4.7 Article

Split Computing and Early Exiting for Deep Learning Applications: Survey and Research Challenges

相关参考文献

注意:仅列出部分参考文献,下载原文获取全部文献信息。
Article Physics, Multidisciplinary

A Probabilistic Re-Intepretation of Confidence Scores in Multi-Exit Models

Jary Pomponi et al.

Summary: This paper introduces a new approach to training deep neural networks with multiple intermediate auxiliary classifiers, which can reduce inference time while maintaining prediction accuracy. By using trained confidence scores, the multi-exit model is trained without hyper-parameters.

ENTROPY (2022)

Proceedings Paper Computer Science, Artificial Intelligence

Supervised Compression for Resource-Constrained Edge Computing Systems

Yoshitomo Matsubara et al.

Summary: This paper addresses the challenges of deploying deep learning algorithms on low-powered devices and proposes a more efficient approach for compressing intermediate feature representations. Through experimental comparisons, it is found that the proposed method achieves better supervised rate-distortion performance while maintaining low latency, and the learned feature representations can be applied to multiple downstream tasks.

2022 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV 2022) (2022)

Proceedings Paper Computer Science, Artificial Intelligence

Optimal Branch Location for Cost-effective Inference on Branchynet

Chang-Han Chiang et al.

Summary: This paper introduces the structure and optimization method of Branchynet, proposes a dynamic programming algorithm to find the optimal branch locations, and validates its effectiveness through experimental results.

2021 IEEE INTERNATIONAL CONFERENCE ON BIG DATA (BIG DATA) (2021)

Proceedings Paper Engineering, Electrical & Electronic

Retransmission Edge Computing System Conducting Adaptive Image Compression Based on Image Recognition Accuracy

Mutsuki Nakahara et al.

Summary: This paper proposes a retransmission control system based on image recognition accuracy to improve network bandwidth usage efficiency in image recognition service using wireless edge computing. By retransmitting images according to the recognition accuracy, the system aims to reduce traffic and guarantee recognition accuracy. The effectiveness of the proposed system is demonstrated through a wireless network simulation.

2021 IEEE 94TH VEHICULAR TECHNOLOGY CONFERENCE (VTC2021-FALL) (2021)

Proceedings Paper Computer Science, Artificial Intelligence

A Splittable DNN-Based Object Detector for Edge-Cloud Collaborative Real-Time Video Inference

Joo Chan Lee et al.

Summary: This paper proposes a splittable object detector that enables edge-cloud collaborative real-time video inference, with the use of a feature reconstruction network and asymmetric scaling to reduce transmitted feature size and edge inference latency while maintaining detection accuracy.

2021 17TH IEEE INTERNATIONAL CONFERENCE ON ADVANCED VIDEO AND SIGNAL BASED SURVEILLANCE (AVSS 2021) (2021)

Article Telecommunications

DEEP COMPRESSIVE OFFLOADING: Speeding Up Edge Offloading for AI Services

Shuochao Yao et al.

GETMOBILE-MOBILE COMPUTING & COMMUNICATIONS REVIEW (2021)

Proceedings Paper Computer Science, Artificial Intelligence

Neural Compression and Filtering for Edge-assisted Real-time Object Detection in Challenged Networks

Yoshitomo Matsubara et al.

Summary: This study focuses on edge computing for remote object detection through Deep Neural Networks, proposing a framework to reduce data transmission over wireless links by splitting DNNs between mobile devices and edge servers. Unlike previous work that focuses on classification tasks, this study concentrates on DNNs for three different object detection tasks and modifies the network structure for optimized results.

2020 25TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR) (2021)

Article Computer Science, Information Systems

Person Re-Identification in Aerial Imagery

Shizhou Zhang et al.

Summary: The paper introduces research on person re-identification in aerial imagery, provides a large-scale aerial person ReID dataset named PRAI-1581, and experimental results show that re-identifying persons in aerial imagery is a challenging problem.

IEEE TRANSACTIONS ON MULTIMEDIA (2021)

Article Computer Science, Hardware & Architecture

Data Security and Privacy Challenges of Computing Offloading in FINs

Fei Wang et al.

IEEE NETWORK (2020)

Article Engineering, Electrical & Electronic

Dual Dynamic Inference: Enabling More Efficient, Adaptive, and Controllable Deep Inference

Yue Wang et al.

IEEE JOURNAL OF SELECTED TOPICS IN SIGNAL PROCESSING (2020)

Proceedings Paper Computer Science, Information Systems

Reranking for Efficient Transformer-based Answer Selection

Yoshitomo Matsubara et al.

PROCEEDINGS OF THE 43RD INTERNATIONAL ACM SIGIR CONFERENCE ON RESEARCH AND DEVELOPMENT IN INFORMATION RETRIEVAL (SIGIR '20) (2020)

Proceedings Paper Acoustics

BACK-AND-FORTH PREDICTION FOR DEEP TENSOR COMPRESSION

Hyomin Choi et al.

2020 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING (2020)

Article Computer Science, Information Systems

Head Network Distillation: Splitting Distilled Deep Neural Networks for Resource-Constrained Edge Computing Systems

Yoshitomo Matsubara et al.

IEEE ACCESS (2020)

Proceedings Paper Computer Science, Theory & Methods

Fast and Accurate Streaming CNN Inference via Communication Compression on the Edge

Diyi Hu et al.

2020 ACM/IEEE FIFTH INTERNATIONAL CONFERENCE ON INTERNET OF THINGS DESIGN AND IMPLEMENTATION (IOTDI 2020) (2020)

Article Engineering, Electrical & Electronic

Deep Learning at the Physical Layer: System Challenges and Applications to 5G and Beyond

Francesco Restuccia et al.

IEEE COMMUNICATIONS MAGAZINE (2020)

Article Computer Science, Theory & Methods

A Survey on Deep Learning: Algorithms, Techniques, and Applications

Samira Pouyanfar et al.

ACM COMPUTING SURVEYS (2019)

Article Computer Science, Artificial Intelligence

Understanding autoencoders with information theoretic concepts

Shujian Yu et al.

NEURAL NETWORKS (2019)

Review Engineering, Electrical & Electronic

Deep Learning With Edge Computing: A Review

Jiasi Chen et al.

PROCEEDINGS OF THE IEEE (2019)

Article Computer Science, Information Systems

Machine learning for wireless communications in the Internet of Things: A comprehensive survey

Jithin Jagannath et al.

AD HOC NETWORKS (2019)

Article Engineering, Electrical & Electronic

Will TCP Work in mmWave 5G Cellular Networks?

Menglei Zhang et al.

IEEE COMMUNICATIONS MAGAZINE (2019)

Article Mechanics

On the information bottleneck theory of deep learning

Andrew M. Saxe et al.

JOURNAL OF STATISTICAL MECHANICS-THEORY AND EXPERIMENT (2019)

Proceedings Paper Engineering, Electrical & Electronic

Analysis of TCP Performance in 5G mm-wave Mobile Networks

Pablo Jimenez Mateo et al.

ICC 2019 - 2019 IEEE INTERNATIONAL CONFERENCE ON COMMUNICATIONS (ICC) (2019)

Proceedings Paper Computer Science, Theory & Methods

DynExit: A Dynamic Early-Exit Strategy for Deep Residual Networks

Meiqi Wang et al.

PROCEEDINGS OF THE 2019 IEEE INTERNATIONAL WORKSHOP ON SIGNAL PROCESSING SYSTEMS (SIPS 2019) (2019)

Article Computer Science, Artificial Intelligence

Neural Network Acceptability Judgments

Alex Warstadt et al.

TRANSACTIONS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (2019)

Article Computer Science, Hardware & Architecture

Learning IoT in Edge: Deep Learning for the Internet of Things with Edge Computing

He Li et al.

IEEE NETWORK (2018)

Proceedings Paper Computer Science, Artificial Intelligence

Auto-tuning Neural Network Quantization Framework for Collaborative Inference Between the Cloud and Edge

Guangli Li et al.

ARTIFICIAL NEURAL NETWORKS AND MACHINE LEARNING - ICANN 2018, PT I (2018)

Proceedings Paper Computer Science, Artificial Intelligence

Eye in the Sky: Real-time Drone Surveillance System (DSS) for Violent Individuals Identification using ScatterNet Hybrid Deep Learning Network

Amarjot Singh et al.

PROCEEDINGS 2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS (CVPRW) (2018)

Article Engineering, Electrical & Electronic

Understanding the Limits of LoRaWAN

Ferran Adelantado et al.

IEEE COMMUNICATIONS MAGAZINE (2017)

Article Computer Science, Information Systems

A Survey on Mobile Edge Computing: The Communication Perspective

Yuyi Mao et al.

IEEE COMMUNICATIONS SURVEYS AND TUTORIALS (2017)

Article Multidisciplinary Sciences

Mastering the game of Go without human knowledge

David Silver et al.

NATURE (2017)

Proceedings Paper Computer Science, Software Engineering

Neurosurgeon: Collaborative Intelligence Between the Cloud and Mobile Edge

Yiping Kang et al.

OPERATING SYSTEMS REVIEW (2017)

Proceedings Paper Computer Science, Hardware & Architecture

Neurosurgeon: Collaborative Intelligence Between the Cloud and Mobile Edge

Yiping Kang et al.

TWENTY-SECOND INTERNATIONAL CONFERENCE ON ARCHITECTURAL SUPPORT FOR PROGRAMMING LANGUAGES AND OPERATING SYSTEMS (ASPLOS XXII) (2017)

Proceedings Paper Computer Science, Artificial Intelligence

Densely Connected Convolutional Networks

Gao Huang et al.

30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017) (2017)

Proceedings Paper Computer Science, Artificial Intelligence

Mask R-CNN

Kaiming He et al.

2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV) (2017)

Proceedings Paper Computer Science, Artificial Intelligence

Channel Pruning for Accelerating Very Deep Neural Networks

Yihui He et al.

2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV) (2017)

Article Computer Science, Information Systems

Survey of Important Issues in UAV Communication Networks

Lav Gupta et al.

IEEE COMMUNICATIONS SURVEYS AND TUTORIALS (2016)

Proceedings Paper Computer Science, Hardware & Architecture

IoT Technologies for Embedded Computing: A Survey

Farzad Samie et al.

2016 INTERNATIONAL CONFERENCE ON HARDWARE/SOFTWARE CODESIGN AND SYSTEM SYNTHESIS (CODES+ISSS) (2016)

Article Computer Science, Artificial Intelligence

ImageNet Large Scale Visual Recognition Challenge

Olga Russakovsky et al.

INTERNATIONAL JOURNAL OF COMPUTER VISION (2015)

Review Multidisciplinary Sciences

Deep learning

Yann LeCun et al.

NATURE (2015)

Article Engineering, Electrical & Electronic

Deep Neural Networks for Acoustic Modeling in Speech Recognition

Geoffrey Hinton et al.

IEEE SIGNAL PROCESSING MAGAZINE (2012)

Article Computer Science, Artificial Intelligence

One-shot learning of object categories

FF Li et al.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2006)