Search Results for author: Cheng Liu

Found 21 papers, 7 papers with code

Cross-Layer Optimization for Fault-Tolerant Deep Learning

no code implementations21 Dec 2023 Qing Zhang, Cheng Liu, Bo Liu, Haitong Huang, Ying Wang, Huawei Li, Xiaowei Li

Fault-tolerant deep learning accelerator is the basis for highly reliable deep learning processing and critical to deploy deep learning in safety-critical applications such as avionics and robotics.

Bayesian Optimization Quantization

High-resolution power equipment recognition based on improved self-attention

no code implementations6 Nov 2023 Siyi Zhang, Cheng Liu, Xiang Li, Xin Zhai, Zhen Wei, Sizhe Li, Xun Ma

The current trend of automating inspections at substations has sparked a surge in interest in the field of transformer image recognition.

Region Proposal

Exploring Winograd Convolution for Cost-effective Neural Network Fault Tolerance

no code implementations16 Aug 2023 Xinghua Xue, Cheng Liu, Bo Liu, Haitong Huang, Ying Wang, Tao Luo, Lei Zhang, Huawei Li, Xiaowei Li

When it is applied on fault-tolerant neural networks enhanced with fault-aware retraining and constrained activation functions, the resulting model accuracy generally shows significant improvement in presence of various faults.

Computational Efficiency

Whale Detection Enhancement through Synthetic Satellite Images

1 code implementation15 Aug 2023 Akshaj Gaur, Cheng Liu, Xiaomin Lin, Nare Karapetyan, Yiannis Aloimonos

With a number of marine populations in rapid decline, collecting and analyzing data about marine populations has become increasingly important to develop effective conservation policies for a wide range of marine animals, including whales.

A Deep-Learning Method Using Auto-encoder and Generative Adversarial Network for Anomaly Detection on Ancient Stone Stele Surfaces

no code implementations8 Aug 2023 Yikun Liu, Yuning Wang, Cheng Liu

Accurate detection of natural deterioration and man-made damage on the surfaces of ancient stele in the first instance is essential for their preventive conservation.

Anomaly Detection Generative Adversarial Network

Deep Learning Accelerator in Loop Reliability Evaluation for Autonomous Driving

no code implementations20 Jun 2023 Haitong Huang, Cheng Liu

The reliability of deep learning accelerators (DLAs) used in autonomous driving systems has significant impact on the system safety.

Autonomous Driving

MRFI: An Open Source Multi-Resolution Fault Injection Framework for Neural Network Processing

1 code implementation20 Jun 2023 Haitong Huang, Cheng Liu, Bo Liu, Xinghua Xue, Huawei Li, Xiaowei Li

It enables users to modify an independent fault configuration file rather than neural network models for the fault injection and vulnerability analysis.

Variation Enhanced Attacks Against RRAM-based Neuromorphic Computing System

no code implementations20 Feb 2023 Hao Lv, Bing Li, Lei Zhang, Cheng Liu, Ying Wang

The RRAM-based neuromorphic computing system has amassed explosive interests for its superior data processing capability and energy efficiency than traditional architectures, and thus being widely used in many data-centric applications.

Adversarial Attack

Text-Guided Unsupervised Latent Transformation for Multi-Attribute Image Manipulation

no code implementations CVPR 2023 Xiwen Wei, Zhen Xu, Cheng Liu, Si Wu, Zhiwen Yu, Hau San Wong

To address this limitation, we propose a Text-guided Unsupervised StyleGAN Latent Transformation (TUSLT) model, which adaptively infers a single transformation step in the latent space of StyleGAN to simultaneously manipulate multiple attributes on a given input image.

Attribute Image Manipulation +2

SeaDroneSim: Simulation of Aerial Images for Detection of Objects Above Water

1 code implementation26 Oct 2022 Xiaomin Lin, Cheng Liu, Allen Pattillo, Miao Yu, Yiannis Aloimonous

To this end, we present a new benchmark suite, SeaDroneSim, that can be used to create photo-realistic aerial image datasets with the ground truth for segmentation masks of any given object.

Statistical Modeling of Soft Error Influence on Neural Networks

no code implementations12 Oct 2022 Haitong Huang, Xinghua Xue, Cheng Liu, Ying Wang, Tao Luo, Long Cheng, Huawei Li, Xiaowei Li

Prior work mainly rely on fault simulation to analyze the influence of soft errors on NN processing.

Quantization

Fault-Tolerant Deep Learning: A Hierarchical Perspective

no code implementations5 Apr 2022 Cheng Liu, Zhen Gao, Siting Liu, Xuefei Ning, Huawei Li, Xiaowei Li

With the rapid advancements of deep learning in the past decade, it can be foreseen that deep learning will be continuously deployed in more and more safety-critical applications such as autonomous driving and robotics.

Autonomous Driving

Adaptive Risk-Tendency: Nano Drone Navigation in Cluttered Environments with Distributional Reinforcement Learning

1 code implementation28 Mar 2022 Cheng Liu, Erik-Jan van Kampen, Guido C. H. E. de Croon

Enabling the capability of assessing risk and making risk-aware decisions is essential to applying reinforcement learning to safety-critical robots like drones.

Distributional Reinforcement Learning Drone navigation +3

Winograd Convolution: A Perspective from Fault Tolerance

no code implementations17 Feb 2022 Xinghua Xue, Haitong Huang, Cheng Liu, Ying Wang, Tao Luo, Lei Zhang

Winograd convolution is originally proposed to reduce the computing overhead by converting multiplication in neural network (NN) with addition via linear transformation.

Physics Driven Deep Retinex Fusion for Adaptive Infrared and Visible Image Fusion

1 code implementation6 Dec 2021 Yuanjie Gu, Zhibo Xiao, Yinghan Guan, Haoran Dai, Cheng Liu, Liang Xue, Shouyu Wang

In this study, we show that, the structures of generative networks capture a great deal of image feature priors, and then these priors are sufficient to reconstruct high-quality fused super-resolution result using only low-resolution inputs.

Image Super-Resolution Infrared And Visible Image Fusion +1

Deep Fusion Prior for Plenoptic Super-Resolution All-in-Focus Imaging

1 code implementation12 Oct 2021 Yuanjie Gu, Yinghan Guan, Zhibo Xiao, Haoran Dai, Cheng Liu, Shouyu Wang

Multi-focus image fusion (MFIF) and super-resolution (SR) are the inverse problem of imaging model, purposes of MFIF and SR are obtaining all-in-focus and high-resolution 2D mapping of targets.

Blind Super-Resolution Image Super-Resolution

R2F: A Remote Retraining Framework for AIoT Processors with Computing Errors

no code implementations7 Jul 2021 Dawen Xu, Meng He, Cheng Liu, Ying Wang, Long Cheng, Huawei Li, Xiaowei Li, Kwang-Ting Cheng

It takes the remote AIoT processor with soft errors in the training loop such that the on-site computing errors can be learned with the application data on the server and the retrained models can be resilient to the soft errors.

Linear Symmetric Quantization of Neural Networks for Low-precision Integer Hardware

no code implementations ICLR 2020 Xiandong Zhao, Ying Wang, Xuyi Cai, Cheng Liu, Lei Zhang

With the proliferation of specialized neural network processors that operate on low-precision integers, the performance of Deep Neural Network inference becomes increasingly dependent on the result of quantization.

object-detection Object Detection +1

Accelerating Generative Neural Networks on Unmodified Deep Learning Processors -- A Software Approach

2 code implementations3 Jul 2019 Dawen Xu, Ying Wang, Kaijie Tu, Cheng Liu, Bingsheng He, Lei Zhang

Generative neural network is a new category of neural networks and it has been widely utilized in applications such as content generation, unsupervised learning, segmentation and pose estimation.

Pose Estimation

A Survey on Graph Processing Accelerators: Challenges and Opportunities

no code implementations26 Feb 2019 Chuangyi Gui, Long Zheng, Bingsheng He, Cheng Liu, Xinyu Chen, Xiaofei Liao, Hai Jin

Graph is a well known data structure to represent the associated relationships in a variety of applications, e. g., data science and machine learning.

Distributed, Parallel, and Cluster Computing

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