive (BayesMAR) model for time series forecasting.
Applications Econometrics Methodology
CARP: Compression through Adaptive Recursive Partitioning for Multi-dimensional Images
Fast and effective image compression for multi-dimensional images has become increasingly important for efficient storage and transfer of massive amounts of high-resolution images and videos.
PGU-net+: Progressive Growing of U-net+ for Automated Cervical Nuclei Segmentation
The experimental results show that the PGU-net+ has superior accuracy than the previous state-of-the-art methods on cervical nuclei segmentation.
Energy-Aware Neural Architecture Optimization with Fast Splitting Steepest Descent
Designing energy-efficient networks is of critical importance for enabling state-of-the-art deep learning in mobile and edge settings where the computation and energy budgets are highly limited.
Experimental realization of state transfer by quantum walks with two coins
Quantum state transfer between different sites is a significant problem for quantum networks and quantum computers.
Quantum Physics
Uncertainty-Guided Domain Alignment for Layer Segmentation in OCT Images
Automatic and accurate segmentation for retinal and choroidal layers of Optical Coherence Tomography (OCT) is crucial for detection of various ocular diseases.
Deep Instance-Level Hard Negative Mining Model for Histopathology Images
Histopathology image analysis can be considered as a Multiple instance learning (MIL) problem, where the whole slide histopathology image (WSI) is regarded as a bag of instances (i. e, patches) and the task is to predict a single class label to the WSI.
Automated segmentaiton and classification of arterioles and venules using Cascading Dilated Convolutional Neural Networks
The change of retinal vasculature is an early sign of many vascular and systematic diseases, such as diabetes and hypertension.
Multistep Speed Prediction on Traffic Networks: A Graph Convolutional Sequence-to-Sequence Learning Approach with Attention Mechanism
Multistep traffic forecasting on road networks is a crucial task in successful intelligent transportation system applications.
Function-on-Scalar Quantile Regression with Application to Mass Spectrometry Proteomics Data
Mass spectrometry proteomics, characterized by spiky, spatially heterogeneous functional data, can be used to identify potential cancer biomarkers.
Methodology
Computed Tomography Image Enhancement using 3D Convolutional Neural Network
Computed tomography (CT) is increasingly being used for cancer screening, such as early detection of lung cancer.
Federated Learning with Non-IID Data
Experiments show that accuracy can be increased by 30% for the CIFAR-10 dataset with only 5% globally shared data.
ISCLAB at SemEval-2018 Task 1: UIR-Miner for Affect in Tweets
This paper presents a UIR-Miner system for emotion and sentiment analysis evaluation in Twitter in SemEval 2018.
Reducing over-clustering via the powered Chinese restaurant process
Dirichlet process mixture (DPM) models tend to produce many small clusters regardless of whether they are needed to accurately characterize the data - this is particularly true for large data sets.
Learning Asymmetric and Local Features in Multi-Dimensional Data through Wavelets with Recursive Partitioning
Effective learning of asymmetric and local features in images and other data observed on multi-dimensional grids is a challenging objective critical for a wide range of image processing applications involving biomedical and natural images.
PrivyNet: A Flexible Framework for Privacy-Preserving Deep Neural Network Training
Massive data exist among user local platforms that usually cannot support deep neural network (DNN) training due to computation and storage resource constraints.
