Search Results for author: Yiyu Shi

Found 108 papers, 26 papers with code

Achieving Fairness Through Channel Pruning for Dermatological Disease Diagnosis

1 code implementation14 May 2024 Qingpeng Kong, Ching-Hao Chiu, Dewen Zeng, Yu-Jen Chen, Tsung-Yi Ho, Jingtong Hu, Yiyu Shi

Numerous studies have revealed that deep learning-based medical image classification models may exhibit bias towards specific demographic attributes, such as race, gender, and age.

Fairness Image Classification +1

Towards Energy-Aware Federated Learning via MARL: A Dual-Selection Approach for Model and Client

no code implementations13 May 2024 Jun Xia, Yiyu Shi

Although Federated Learning (FL) is promising in knowledge sharing for heterogeneous Artificial Intelligence of Thing (AIoT) devices, their training performance and energy efficacy are severely restricted in practical battery-driven scenarios due to the ``wooden barrel effect'' caused by the mismatch between homogeneous model paradigms and heterogeneous device capability.

Federated Learning

Graph Learning for Parameter Prediction of Quantum Approximate Optimization Algorithm

no code implementations5 Mar 2024 Zhiding Liang, Gang Liu, Zheyuan Liu, Jinglei Cheng, Tianyi Hao, Kecheng Liu, Hang Ren, Zhixin Song, Ji Liu, Fanny Ye, Yiyu Shi

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.

Combinatorial Optimization Graph Learning +1

Toward Fairness via Maximum Mean Discrepancy Regularization on Logits Space

no code implementations20 Feb 2024 Hao-Wei Chung, Ching-Hao Chiu, Yu-Jen Chen, Yiyu Shi, Tsung-Yi Ho

Fairness has become increasingly pivotal in machine learning for high-risk applications such as machine learning in healthcare and facial recognition.

Fairness

EBFT: Effective and Block-Wise Fine-Tuning for Sparse LLMs

1 code implementation19 Feb 2024 Song Guo, Fan Wu, Lei Zhang, Xiawu Zheng, Shengchuan Zhang, Fei Chao, Yiyu Shi, Rongrong Ji

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

no code implementations9 Feb 2024 Ruiyang Qin, Yuting Hu, Zheyu Yan, JinJun Xiong, Ahmed Abbasi, Yiyu Shi

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.

Fairness Neural Architecture Search

Achieve Fairness without Demographics for Dermatological Disease Diagnosis

no code implementations16 Jan 2024 Ching-Hao Chiu, Yu-Jen Chen, Yawen Wu, Yiyu Shi, Tsung-Yi Ho

To overcome this, we propose a method enabling fair predictions for sensitive attributes during the testing phase without using such information during training.

Attribute Fairness

U-SWIM: Universal Selective Write-Verify for Computing-in-Memory Neural Accelerators

no code implementations11 Dec 2023 Zheyu Yan, Xiaobo Sharon Hu, Yiyu Shi

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

no code implementations11 Dec 2023 Zheyu Yan, Xiaobo Sharon Hu, Yiyu Shi

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

no code implementations27 Nov 2023 Hanrui Wang, Yilian Liu, Pengyu Liu, Jiaqi Gu, Zirui Li, Zhiding Liang, Jinglei Cheng, Yongshan Ding, Xuehai Qian, Yiyu Shi, David Z. Pan, Frederic T. Chong, Song Han

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

no code implementations21 Nov 2023 Ruiyang Qin, Jun Xia, Zhenge Jia, Meng Jiang, Ahmed Abbasi, Peipei Zhou, Jingtong Hu, Yiyu Shi

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.

Language Modelling Large Language Model

Masked Diffusion as Self-supervised Representation Learner

1 code implementation10 Aug 2023 Zixuan Pan, Jianxu Chen, Yiyu Shi

Denoising diffusion probabilistic models have recently demonstrated state-of-the-art generative performance and have been used as strong pixel-level representation learners.

Denoising Medical Image Segmentation +3

Proof-of-Federated-Learning-Subchain: Free Partner Selection Subchain Based on Federated Learning

no code implementations30 Jul 2023 Boyang Li, Bingyu Shen, Qing Lu, Taeho Jung, Yiyu Shi

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.

Federated Learning

Improving Realistic Worst-Case Performance of NVCiM DNN Accelerators through Training with Right-Censored Gaussian Noise

no code implementations29 Jul 2023 Zheyu Yan, Yifan Qin, Wujie Wen, Xiaobo Sharon Hu, Yiyu Shi

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.

Self-Driving Cars

AME-CAM: Attentive Multiple-Exit CAM for Weakly Supervised Segmentation on MRI Brain Tumor

1 code implementation26 Jun 2023 Yu-Jen Chen, Xinrong Hu, Yiyu Shi, Tsung-Yi Ho

Magnetic resonance imaging (MRI) is commonly used for brain tumor segmentation, which is critical for patient evaluation and treatment planning.

Brain Tumor Segmentation Segmentation +4

How to Efficiently Adapt Large Segmentation Model(SAM) to Medical Images

1 code implementation23 Jun 2023 Xinrong Hu, Xiaowei Xu, Yiyu Shi

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.

Image Segmentation Medical Image Segmentation +4

On the Viability of using LLMs for SW/HW Co-Design: An Example in Designing CiM DNN Accelerators

no code implementations12 Jun 2023 Zheyu Yan, Yifan Qin, Xiaobo Sharon Hu, Yiyu Shi

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

1 code implementation8 Jun 2023 Yu-Jen Chen, Yiyu Shi, Tsung-Yi Ho

Magnetic resonance imaging (MRI) is a commonly used technique for brain tumor segmentation, which is critical for evaluating patients and planning treatment.

Brain Tumor Segmentation Object Localization +4

Conditional Diffusion Models for Weakly Supervised Medical Image Segmentation

1 code implementation6 Jun 2023 Xinrong Hu, Yu-Jen Chen, Tsung-Yi Ho, Yiyu Shi

Recent advances in denoising diffusion probabilistic models have shown great success in image synthesis tasks.

Denoising Image Generation +5

Additional Positive Enables Better Representation Learning for Medical Images

no code implementations31 May 2023 Dewen Zeng, Yawen Wu, Xinrong Hu, Xiaowei Xu, Jingtong Hu, Yiyu Shi

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.

Representation Learning Self-Supervised Learning +1

Negative Feedback Training: A Novel Concept to Improve Robustness of NVCIM DNN Accelerators

1 code implementation23 May 2023 Yifan Qin, Zheyu Yan, Wujie Wen, Xiaobo Sharon Hu, Yiyu Shi

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

no code implementations9 May 2023 Zhenge Jia, Dawei Li, Cong Liu, Liqi Liao, Xiaowei Xu, Lichuan Ping, Yiyu Shi

This paper concludes with the direction of improvement for the future TinyML design for health monitoring applications.

Arrhythmia Detection

Development of A Real-time POCUS Image Quality Assessment and Acquisition Guidance System

no code implementations16 Dec 2022 Zhenge Jia, Yiyu Shi, Jingtong Hu, Lei Yang, Benjamin Nti

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.

Image Quality Assessment

Unsupervised Feature Clustering Improves Contrastive Representation Learning for Medical Image Segmentation

no code implementations15 Nov 2022 Yejia Zhang, Xinrong Hu, Nishchal Sapkota, Yiyu Shi, Danny Z. Chen

Self-supervised instance discrimination is an effective contrastive pretext task to learn feature representations and address limited medical image annotations.

Clustering Contrastive Learning +4

QuEst: Graph Transformer for Quantum Circuit Reliability Estimation

1 code implementation30 Oct 2022 Hanrui Wang, Pengyu Liu, Jinglei Cheng, Zhiding Liang, Jiaqi Gu, Zirui Li, Yongshan Ding, Weiwen Jiang, Yiyu Shi, Xuehai Qian, David Z. Pan, Frederic T. Chong, Song Han

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

no code implementations24 Aug 2022 Yawen Wu, Dewen Zeng, Zhepeng Wang, Yi Sheng, Lei Yang, Alaina J. James, Yiyu Shi, Jingtong Hu

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.

Contrastive Learning Federated Learning +1

Achieving Fairness in Dermatological Disease Diagnosis through Automatic Weight Adjusting Federated Learning and Personalization

no code implementations23 Aug 2022 Gelei Xu, Yawen Wu, Jingtong Hu, Yiyu Shi

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.

Fairness Federated Learning

Distributed Contrastive Learning for Medical Image Segmentation

no code implementations7 Aug 2022 Yawen Wu, Dewen Zeng, Zhepeng Wang, Yiyu Shi, Jingtong Hu

However, when adopting CL in FL, the limited data diversity on each site makes federated contrastive learning (FCL) ineffective.

Contrastive Learning Federated Learning +4

Contrastive Image Synthesis and Self-supervised Feature Adaptation for Cross-Modality Biomedical Image Segmentation

1 code implementation27 Jul 2022 Xinrong Hu, Corey Wang, Yiyu Shi

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.

Domain Adaptation Image Generation +3

Computing-In-Memory Neural Network Accelerators for Safety-Critical Systems: Can Small Device Variations Be Disastrous?

no code implementations15 Jul 2022 Zheyu Yan, Xiaobo Sharon Hu, Yiyu Shi

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

no code implementations8 Jun 2022 Qing Lu, Xiaowei Xu, Shunjie Dong, Cong Hao, Lei Yang, Cheng Zhuo, Yiyu Shi

Accurately segmenting temporal frames of cine magnetic resonance imaging (MRI) is a crucial step in various real-time MRI guided cardiac interventions.

MRI segmentation Neural Architecture Search

OTFPF: Optimal Transport-Based Feature Pyramid Fusion Network for Brain Age Estimation with 3D Overlapped ConvNeXt

2 code implementations10 May 2022 Yu Fu, Yanyan Huang, Yalin Wang, Shunjie Dong, Le Xue, Xunzhao Yin, Qianqian Yang, Yiyu Shi, Cheng Zhuo

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.

Age Estimation

A Collaboration Strategy in the Mining Pool for Proof-of-Neural-Architecture Consensus

no code implementations5 May 2022 Boyang Li, Qing Lu, Weiwen Jiang, Taeho Jung, Yiyu Shi

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.

Neural Architecture Search

Federated Contrastive Learning for Volumetric Medical Image Segmentation

no code implementations23 Apr 2022 Yawen Wu, Dewen Zeng, Zhepeng Wang, Yiyu Shi, Jingtong Hu

However, in medical imaging analysis, each site may only have a limited amount of data and labels, which makes learning ineffective.

Contrastive Learning Federated Learning +4

A Semi-Decoupled Approach to Fast and Optimal Hardware-Software Co-Design of Neural Accelerators

1 code implementation25 Mar 2022 Bingqian Lu, Zheyu Yan, Yiyu Shi, Shaolei Ren

We first perform neural architecture search to obtain a small set of optimal architectures for one accelerator candidate.

Neural Architecture Search

FairPrune: Achieving Fairness Through Pruning for Dermatological Disease Diagnosis

no code implementations4 Mar 2022 Yawen Wu, Dewen Zeng, Xiaowei Xu, Yiyu Shi, Jingtong Hu

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.

Fairness Image Classification +1

The Larger The Fairer? Small Neural Networks Can Achieve Fairness for Edge Devices

no code implementations23 Feb 2022 Yi Sheng, Junhuan Yang, Yawen Wu, Kevin Mao, Yiyu Shi, Jingtong Hu, Weiwen Jiang, Lei Yang

Results show that FaHaNa can identify a series of neural networks with higher fairness and accuracy on a dermatology dataset.

Face Recognition Fairness +2

SWIM: Selective Write-Verify for Computing-in-Memory Neural Accelerators

1 code implementation17 Feb 2022 Zheyu Yan, Xiaobo Sharon Hu, Yiyu Shi

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.

Federated Contrastive Learning for Dermatological Disease Diagnosis via On-device Learning

no code implementations14 Feb 2022 Yawen Wu, Dewen Zeng, Zhepeng Wang, Yi Sheng, Lei Yang, Alaina J. James, Yiyu Shi, Jingtong Hu

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.

Contrastive Learning Federated Learning +1

Synthetic Data Can Also Teach: Synthesizing Effective Data for Unsupervised Visual Representation Learning

no code implementations14 Feb 2022 Yawen Wu, Zhepeng Wang, Dewen Zeng, Yiyu Shi, Jingtong Hu

To tackle this problem, we propose a data generation framework with two methods to improve CL training by joint sample generation and contrastive learning.

Contrastive Learning Representation Learning +2

Decentralized Unsupervised Learning of Visual Representations

no code implementations21 Nov 2021 Yawen Wu, Zhepeng Wang, Dewen Zeng, Meng Li, Yiyu Shi, Jingtong Hu

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.

Contrastive Learning Federated Learning +2

One Proxy Device Is Enough for Hardware-Aware Neural Architecture Search

1 code implementation1 Nov 2021 Bingqian Lu, Jianyi Yang, Weiwen Jiang, Yiyu Shi, Shaolei Ren

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

no code implementations23 Oct 2021 Yu-Jen Chen, Yen-Jung Chang, Shao-Cheng Wen, Yiyu Shi, Xiaowei Xu, Tsung-Yi Ho, Meiping Huang, Haiyun Yuan, Jian Zhuang

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.

Computed Tomography (CT)

Federated Contrastive Representation Learning with Feature Fusion and Neighborhood Matching

no code implementations29 Sep 2021 Yawen Wu, Zhepeng Wang, Dewen Zeng, Meng Li, Yiyu Shi, Jingtong Hu

Federated learning (FL) enables distributed clients to learn a shared model for prediction while keeping the training data local on each client.

Contrastive Learning Federated Learning +2

Data-Efficient Contrastive Learning by Differentiable Hard Sample and Hard Positive Pair Generation

no code implementations29 Sep 2021 Yawen Wu, Zhepeng Wang, Dewen Zeng, Yiyu Shi, Jingtong Hu

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.

Contrastive Learning Self-Supervised Learning

Semi-supervised Contrastive Learning for Label-efficient Medical Image Segmentation

1 code implementation15 Sep 2021 Xinrong Hu, Dewen Zeng, Xiaowei Xu, Yiyu Shi

With different amounts of labeled data, our methods consistently outperform the state-of-the-art contrast-based methods and other semi-supervised learning techniques.

Contrastive Learning Image Segmentation +2

RADARS: Memory Efficient Reinforcement Learning Aided Differentiable Neural Architecture Search

no code implementations13 Sep 2021 Zheyu Yan, Weiwen Jiang, Xiaobo Sharon Hu, Yiyu Shi

To the best of the authors' knowledge, this is the first DNAS framework that can handle large search spaces with bounded memory usage.

Neural Architecture Search reinforcement-learning +1

Can Noise on Qubits Be Learned in Quantum Neural Network? A Case Study on QuantumFlow

no code implementations8 Sep 2021 Zhiding Liang, Zhepeng Wang, Junhuan Yang, Lei Yang, JinJun Xiong, Yiyu Shi, Weiwen Jiang

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

no code implementations8 Sep 2021 Zhepeng Wang, Zhiding Liang, Shanglin Zhou, Caiwen Ding, Yiyu Shi, Weiwen Jiang

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

1 code implementation7 Sep 2021 Dewen Zeng, John N. Kheir, Peng Zeng, Yiyu Shi

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.

Contrastive Learning Image Segmentation +7

Uncertainty Modeling of Emerging Device-based Computing-in-Memory Neural Accelerators with Application to Neural Architecture Search

no code implementations6 Jul 2021 Zheyu Yan, Da-Cheng Juan, Xiaobo Sharon Hu, Yiyu Shi

Emerging device-based Computing-in-memory (CiM) has been proved to be a promising candidate for high-energy efficiency deep neural network (DNN) computations.

Neural Architecture Search

Segmentation with Multiple Acceptable Annotations: A Case Study of Myocardial Segmentation in Contrast Echocardiography

2 code implementations29 Jun 2021 Dewen Zeng, Mingqi Li, Yukun Ding, Xiaowei Xu, Qiu Xie, Ruixue Xu, Hongwen Fei, Meiping Huang, Jian Zhuang, Yiyu Shi

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.

Image Segmentation Segmentation +1

Enabling On-Device Self-Supervised Contrastive Learning With Selective Data Contrast

no code implementations7 Jun 2021 Yawen Wu, Zhepeng Wang, Dewen Zeng, Yiyu Shi, Jingtong Hu

After a model is deployed on edge devices, it is desirable for these devices to learn from unlabeled data to continuously improve accuracy.

Contrastive Learning

EchoCP: An Echocardiography Dataset in Contrast Transthoracic Echocardiography for Patent Foramen Ovale Diagnosis

no code implementations18 May 2021 Tianchen Wang, Zhihe Li, Meiping Huang, Jian Zhuang, Shanshan Bi, Jiawei Zhang, Yiyu Shi, Hongwen Fei, Xiaowei Xu

For PFO diagnosis, contrast transthoracic echocardiography (cTTE) is preferred as being a more robust method compared with others.

Quantization of Deep Neural Networks for Accurate Edge Computing

no code implementations25 Apr 2021 Wentao Chen, Hailong Qiu, Jian Zhuang, Chutong Zhang, Yu Hu, Qing Lu, Tianchen Wang, Yiyu Shi, Meiping Huang, Xiaowe Xu

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

no code implementations12 Feb 2021 Yuhong Song, Weiwen Jiang, Bingbing Li, Panjie Qi, Qingfeng Zhuge, Edwin Hsing-Mean Sha, Sakyasingha Dasgupta, Yiyu Shi, Caiwen Ding

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).

AutoML

ImageCHD: A 3D Computed Tomography Image Dataset for Classification of Congenital Heart Disease

1 code implementation26 Jan 2021 Xiaowei Xu, Tianchen Wang, Jian Zhuang, Haiyun Yuan, Meiping Huang, Jianzheng Cen, Qianjun Jia, Yuhao Dong, Yiyu Shi

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.

Classification Computed Tomography (CT) +1

Enabling Efficient On-Device Self-supervised Contrastive Learning by Data Selection

no code implementations1 Jan 2021 Yawen Wu, Zhepeng Wang, Dewen Zeng, Yiyu Shi, Jingtong Hu

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.

Contrastive Learning

Attention Based Joint Learning for Supervised Premature Ventricular Contraction Differentiation with Unsupervised Abnormal Beat Segmentation

no code implementations1 Jan 2021 Xinrong Hu, long wen, shushui wang, Dongpo Liang, Jian Zhuang, Yiyu Shi

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.

Classification General Classification

FGNAS: FPGA-Aware Graph Neural Architecture Search

no code implementations1 Jan 2021 Qing Lu, Weiwen Jiang, Meng Jiang, Jingtong Hu, Sakyasingha Dasgupta, Yiyu Shi

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.

Neural Architecture Search

On the Universal Approximability and Complexity Bounds of Deep Learning in Hybrid Quantum-Classical Computing

no code implementations1 Jan 2021 Weiwen Jiang, Yukun Ding, Yiyu Shi

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.

Myocardial Segmentation of Cardiac MRI Sequences with Temporal Consistency for Coronary Artery Disease Diagnosis

no code implementations29 Dec 2020 Yutian Chen, Xiaowei Xu, Dewen Zeng, Yiyu Shi, Haiyun Yuan, Jian Zhuang, Yuhao Dong, Qianjun Jia, Meiping Huang

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.

Segmentation

Personalized Deep Learning for Ventricular Arrhythmias Detection on Medical IoT Systems

no code implementations18 Aug 2020 Zhenge Jia, Zhepeng Wang, Feng Hong, Lichuan Ping, Yiyu Shi, Jingtong Hu

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

no code implementations17 Aug 2020 Dewen Zeng, Weiwen Jiang, Tianchen Wang, Xiaowei Xu, Haiyun Yuan, Meiping Huang, Jian Zhuang, Jingtong Hu, Yiyu Shi

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.

MRI segmentation Neural Architecture Search +1

Standing on the Shoulders of Giants: Hardware and Neural Architecture Co-Search with Hot Start

1 code implementation17 Jul 2020 Weiwen Jiang, Lei Yang, Sakyasingha Dasgupta, Jingtong Hu, Yiyu Shi

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.

Neural Architecture Search

BUNET: Blind Medical Image Segmentation Based on Secure UNET

no code implementations14 Jul 2020 Song Bian, Xiaowei Xu, Weiwen Jiang, Yiyu Shi, Takashi Sato

The strict security requirements placed on medical records by various privacy regulations become major obstacles in the age of big data.

Image Segmentation Medical Image Segmentation +2

DeU-Net: Deformable U-Net for 3D Cardiac MRI Video Segmentation

no code implementations13 Jul 2020 Shunjie Dong, Jinlong Zhao, Maojun Zhang, Zhengxue Shi, Jianing Deng, Yiyu Shi, Mei Tian, Cheng Zhuo

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.

Video Segmentation Video Semantic Segmentation

MS-NAS: Multi-Scale Neural Architecture Search for Medical Image Segmentation

no code implementations13 Jul 2020 Xingang Yan, Weiwen Jiang, Yiyu Shi, Cheng Zhuo

The recent breakthroughs of Neural Architecture Search (NAS) have motivated various applications in medical image segmentation.

Image Segmentation Medical Image Segmentation +3

Enabling On-Device CNN Training by Self-Supervised Instance Filtering and Error Map Pruning

no code implementations7 Jul 2020 Yawen Wu, Zhepeng Wang, Yiyu Shi, Jingtong Hu

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%.

Quantization

A Co-Design Framework of Neural Networks and Quantum Circuits Towards Quantum Advantage

3 code implementations26 Jun 2020 Weiwen Jiang, JinJun Xiong, Yiyu Shi

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

no code implementations23 Apr 2020 Yawen Wu, Zhepeng Wang, Zhenge Jia, Yiyu Shi, Jingtong Hu

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

no code implementations CVPR 2020 Song Bian, Tianchen Wang, Masayuki Hiromoto, Yiyu Shi, Takashi Sato

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.

Privacy Preserving

Multi-Cycle-Consistent Adversarial Networks for CT Image Denoising

no code implementations27 Feb 2020 Jinglan Liu, Yukun Ding, JinJun Xiong, Qianjun Jia, Meiping Huang, Jian Zhuang, Bike Xie, Chun-Chen Liu, Yiyu Shi

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?

Image Denoising Image-to-Image Translation +1

Co-Exploration of Neural Architectures and Heterogeneous ASIC Accelerator Designs Targeting Multiple Tasks

no code implementations10 Feb 2020 Lei Yang, Zheyu Yan, Meng Li, Hyoukjun Kwon, Liangzhen Lai, Tushar Krishna, Vikas Chandra, Weiwen Jiang, Yiyu Shi

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).

Neural Architecture Search

NASS: Optimizing Secure Inference via Neural Architecture Search

no code implementations30 Jan 2020 Song Bian, Weiwen Jiang, Qing Lu, Yiyu Shi, Takashi Sato

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.

Neural Architecture Search

Uncertainty-Aware Training of Neural Networks for Selective Medical Image Segmentation

no code implementations MIDL 2019 Yukun Ding, Jinglan Liu, Xiaowei Xu, Meiping Huang, Jian Zhuang, JinJun Xiong, Yiyu Shi

Existing selective segmentation methods, however, ignore this unique property of selective segmentation and train their DNN models by optimizing accuracy on the entire dataset.

Image Segmentation Medical Image Segmentation +2

Faceted Hierarchy: A New Graph Type to Organize Scientific Concepts and a Construction Method

no code implementations WS 2019 Qingkai Zeng, Mengxia Yu, Wenhao Yu, JinJun Xiong, Yiyu Shi, Meng Jiang

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.

Face Recognition

On Neural Architecture Search for Resource-Constrained Hardware Platforms

no code implementations31 Oct 2019 Qing Lu, Weiwen Jiang, Xiaowei Xu, Yiyu Shi, Jingtong Hu

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.

Neural Architecture Search Quantization +1

Device-Circuit-Architecture Co-Exploration for Computing-in-Memory Neural Accelerators

no code implementations31 Oct 2019 Weiwen Jiang, Qiuwen Lou, Zheyu Yan, Lei Yang, Jingtong Hu, Xiaobo Sharon Hu, Yiyu Shi

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.

Neural Architecture Search

When Single Event Upset Meets Deep Neural Networks: Observations, Explorations, and Remedies

1 code implementation10 Sep 2019 Zheyu Yan, Yiyu Shi, Wang Liao, Masanori Hashimoto, Xichuan Zhou, Cheng Zhuo

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.

Hardware/Software Co-Exploration of Neural Architectures

1 code implementation6 Jul 2019 Weiwen Jiang, Lei Yang, Edwin Sha, Qingfeng Zhuge, Shouzhen Gu, Sakyasingha Dasgupta, Yiyu Shi, Jingtong Hu

We propose a novel hardware and software co-exploration framework for efficient neural architecture search (NAS).

Neural Architecture Search

Accurate Congenital Heart Disease Model Generation for 3D Printing

no code implementations6 Jul 2019 Xiaowei Xu, Tianchen Wang, Dewen Zeng, Yiyu Shi, Qianjun Jia, Haiyun Yuan, Meiping Huang, Jian Zhuang

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.

Anatomy Decision Making +2

Real-Time Adversarial Attacks

1 code implementation31 May 2019 Yuan Gong, Boyang Li, Christian Poellabauer, Yiyu Shi

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.

Adversarial Attack BIG-bench Machine Learning

DLBC: A Deep Learning-Based Consensus in Blockchains for Deep Learning Services

no code implementations15 Apr 2019 Boyang Li, Changhao Chenli, Xiaowei Xu, Yiyu Shi, Taeho Jung

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.

Semantic Segmentation

Machine Vision Guided 3D Medical Image Compression for Efficient Transmission and Accurate Segmentation in the Clouds

no code implementations CVPR 2019 Zihao Liu, Xiaowei Xu, Tao Liu, Qi Liu, Yanzhi Wang, Yiyu Shi, Wujie Wen, Meiping Huang, Haiyun Yuan, Jian Zhuang

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.

Image Compression Image Segmentation +3

SCNN: A General Distribution based Statistical Convolutional Neural Network with Application to Video Object Detection

no code implementations15 Mar 2019 Tianchen Wang, JinJun Xiong, Xiaowei Xu, Yiyu Shi

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.

object-detection Video Object Detection

Real-Time Boiler Control Optimization with Machine Learning

no code implementations7 Mar 2019 Yukun Ding, Yiyu Shi

In coal-fired power plants, it is critical to improve the operational efficiency of boilers for sustainability.

BIG-bench Machine Learning FLUE

Revisiting the Evaluation of Uncertainty Estimation and Its Application to Explore Model Complexity-Uncertainty Trade-Off

1 code implementation5 Mar 2019 Yukun Ding, Jinglan Liu, JinJun Xiong, Yiyu Shi

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.

Autonomous Driving

Accuracy vs. Efficiency: Achieving Both through FPGA-Implementation Aware Neural Architecture Search

no code implementations31 Jan 2019 Weiwen Jiang, Xinyi Zhang, Edwin H. -M. Sha, Lei Yang, Qingfeng Zhuge, Yiyu Shi, Jingtong Hu

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.

Neural Architecture Search

Quantization of Fully Convolutional Networks for Accurate Biomedical Image Segmentation

no code implementations CVPR 2018 Xiaowei Xu, Qing Lu, Yu Hu, Lin Yang, Sharon Hu, Danny Chen, Yiyu Shi

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.

Image Segmentation Quantization +2

PBGen: Partial Binarization of Deconvolution-Based Generators for Edge Intelligence

no code implementations26 Feb 2018 Jinglan Liu, Jiaxin Zhang, Yukun Ding, Xiaowei Xu, Meng Jiang, Yiyu Shi

This work explores the binarization of the deconvolution-based generator in a GAN for memory saving and speedup of image construction.

Binarization

On the Universal Approximability and Complexity Bounds of Quantized ReLU Neural Networks

no code implementations ICLR 2019 Yukun Ding, Jinglan Liu, JinJun Xiong, Yiyu Shi

To the best of our knowledge, this is the first in-depth study on the complexity bounds of quantized neural networks.

Quantization

Cannot find the paper you are looking for? You can Submit a new open access paper.