Search Results for author:
Found 105 papers, 25 papers with code
Graph Learning for Parameter Prediction of Quantum Approximate Optimization Algorithm
In recent years, quantum computing has emerged as a transformative force in the field of combinatorial optimization, offering novel approaches to tackling complex problems that have long challenged classical computational methods.
Toward Fairness via Maximum Mean Discrepancy Regularization on Logits Space
Fairness has become increasingly pivotal in machine learning for high-risk applications such as machine learning in healthcare and facial recognition.
EBFT: Effective and Block-Wise Fine-Tuning for Sparse LLMs
For instance, on the Wikitext2 dataset with LlamaV1-7B at 70% sparsity, our proposed EBFT achieves a perplexity of 16. 88, surpassing the state-of-the-art DSnoT with a perplexity of 75. 14.
FL-NAS: Towards Fairness of NAS for Resource Constrained Devices via Large Language Models
Neural Architecture Search (NAS) has become the de fecto tools in the industry in automating the design of deep neural networks for various applications, especially those driven by mobile and edge devices with limited computing resources.
Achieve Fairness without Demographics for Dermatological Disease Diagnosis
To overcome this, we propose a method enabling fair predictions for sensitive attributes during the testing phase without using such information during training.
U-SWIM: Universal Selective Write-Verify for Computing-in-Memory Neural Accelerators
In our research, we illustrate that only a small fraction of weights need this write-verify treatment for the corresponding devices and the DNN accuracy can be preserved, yielding a notable programming acceleration.
Compute-in-Memory based Neural Network Accelerators for Safety-Critical Systems: Worst-Case Scenarios and Protections
In this study, we define the problem of pinpointing the worst-case performance of CiM DNN accelerators affected by device variations.
RobustState: Boosting Fidelity of Quantum State Preparation via Noise-Aware Variational Training
Arbitrary state preparation algorithms can be broadly categorized into arithmetic decomposition (AD) and variational quantum state preparation (VQSP).
Enabling On-Device Large Language Model Personalization with Self-Supervised Data Selection and Synthesis
While it is possible to obtain annotation locally by directly asking users to provide preferred responses, such annotations have to be sparse to not affect user experience.
Muffin: A Framework Toward Multi-Dimension AI Fairness by Uniting Off-the-Shelf Models
Model fairness (a. k. a., bias) has become one of the most critical problems in a wide range of AI applications.
Masked Diffusion as Self-supervised Representation Learner
Denoising diffusion probabilistic models have recently demonstrated state-of-the-art generative performance and have been used as strong pixel-level representation learners.
Ranked #1 on
Medical Image Segmentation
on MoNuSeg
Proof-of-Federated-Learning-Subchain: Free Partner Selection Subchain Based on Federated Learning
In the conducted experiments, the PoFLSC consensus supported the subchain manager to be aware of reservation priority and the core partition of contributors to establish and maintain a competitive subchain.
Improving Realistic Worst-Case Performance of NVCiM DNN Accelerators through Training with Right-Censored Gaussian Noise
In this work, we propose to use the k-th percentile performance (KPP) to capture the realistic worst-case performance of DNN models executing on CiM accelerators.
AME-CAM: Attentive Multiple-Exit CAM for Weakly Supervised Segmentation on MRI Brain Tumor
Magnetic resonance imaging (MRI) is commonly used for brain tumor segmentation, which is critical for patient evaluation and treatment planning.
Toward Fairness Through Fair Multi-Exit Framework for Dermatological Disease Diagnosis
Fairness has become increasingly pivotal in medical image recognition.
How to Efficiently Adapt Large Segmentation Model(SAM) to Medical Images
To evaluate the label-efficiency of our finetuning method, we compare the results of these three prediction heads on a public medical image segmentation dataset with limited labeled data.
On the Viability of using LLMs for SW/HW Co-Design: An Example in Designing CiM DNN Accelerators
In this study, we present a novel approach that leverages Large Language Models (LLMs) to address this issue.
A Novel Confidence Induced Class Activation Mapping for MRI Brain Tumor Segmentation
Magnetic resonance imaging (MRI) is a commonly used technique for brain tumor segmentation, which is critical for evaluating patients and planning treatment.
Conditional Diffusion Models for Weakly Supervised Medical Image Segmentation
Recent advances in denoising diffusion probabilistic models have shown great success in image synthesis tasks.
Additional Positive Enables Better Representation Learning for Medical Images
This paper presents a new way to identify additional positive pairs for BYOL, a state-of-the-art (SOTA) self-supervised learning framework, to improve its representation learning ability.
Negative Feedback Training: A Novel Concept to Improve Robustness of NVCIM DNN Accelerators
However, the stochastic nature and intrinsic variations of NVM devices often result in performance degradation in DNN inference.
TinyML Design Contest for Life-Threatening Ventricular Arrhythmia Detection
This paper concludes with the direction of improvement for the future TinyML design for health monitoring applications.
Fair Multi-Exit Framework for Facial Attribute Classification
Fairness has become increasingly pivotal in facial recognition.
Development of A Real-time POCUS Image Quality Assessment and Acquisition Guidance System
Point-of-care ultrasound (POCUS) is one of the most commonly applied tools for cardiac function imaging in the clinical routine of the emergency department and pediatric intensive care unit.
Self-supervised On-device Federated Learning from Unlabeled Streams
The ubiquity of edge devices has led to a growing amount of unlabeled data produced at the edge.
Unsupervised Feature Clustering Improves Contrastive Representation Learning for Medical Image Segmentation
Self-supervised instance discrimination is an effective contrastive pretext task to learn feature representations and address limited medical image annotations.
ImageCAS: A Large-Scale Dataset and Benchmark for Coronary Artery Segmentation based on Computed Tomography Angiography Images
In this paper, we propose a large-scale dataset for coronary artery segmentation on CTA images.
QuEst: Graph Transformer for Quantum Circuit Reliability Estimation
Specifically, the TorchQuantum library also supports using data-driven ML models to solve problems in quantum system research, such as predicting the impact of quantum noise on circuit fidelity and improving the quantum circuit compilation efficiency.
Federated Self-Supervised Contrastive Learning and Masked Autoencoder for Dermatological Disease Diagnosis
Self-supervised learning (SSL) methods, contrastive learning (CL) and masked autoencoders (MAE), can leverage the unlabeled data to pre-train models, followed by fine-tuning with limited labels.
Achieving Fairness in Dermatological Disease Diagnosis through Automatic Weight Adjusting Federated Learning and Personalization
The framework is divided into two stages: In the first in-FL stage, clients with different skin types are trained in a federated learning process to construct a global model for all skin types.
Distributed Contrastive Learning for Medical Image Segmentation
However, when adopting CL in FL, the limited data diversity on each site makes federated contrastive learning (FCL) ineffective.
NAPA: Intermediate-level Variational Native-pulse Ansatz for Variational Quantum Algorithms
Therefore, we propose NAPA, a native-pulse ansatz generator framework for VQAs.
Contrastive Image Synthesis and Self-supervised Feature Adaptation for Cross-Modality Biomedical Image Segmentation
As such, we enforce contrastive losses on the generated images and the input images to train the encoder of a segmentation model to minimize the discrepancy between paired images in the learned embedding space.
Computing-In-Memory Neural Network Accelerators for Safety-Critical Systems: Can Small Device Variations Be Disastrous?
In this work, we formulate the problem of determining the worst-case performance of CiM DNN accelerators under the impact of device variations.
RT-DNAS: Real-time Constrained Differentiable Neural Architecture Search for 3D Cardiac Cine MRI Segmentation
Accurately segmenting temporal frames of cine magnetic resonance imaging (MRI) is a crucial step in various real-time MRI guided cardiac interventions.
OTFPF: Optimal Transport-Based Feature Pyramid Fusion Network for Brain Age Estimation with 3D Overlapped ConvNeXt
In this paper, we propose an end-to-end neural network architecture, referred to as optimal transport based feature pyramid fusion (OTFPF) network, for the brain age estimation with T1 MRIs.
A Collaboration Strategy in the Mining Pool for Proof-of-Neural-Architecture Consensus
In many recent novel blockchain consensuses, the deep learning training procedure becomes the task for miners to prove their workload, thus the computation power of miners will not purely be spent on the hash puzzle.
Federated Contrastive Learning for Volumetric Medical Image Segmentation
However, in medical imaging analysis, each site may only have a limited amount of data and labels, which makes learning ineffective.
A Semi-Decoupled Approach to Fast and Optimal Hardware-Software Co-Design of Neural Accelerators
We first perform neural architecture search to obtain a small set of optimal architectures for one accelerator candidate.
FairPrune: Achieving Fairness Through Pruning for Dermatological Disease Diagnosis
By pruning the parameters based on this importance difference, we can reduce the accuracy difference between the privileged group and the unprivileged group to improve fairness without a large accuracy drop.
The Larger The Fairer? Small Neural Networks Can Achieve Fairness for Edge Devices
Results show that FaHaNa can identify a series of neural networks with higher fairness and accuracy on a dermatology dataset.
SWIM: Selective Write-Verify for Computing-in-Memory Neural Accelerators
In this work, we show that it is only necessary to select a small portion of the weights for write-verify to maintain the DNN accuracy, thus achieving significant speedup.
Synthetic Data Can Also Teach: Synthesizing Effective Data for Unsupervised Visual Representation Learning
To tackle this problem, we propose a data generation framework with two methods to improve CL training by joint sample generation and contrastive learning.
Federated Contrastive Learning for Dermatological Disease Diagnosis via On-device Learning
The recently developed self-supervised learning approach, contrastive learning (CL), can leverage the unlabeled data to pre-train a model, after which the model is fine-tuned on limited labeled data for dermatological disease diagnosis.
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.
One Proxy Device Is Enough for Hardware-Aware Neural Architecture Search
A key requirement of efficient hardware-aware NAS is the fast evaluation of inference latencies in order to rank different architectures.
Hardware Aware Neural Architecture Search
Neural Architecture Search
"One-Shot" Reduction of Additive Artifacts in Medical Images
Medical images may contain various types of artifacts with different patterns and mixtures, which depend on many factors such as scan setting, machine condition, patients' characteristics, surrounding environment, etc.
Data-Efficient Contrastive Learning by Differentiable Hard Sample and Hard Positive Pair Generation
In this way, the main model learns to cluster hard positives by pulling the representations of similar yet distinct samples together, by which the representations of similar samples are well-clustered and better representations can be learned.
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.
Semi-supervised Contrastive Learning for Label-efficient Medical Image Segmentation
With different amounts of labeled data, our methods consistently outperform the state-of-the-art contrast-based methods and other semi-supervised learning techniques.
Hardware-aware Real-time Myocardial Segmentation Quality Control in Contrast Echocardiography
At the data acquisition time, the operator could not know the quality of the segmentation results.
Hardware Aware Neural Architecture Search
Neural Architecture Search
+1
RADARS: Memory Efficient Reinforcement Learning Aided Differentiable Neural Architecture Search
To the best of the authors' knowledge, this is the first DNAS framework that can handle large search spaces with bounded memory usage.
Can Noise on Qubits Be Learned in Quantum Neural Network? A Case Study on QuantumFlow
Specifically, this paper targets quantum neural network (QNN), and proposes to learn the errors in the training phase, so that the identified QNN model can be resilient to noise.
Exploration of Quantum Neural Architecture by Mixing Quantum Neuron Designs
Experimental results demonstrate that the identified quantum neural architectures with mixed quantum neurons can achieve 90. 62% of accuracy on the MNIST dataset, compared with 52. 77% and 69. 92% on the VQC and QuantumFlow, respectively.
Contrastive Learning with Temporal Correlated Medical Images: A Case Study using Lung Segmentation in Chest X-Rays
In this work, we use lung segmentation in chest X-rays as a case study and propose a contrastive learning framework with temporal correlated medical images, named CL-TCI, to learn superior encoders for initializing the segmentation network.
ImageTBAD: A 3D Computed Tomography Angiography Image Dataset for Automatic Segmentation of Type-B Aortic Dissection
Results show that the baseline method can achieve comparable results with existing works on aorta and TL segmentation.
Uncertainty Modeling of Emerging Device-based Computing-in-Memory Neural Accelerators with Application to Neural Architecture Search
Emerging device-based Computing-in-memory (CiM) has been proved to be a promising candidate for high-energy efficiency deep neural network (DNN) computations.
Segmentation with Multiple Acceptable Annotations: A Case Study of Myocardial Segmentation in Contrast Echocardiography
Experiment results on our clinical MCE data set demonstrate that the neural network trained with the proposed loss function outperforms those existing ones that try to obtain a unique ground truth from multiple annotations, both quantitatively and qualitatively.
Positional Contrastive Learning for Volumetric Medical Image Segmentation
The success of deep learning heavily depends on the availability of large labeled training sets.
Enabling On-Device Self-Supervised Contrastive Learning With Selective Data Contrast
After a model is deployed on edge devices, it is desirable for these devices to learn from unlabeled data to continuously improve accuracy.
EchoCP: An Echocardiography Dataset in Contrast Transthoracic Echocardiography for Patent Foramen Ovale Diagnosis
For PFO diagnosis, contrast transthoracic echocardiography (cTTE) is preferred as being a more robust method compared with others.
Multi-Cycle-Consistent Adversarial Networks for Edge Denoising of Computed Tomography Images
As one of the most commonly ordered imaging tests, computed tomography (CT) scan comes with inevitable radiation exposure that increases the cancer risk to patients.
Quantization of Deep Neural Networks for Accurate Edge Computing
Deep neural networks (DNNs) have demonstrated their great potential in recent years, exceeding the per-formance of human experts in a wide range of applications.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+5
Dancing along Battery: Enabling Transformer with Run-time Reconfigurability on Mobile Devices
Specifically, RT3 integrates two-level optimizations: First, it utilizes an efficient BP as the first-step compression for resource-constrained mobile devices; then, RT3 heuristically generates a shrunken search space based on the first level optimization and searches multiple pattern sets with diverse sparsity for PP via reinforcement learning to support lightweight software reconfiguration, which corresponds to available frequency levels of DVFS (i. e., hardware reconfiguration).
ImageCHD: A 3D Computed Tomography Image Dataset for Classification of Congenital Heart Disease
To demonstrate this, we further present a baseline framework for the automatic classification of CHD, based on a state-of-the-art CHD segmentation method.
On the Universal Approximability and Complexity Bounds of Deep Learning in Hybrid Quantum-Classical Computing
With the continuously increasing number of quantum bits in quantum computers, there are growing interests in exploring applications that can harvest the power of them.
FGNAS: FPGA-Aware Graph Neural Architecture Search
The success of gragh neural networks (GNNs) in the past years has aroused grow-ing interest and effort in designing best models to handle graph-structured data.
Enabling Efficient On-Device Self-supervised Contrastive Learning by Data Selection
In this paper, we propose a framework to automatically select the most representative data from unlabeled input stream on-the-fly, which only requires the use of a small data buffer for dynamic learning.
Attention Based Joint Learning for Supervised Premature Ventricular Contraction Differentiation with Unsupervised Abnormal Beat Segmentation
Though the training data is only labeled to supervise theclassifier, the segmenter and the classifier are trained in an end-to-end manner sothat optimizing classification performance also adjusts how the abnormal beats aresegmented.
Myocardial Segmentation of Cardiac MRI Sequences with Temporal Consistency for Coronary Artery Disease Diagnosis
Coronary artery disease (CAD) is the most common cause of death globally, and its diagnosis is usually based on manual myocardial segmentation of Magnetic Resonance Imaging (MRI) sequences.
When Machine Learning Meets Quantum Computers: A Case Study
It is imminent to know how to design the quantum circuit for accelerating neural networks.
Do Noises Bother Human and Neural Networks In the Same Way? A Medical Image Analysis Perspective
Deep learning had already demonstrated its power in medical images, including denoising, classification, segmentation, etc.
Personalized Deep Learning for Ventricular Arrhythmias Detection on Medical IoT Systems
We equip the system with real-time inference on both intracardiac and surface rhythm monitors.
Towards Cardiac Intervention Assistance: Hardware-aware Neural Architecture Exploration for Real-Time 3D Cardiac Cine MRI Segmentation
Experimental results on ACDC MICCAI 2017 dataset demonstrate that our hardware-aware multi-scale NAS framework can reduce the latency by up to 3. 5 times and satisfy the real-time constraints, while still achieving competitive segmentation accuracy, compared with the state-of-the-art NAS segmentation framework.
ICA-UNet: ICA Inspired Statistical UNet for Real-time 3D Cardiac Cine MRI Segmentation
Real-time cine magnetic resonance imaging (MRI) plays an increasingly important role in various cardiac interventions.
Standing on the Shoulders of Giants: Hardware and Neural Architecture Co-Search with Hot Start
To tackle this issue, HotNAS builds a chain of tools to design hardware to support compression, based on which a global optimizer is developed to automatically co-search all the involved search spaces.
BUNET: Blind Medical Image Segmentation Based on Secure UNET
The strict security requirements placed on medical records by various privacy regulations become major obstacles in the age of big data.
MS-NAS: Multi-Scale Neural Architecture Search for Medical Image Segmentation
The recent breakthroughs of Neural Architecture Search (NAS) have motivated various applications in medical image segmentation.
DeU-Net: Deformable U-Net for 3D Cardiac MRI Video Segmentation
In this paper, we propose a novel Deformable U-Net (DeU-Net) to fully exploit spatio-temporal information from 3D cardiac MRI video, including a Temporal Deformable Aggregation Module (TDAM) and a Deformable Global Position Attention (DGPA) network.
Enabling On-Device CNN Training by Self-Supervised Instance Filtering and Error Map Pruning
For example, when training ResNet-110 on CIFAR-10, we achieve 68% computation saving while preserving full accuracy and 75% computation saving with a marginal accuracy loss of 1. 3%.
A Co-Design Framework of Neural Networks and Quantum Circuits Towards Quantum Advantage
We discover that, in order to make full use of the strength of quantum representation, it is best to represent data in a neural network as either random variables or numbers in unitary matrices, such that they can be directly operated by the basic quantum logical gates.
Intermittent Inference with Nonuniformly Compressed Multi-Exit Neural Network for Energy Harvesting Powered Devices
This work aims to enable persistent, event-driven sensing and decision capabilities for energy-harvesting (EH)-powered devices by deploying lightweight DNNs onto EH-powered devices.
ENSEI: Efficient Secure Inference via Frequency-Domain Homomorphic Convolution for Privacy-Preserving Visual Recognition
In this work, we propose ENSEI, a secure inference (SI) framework based on the frequency-domain secure convolution (FDSC) protocol for the efficient execution of privacy-preserving visual recognition.
Multi-Cycle-Consistent Adversarial Networks for CT Image Denoising
For example, if the noise is large leading to significant difference between domain $X$ and domain $Y$, can we bridge $X$ and $Y$ with an intermediate domain $Z$ such that both the denoising process between $X$ and $Z$ and that between $Z$ and $Y$ are easier to learn?
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).
NASS: Optimizing Secure Inference via Neural Architecture Search
Due to increasing privacy concerns, neural network (NN) based secure inference (SI) schemes that simultaneously hide the client inputs and server models attract major research interests.
Uncertainty-Aware Training of Neural Networks for Selective Medical Image Segmentation
Existing selective segmentation methods, however, ignore this unique property of selective segmentation and train their DNN models by optimizing accuracy on the entire dataset.
Faceted Hierarchy: A New Graph Type to Organize Scientific Concepts and a Construction Method
On a scientific concept hierarchy, a parent concept may have a few attributes, each of which has multiple values being a group of child concepts.
On Neural Architecture Search for Resource-Constrained Hardware Platforms
With 30, 000 LUTs, a light-weight design is found to achieve 82. 98\% accuracy and 1293 images/second throughput, compared to which, under the same constraints, the traditional method even fails to find a valid solution.
Device-Circuit-Architecture Co-Exploration for Computing-in-Memory Neural Accelerators
In this paper, we are the first to bring the computing-in-memory architecture, which can easily transcend the memory wall, to interplay with the neural architecture search, aiming to find the most efficient neural architectures with high network accuracy and maximized hardware efficiency.
MSU-Net: Multiscale Statistical U-Net for Real-time 3D Cardiac MRI Video Segmentation
Cardiac magnetic resonance imaging (MRI) is an essential tool for MRI-guided surgery and real-time intervention.
When Single Event Upset Meets Deep Neural Networks: Observations, Explorations, and Remedies
We are then able to analytically explore the weakness of a network and summarize the key findings for the impact of SIPP on different types of bits in a floating point parameter, layer-wise robustness within the same network and impact of network depth.
Accurate Congenital Heart Disease Model Generation for 3D Printing
3D printing has been widely adopted for clinical decision making and interventional planning of Congenital heart disease (CHD), while whole heart and great vessel segmentation is the most significant but time-consuming step in the model generation for 3D printing.
Hardware/Software Co-Exploration of Neural Architectures
We propose a novel hardware and software co-exploration framework for efficient neural architecture search (NAS).
Real-Time Adversarial Attacks
In recent years, many efforts have demonstrated that modern machine learning algorithms are vulnerable to adversarial attacks, where small, but carefully crafted, perturbations on the input can make them fail.
DLBC: A Deep Learning-Based Consensus in Blockchains for Deep Learning Services
In this paper, we propose DLBC to exploit the computation power of miners for deep learning training as proof of useful work instead of calculating hash values.
Machine Vision Guided 3D Medical Image Compression for Efficient Transmission and Accurate Segmentation in the Clouds
In this paper we will use deep learning based medical image segmentation as a vehicle and demonstrate that interestingly, machine and human view the compression quality differently.
SCNN: A General Distribution based Statistical Convolutional Neural Network with Application to Video Object Detection
By introducing a parameterized canonical model to model correlated data and defining corresponding operations as required for CNN training and inference, we show that SCNN can process multiple frames of correlated images effectively, hence achieving significant speedup over existing CNN models.
Real-Time Boiler Control Optimization with Machine Learning
In coal-fired power plants, it is critical to improve the operational efficiency of boilers for sustainability.
Revisiting the Evaluation of Uncertainty Estimation and Its Application to Explore Model Complexity-Uncertainty Trade-Off
Accurately estimating uncertainties in neural network predictions is of great importance in building trusted DNNs-based models, and there is an increasing interest in providing accurate uncertainty estimation on many tasks, such as security cameras and autonomous driving vehicles.
Accuracy vs. Efficiency: Achieving Both through FPGA-Implementation Aware Neural Architecture Search
In addition, with a performance abstraction model to analyze the latency of neural architectures without training, our framework can quickly prune architectures that do not satisfy the specification, leading to higher efficiency.
DAC-SDC Low Power Object Detection Challenge for UAV Applications
The 55th Design Automation Conference (DAC) held its first System Design Contest (SDC) in 2018.
Quantization of Fully Convolutional Networks for Accurate Biomedical Image Segmentation
Unlike existing litera- ture on quantization which primarily targets memory and computation complexity reduction, we apply quan- tization as a method to reduce over tting in FCNs for better accuracy.
PBGen: Partial Binarization of Deconvolution-Based Generators for Edge Intelligence
This work explores the binarization of the deconvolution-based generator in a GAN for memory saving and speedup of image construction.
On the Universal Approximability and Complexity Bounds of Quantized ReLU Neural Networks
To the best of our knowledge, this is the first in-depth study on the complexity bounds of quantized neural networks.
