arxiv: 2605.06714 · v1 · submitted 2026-05-07 · 💻 cs.CV · cs.AI

Recognition: 2 theorem links

· Lean Theorem

Edge Deep Learning in Computer Vision and Medical Diagnostics: A Comprehensive Survey

Yiwen Xu , Tariq M. Khan , Yang Song , Erik Meijering

Authors on Pith no claims yet

Pith reviewed 2026-05-11 01:16 UTC · model grok-4.3

classification 💻 cs.CV cs.AI

keywords edge deep learningcomputer visionmedical diagnosticsedge computingmodel compressionhardware platformsdeep neural networksreal-time processing

0 comments

The pith

A survey of edge deep learning in computer vision and medical diagnostics introduces a novel categorization of edge hardware platforms based on performance and usage scenarios.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper reviews the integration of deep learning models with edge computing resources to enable real-time, context-aware decisions in computer vision tasks. It emphasizes applications in medical diagnostics where on-device processing can improve speed and privacy. A new categorization of hardware platforms is presented to guide selection according to performance levels and typical usage. Implementation techniques such as lightweight network design and model compression are examined to fit models onto constrained devices. The work concludes by outlining applications, obstacles, and directions for future development.

Core claim

The paper establishes that edge deep learning reconciles computational resources with data sources at the edge to support real-time decisions, and that a novel categorization of edge hardware platforms organized by performance and usage scenarios facilitates platform selection and operational effectiveness for computer vision and medical diagnostic applications.

What carries the argument

The novel categorization of edge hardware platforms based on performance and usage scenarios, which organizes platforms to support selection and effective deployment of deep learning models.

If this is right

Lightweight design and model compression methods enable deep neural networks to run efficiently on resource-limited edge devices.
Medical diagnostics applications achieve real-time decision making attuned to environmental factors when models are deployed at the edge.
Analysis of obstacles to adoption points toward targeted advancements that can accelerate intelligent edge solutions.
The categorization supports operational effectiveness across a wide range of computer vision domains beyond medicine.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

The same hardware categorization could be tested for fit in non-medical domains such as autonomous navigation or industrial inspection to check its generality.
Empirical trials that measure selection time and deployment success rates before and after applying the categories would provide direct evidence of practical value.
Extending the categories to incorporate power-consumption or thermal constraints might address additional barriers specific to portable medical devices.
Linkage with privacy regulations could show how on-device inference reduces data transmission risks in diagnostic workflows.

Load-bearing premise

The reviewed body of literature is sufficiently comprehensive and representative to support both the overview and the proposed novel hardware categorization.

What would settle it

A demonstration that many prominent edge hardware platforms fall outside the proposed performance-and-scenario categories or that using the categories does not measurably improve selection outcomes in practice would undermine the central claim.

read the original abstract

Edge deep learning, a paradigm change reconciling edge computing and deep learning, facilitates real-time decision making attuned to environmental factors through the close integration of computational resources and data sources. Here we provide a comprehensive review of the current state of the art in edge deep learning, focusing on computer vision applications, in particular medical diagnostics. An overview of the foundational principles and technical advantages of edge deep learning is presented, emphasising the capacity of this technology to revolutionise a wide range of domains. Furthermore, we present a novel categorisation of edge hardware platforms based on performance and usage scenarios, facilitating platform selection and operational effectiveness. Following this, we dive into approaches to effectively implement deep neural networks on edge devices, encompassing methods such as lightweight design and model compression. Reviewing practical applications in the fields of computer vision in general and medical diagnostics in particular, we demonstrate the profound impact edge-deployed deep learning models can have in real-life situations. Finally, we provide an analysis of potential future directions and obstacles to the adoption of edge deep learning, with the intention to stimulate further investigations and advancements of intelligent edge deep learning solutions. This survey provides researchers and practitioners with a comprehensive reference shedding light on the critical role deep learning plays in the advancement of edge computing applications.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Desk Editor's Note private letter to a colleague

A standard survey on edge DL for CV and medical imaging that proposes a hardware categorization without showing its review methodology.

read the letter

This survey pulls together existing work on running deep learning models at the edge for computer vision, with a focus on medical diagnostics. It covers the basics of combining edge computing with neural nets, the advantages for real-time local decisions, and ways to shrink models so they fit on limited hardware. The authors also walk through applications in diagnostics and list some future challenges like power use and data privacy. The one new element they highlight is a categorization of edge hardware platforms by performance and usage scenarios, meant to help with platform choice. That framing could be handy for someone picking devices for a medical imaging project. The paper does a reasonable job organizing the implementation side, including compression techniques and lightweight designs, and it ties those to concrete diagnostic uses. The future directions section is straightforward about barriers to wider adoption. The soft spot is the lack of any description of how the literature was gathered or filtered. No search strings, databases, paper counts, or inclusion rules appear, so the novel categorization rests on an opaque selection process. That makes it hard to judge whether the categories are comprehensive or just reflect what the authors read, and it risks duplicating prior surveys without adding clear value. This is the sort of reference that helps newcomers or practitioners who need a single place to start on edge AI for healthcare. Experts already in the area will probably skim it for the applications list and move on. I would bring it to a reading group if the group is looking at applied medical imaging work, but only as background. I would not cite it in my own papers. It deserves peer review because the topic is timely and the structure is usable, but reviewers will need to see the review protocol added and the categorization justified against existing ones.

Referee Report

2 major / 2 minor

Summary. The manuscript is a survey on edge deep learning for computer vision applications, with emphasis on medical diagnostics. It reviews foundational principles and advantages, introduces a novel categorization of edge hardware platforms based on performance and usage scenarios, covers implementation techniques such as lightweight DNN design and model compression, discusses real-world applications in CV and medical diagnostics, and outlines future directions and adoption challenges.

Significance. A well-supported novel categorization of edge hardware could aid platform selection for real-time CV and medical tasks, adding value to the growing literature on edge AI. The survey's utility depends on transparent synthesis of the reviewed works; without it, the categorization risks being perceived as ad hoc rather than systematically derived.

major comments (2)

[Abstract and §1] Abstract and §1 (Introduction): The central claim of a 'novel categorisation of edge hardware platforms based on performance and usage scenarios' is asserted without any description of the literature review protocol (databases searched, search strings, inclusion/exclusion criteria, total papers reviewed, or synthesis method). This is load-bearing for the claim that the categorization facilitates platform selection, as it prevents assessment of completeness or selection bias.
[§3] §3 (Hardware categorization section): The proposed categories are presented as derived from the state of the art, yet no mapping is shown from specific reviewed papers to the categories, nor is there discussion of how performance metrics or usage scenarios were standardized across heterogeneous hardware reports. This leaves the novelty and operational usefulness of the taxonomy unverified.

minor comments (2)

[Abstract] The abstract and introduction could more explicitly state the scope boundaries (e.g., time period covered, exclusion of non-CV edge DL work) to help readers gauge coverage.
[Figures and Tables] Figure captions and table headings in the hardware and applications sections should include source references or paper counts per category for traceability.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for their thoughtful and constructive review of our survey manuscript. We address each major comment below and have revised the manuscript to improve methodological transparency.

read point-by-point responses

Referee: [Abstract and §1] Abstract and §1 (Introduction): The central claim of a 'novel categorisation of edge hardware platforms based on performance and usage scenarios' is asserted without any description of the literature review protocol (databases searched, search strings, inclusion/exclusion criteria, total papers reviewed, or synthesis method). This is load-bearing for the claim that the categorization facilitates platform selection, as it prevents assessment of completeness or selection bias.

Authors: We agree that explicitly documenting the literature review protocol would strengthen the paper and enable readers to evaluate the categorization's completeness and potential biases. The original manuscript did not include a dedicated description of the review process. In the revised version, we will add a new subsection (e.g., in §1 or as §2.1) that outlines the databases searched (IEEE Xplore, ACM Digital Library, PubMed, Google Scholar, arXiv), search strings (combinations of 'edge deep learning', 'edge AI hardware', 'lightweight DNN', 'computer vision', 'medical diagnostics'), inclusion/exclusion criteria (peer-reviewed works and preprints from 2015 onward focused on edge deployment for CV or medical applications), approximate total papers reviewed, and the thematic synthesis approach used to group hardware by performance tiers and usage scenarios. This addition will support the claim that the categorization aids platform selection. revision: yes
Referee: [§3] §3 (Hardware categorization section): The proposed categories are presented as derived from the state of the art, yet no mapping is shown from specific reviewed papers to the categories, nor is there discussion of how performance metrics or usage scenarios were standardized across heterogeneous hardware reports. This leaves the novelty and operational usefulness of the taxonomy unverified.

Authors: We concur that providing explicit mappings and details on metric standardization would make the taxonomy more verifiable and operationally useful. The original §3 presents the categories without these elements. In the revision, we will augment §3 with a table mapping representative papers from the reviewed literature to each category, including extracted performance metrics (latency, power, throughput) and usage scenarios. We will also add a paragraph discussing standardization: metrics were aligned to common units where reported values allowed (e.g., FPS or mJ/inference), with original experimental conditions noted and limitations from heterogeneous reporting acknowledged. This will demonstrate the systematic basis and practical value of the categorization. revision: yes

Circularity Check

0 steps flagged

Survey paper presents no derivations, predictions, or fitted quantities

full rationale

This is a literature review surveying edge deep learning for computer vision and medical diagnostics. It contains no mathematical derivations, no equations, no parameter fitting, no predictions of new quantities, and no self-citation chains used to justify uniqueness theorems or ansatzes. The novel hardware categorization is presented as a synthesis of reviewed work rather than a formal derivation that reduces to its own inputs by construction. Per the hard rules, no circularity can be claimed without quoting a specific reduction (e.g., Eq. X = Eq. Y by definition or a fitted parameter renamed as prediction), which is absent here. The work is therefore self-contained as a review and receives the default non-finding score.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

No free parameters, axioms, or invented entities are introduced; the contribution rests on selection and synthesis of prior literature.

pith-pipeline@v0.9.0 · 5526 in / 1036 out tokens · 47400 ms · 2026-05-11T01:16:04.943589+00:00 · methodology

discussion (0)

Lean theorems connected to this paper

Citations machine-checked in the Pith Canon. Every link opens the source theorem in the public Lean library.

IndisputableMonolith/Foundation/AbsoluteFloorClosure.lean; IndisputableMonolith/Cost/FunctionalEquation.lean reality_from_one_distinction; washburn_uniqueness_aczel unclear

?

unclear
Relation between the paper passage and the cited Recognition theorem.

we present a novel categorisation of edge hardware platforms based on performance and usage scenarios... low-end, medium-range, and high-performance devices (Fig. 3, Table 2)
IndisputableMonolith/Foundation/BranchSelection.lean; IndisputableMonolith/Foundation/AlphaCoordinateFixation.lean branch_selection; J_uniquely_calibrated_via_higher_derivative unclear

?

unclear
Relation between the paper passage and the cited Recognition theorem.

methods such as lightweight design and model compression... network pruning, sparse representation, quantised neural networks, MobileNet

What do these tags mean?

matches: The paper's claim is directly supported by a theorem in the formal canon.
supports: The theorem supports part of the paper's argument, but the paper may add assumptions or extra steps.
extends: The paper goes beyond the formal theorem; the theorem is a base layer rather than the whole result.
uses: The paper appears to rely on the theorem as machinery.
contradicts: The paper's claim conflicts with a theorem or certificate in the canon.
unclear: Pith found a possible connection, but the passage is too broad, indirect, or ambiguous to say the theorem truly supports the claim.

Reference graph

Works this paper leans on

300 extracted references · 300 canonical work pages · 8 internal anchors

[1]

, Zhang , Y

barticle Abbas , N. , Zhang , Y. , Taherkordi , A. , Skeie , T. : Mobile edge computing: A survey . IEEE Internet of Things Journal 5 ( 1 ), 450 -- 465 ( 2017 ) barticle

work page 2017
[2]

, Samara , L

barticle Abdellatif , A.A. , Samara , L. , Mohamed , A. , Erbad , A. , Chiasserini , C.F. , Guizani , M. , O’Connor , M.D. , Laughton , J. : MEdge-Chain : Leveraging edge computing and blockchain for efficient medical data exchange . IEEE Internet of Things Journal 8 ( 21 ), 15762 -- 15775 ( 2021 ) barticle

work page 2021
[3]

, Silva , M.J

botherref Abrantes , J. , Silva , M.J. , Meneses , J. , Oliveira , C. , Calisto , F.M. , Filice , R. : External validation of a deep learning model for breast density classification. ESR—European Society of Radiology: Vienna, Austria (2023) botherref

work page 2023
[4]

, Hayajneh , M

barticle Abreha , H.G. , Hayajneh , M. , Serhani , M.A. : Federated learning in edge computing: a systematic survey . Sensors 22 ( 2 ), 450 ( 2022 ) barticle

work page 2022
[5]

, Baskar , S

barticle Abubeker , K. , Baskar , S. : B2-Net : An artificial intelligence powered machine learning framework for the classification of pneumonia in chest X-ray images . Machine Learning: Science and Technology 4 ( 1 ), 015036 ( 2023 ) barticle

work page 2023
[6]

, Mohtaram , N

bchapter Achakir , F. , Mohtaram , N. , Escartin , A. : An automated AI -based solution for out-of-stock detection in retail environments . In: International Conference on Electrical, Computer, Communications and Mechatronics Engineering (ICECCME) , pp. 1 -- 6 ( 2023 ) bchapter

work page 2023
[7]

, Falcone , G.J

barticle Acosta , J.N. , Falcone , G.J. , Rajpurkar , P. , Topol , E.J. : Multimodal biomedical AI . Nature Medicine 28 ( 9 ), 1773 -- 1784 ( 2022 ) barticle

work page 2022
[8]

, Masood , M

barticle Albattah , W. , Masood , M. , Javed , A. , Nawaz , M. , Albahli , S. : Custom CornerNet : A drone-based improved deep learning technique for large-scale multiclass pest localization and classification . Complex & Intelligent Systems 9 ( 2 ), 1299 -- 1316 ( 2023 ) barticle

work page 2023
[9]

, Polimante , S

bchapter Albuquerque , C.K. , Polimante , S. , Torre-Neto , A. , Prati , R.C. : Water spray detection for smart irrigation systems with Mask R-CNN and UAV footage . In: IEEE International Workshop on Metrology for Agriculture and Forestry (MetroAgriFor) , pp. 236 -- 240 ( 2020 ) bchapter

work page 2020
[10]

, Klyachin , V

bchapter Alexey , G. , Klyachin , V. , Eldar , K. , Driaba , A. : Autonomous mobile robot with AI based on Jetson Nano . In: Future Technologies Conference (FTC) , pp. 190 -- 204 ( 2021 ) bchapter

work page 2021
[11]

, Gregory , M.A

barticle Ali , B. , Gregory , M.A. , Li , S. : Multi-access edge computing architecture, data security and privacy: A review . IEEE Access 9 , 18706 -- 18721 ( 2021 ) barticle

work page 2021
[12]

: An overview of fog computing and edge computing security and privacy issues

barticle Alwakeel , A.M. : An overview of fog computing and edge computing security and privacy issues . Sensors 21 ( 24 ), 8226 ( 2021 ) barticle

work page 2021
[13]

, Partel , V

barticle Ampatzidis , Y. , Partel , V. : UAV -based high throughput phenotyping in citrus utilizing multispectral imaging and artificial intelligence . Remote Sensing 11 ( 4 ), 410 ( 2019 ) barticle

work page 2019
[14]

, Duan , Z

bchapter Angus , A. , Duan , Z. , Zussman , G. , Kosti \'c , Z. : Real-time video anonymization in smart city intersections . In: IEEE International Conference on Mobile Ad Hoc and Smart Systems (MASS) , pp. 514 -- 522 ( 2022 ) bchapter

work page 2022
[15]

, Barthelemy , J

bchapter Arshad , B. , Barthelemy , J. , Pilton , E. , Perez , P. : Where is my deer? Wildlife tracking and counting via edge computing and deep learning . In: IEEE SENSORS , pp. 1 -- 4 ( 2020 ) bchapter

work page 2020
[16]

, Banerjee , S

barticle ASGE Technology Committee , Wang , A. , Banerjee , S. , Barth , B.A. , Bhat , Y.M. , Chauhan , S. , Gottlieb , K.T. , Konda , V. , Maple , J.T. , Murad , F. , Pfau , P.R. , Pleskow , D.K. , Siddiqui , U.D. , Tokar , J.L. , Rodriguez , S.A. : Wireless capsule endoscopy . Gastrointestinal Endoscopy 78 ( 6 ), 805 -- 815 ( 2013 ) barticle

work page 2013
[17]

, Palsana , D

barticle Auguste , L. , Palsana , D. : Mobile Whole Slide Imaging (mWSI) : A low resource acquisition and transport technique for microscopic pathological specimens . BMJ Innovations 1 ( 3 ), 137 -- 143 ( 2015 ) barticle

work page 2015
[18]

, Hasanuddin , I

botherref Aulia , U. , Hasanuddin , I. , Dirhamsyah , M. , Nasaruddin , N. : A new CNN-based object detection system for autonomous mobile robots based on real-world vehicle datasets. Heliyon 10(15) (2024) botherref

work page 2024
[19]

, Bongiovanni , M

bchapter Avvenuti , M. , Bongiovanni , M. , Ciampi , L. , Falchi , F. , Gennaro , C. , Messina , N. : A spatio-temporal attentive network for video-based crowd counting . In: IEEE Symposium on Computers and Communications (ISCC) , pp. 1 -- 6 ( 2022 ) bchapter

work page 2022
[20]

, Takalo-Mattila , J

bchapter Azimi , I. , Takalo-Mattila , J. , Anzanpour , A. , Rahmani , A.M. , Soininen , J.-P. , Liljeberg , P. : Empowering healthcare IoT systems with hierarchical edge-based deep learning . In: IEEE/ACM International Conference on Connected Health: Applications, Systems and Engineering Technologies (CHASE) , pp. 63 -- 68 ( 2018 ) bchapter

work page 2018
[21]

, Khan , M.S

barticle Babar , M. , Khan , M.S. , Ali , F. , Imran , M. , Shoaib , M. : Cloudlet computing: Recent advances, taxonomy, and challenges . IEEE Access 9 , 29609 -- 29622 ( 2021 ) barticle

work page 2021
[22]

, Chen , J

bchapter Bai , S. , Chen , J. , Shen , X. , Qian , Y. , Liu , Y. : Unified data-free compression: Pruning and quantization without fine-tuning . In: IEEE/CVF International Conference on Computer Vision (ICCV) , pp. 5876 -- 5885 ( 2023 ) bchapter

work page 2023
[23]

, Zhou , C

bchapter Banbury , C. , Zhou , C. , Fedorov , I. , Navarro , R.M. , Thakker , U. , Gope , D. , Reddi , V.J. , Mattina , M. , Whatmough , P.N. : MicroNets : Neural network architectures for deploying TinyML applications on commodity microcontrollers . In: Machine Learning and Systems (MLSys) , pp. 1 -- 16 ( 2021 ) bchapter

work page 2021
[24]

, Lafata , K.J

barticle Barisoni , L. , Lafata , K.J. , Hewitt , S.M. , Madabhushi , A. , Balis , U.G. : Digital pathology and computational image analysis in nephropathology . Nature Reviews Nephrology 16 ( 11 ), 669 -- 685 ( 2020 ) barticle

work page 2020
[25]

, Klatt , S

bchapter Baumgartner , T. , Klatt , S. : Monocular 3D human pose estimation for sports broadcasts using partial sports field registration . In: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) , pp. 5108 -- 5117 ( 2023 ) bchapter

work page 2023
[26]

A comprehensive survey on hardware-aware neural architecture search,

botherref Benmeziane , H. , Maghraoui , K.E. , Ouarnoughi , H. , Niar , S. , Wistuba , M. , Wang , N. : A comprehensive survey on hardware-aware neural architecture search. arXiv:2101.09336 (2021) botherref

work page arXiv 2021
[27]

, Diffenderfer , J

bchapter Bhardwaj , K. , Diffenderfer , J. , Kailkhura , B. , Gokhale , M. : Unsupervised test-time adaptation of deep neural networks at the edge: A case study . In: Design, Automation & Test in Europe Conference & Exhibition (DATE) , pp. 412 -- 417 ( 2022 ) bchapter

work page 2022
[28]

, Wittek , P

barticle Biamonte , J. , Wittek , P. , Pancotti , N. , Rebentrost , P. , Wiebe , N. , Lloyd , S. : Quantum machine learning . Nature 549 ( 7671 ), 195 -- 202 ( 2017 ) barticle

work page 2017
[29]

YOLOv4: Optimal Speed and Accuracy of Object Detection

botherref Bochkovskiy , A. , Wang , C.-Y. , Liao , H.-Y.M. : YOLOv4 : Optimal speed and accuracy of object detection. arXiv:2004.10934 (2020) botherref

work page internal anchor Pith review arXiv 2004
[30]

, Kondapalli , S.S

barticle Bonam , J. , Kondapalli , S.S. , Prasad , L. , Marlapalli , K. : Lightweight CNN models for product defect detection with edge computing in manufacturing industries . Journal of Scientific & Industrial Research 82 ( 04 ), 418 -- 425 ( 2023 ) barticle

work page 2023
[31]

, Milito , R

bchapter Bonomi , F. , Milito , R. , Zhu , J. , Addepalli , S. : Fog computing and its role in the internet of things . In: Workshop on Mobile Cloud Computing (MCC) , pp. 13 -- 16 ( 2012 ) bchapter

work page 2012
[32]

: Large-scale machine learning with stochastic gradient descent

bchapter Bottou , L. : Large-scale machine learning with stochastic gradient descent . In: International Conference on Computational Statistics (COMPSTAT) , pp. 177 -- 186 ( 2010 ) bchapter

work page 2010
[33]

, Kajati , E

barticle Brecko , A. , Kajati , E. , Koziorek , J. , Zolotova , I. : Federated learning for edge computing: A survey . Applied Sciences 12 ( 18 ), 9124 ( 2022 ) barticle

work page 2022
[34]

, Hishamuddin , T.A

barticle Caesarendra , W. , Hishamuddin , T.A. , Lai , D.T.C. , Husaini , A. , Nurhasanah , L. , Glowacz , A. , Alfarisy , G.A.F. : An embedded system using convolutional neural network model for online and real-time ECG signal classification and prediction . Diagnostics 12 ( 4 ), 795 ( 2022 ) barticle

work page 2022
[35]

ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware

botherref Cai , H. , Zhu , L. , Han , S. : ProxylessNAS : Direct neural architecture search on target task and hardware. arXiv:1812.00332 (2018) botherref

work page Pith review arXiv 2018
[36]

, Nunes , N

barticle Calisto , F.M. , Nunes , N. , Nascimento , J.C. : Modeling adoption of intelligent agents in medical imaging . International Journal of Human-Computer Studies 168 , 102922 ( 2022 ) barticle

work page 2022
[37]

: Medical imaging multimodality breast cancer diagnosis user interface

botherref Calisto , F.M. : Medical imaging multimodality breast cancer diagnosis user interface. Master's thesis. Instituto Superior T \'e cnico, Avenida Rovisco Pais 1 (2017) botherref

work page 2017
[38]

, Liu , Y

barticle Cao , K. , Liu , Y. , Meng , G. , Sun , Q. : An overview on edge computing research . IEEE Access 8 , 85714 -- 85728 ( 2020 ) barticle

work page 2020
[39]

, Song , P

barticle Cao , L. , Song , P. , Wang , Y. , Yang , Y. , Peng , B. : An improved lightweight real-time detection algorithm based on the edge computing platform for UAV images . Electronics 12 ( 10 ), 2274 ( 2023 ) barticle

work page 2023
[40]

, Shen , W

barticle Cao , W. , Shen , W. , Zhang , Z. , Qin , J. : Privacy-preserving healthcare monitoring for IoT devices under edge computing . Computers & Security 134 , 103464 ( 2023 ) barticle

work page 2023
[41]

: Nvidia makes it easy to embed AI : The Jetson Nano packs a lot of machine-learning power into DIY projects

barticle Cass , S. : Nvidia makes it easy to embed AI : The Jetson Nano packs a lot of machine-learning power into DIY projects . IEEE Spectrum 57 ( 7 ), 14 -- 16 ( 2020 ) barticle

work page 2020
[42]

, Ramos , J.S

barticle Cazzolato , M.T. , Ramos , J.S. , Rodrigues , L.S. , Scabora , L.C. , Chino , D.Y. , Jorge , A.E. , Azevedo-Marques , P.M. , Traina Jr , C. , Traina , A.J. : The UTrack framework for segmenting and measuring dermatological ulcers through telemedicine . Computers in Biology and Medicine 134 , 104489 ( 2021 ) barticle

work page 2021
[43]

, Crupi , L

botherref Cereda , E. , Crupi , L. , Risso , M. , Burrello , A. , Benini , L. , Giusti , A. , Pagliari , D.J. , Palossi , D. : Deep neural network architecture search for accurate visual pose estimation aboard nano-UAVs . arXiv:2303.01931 (2023) botherref

work page arXiv 2023
[44]

, Narayanan , P

barticle Chang , H.-Y. , Narayanan , P. , Lewis , S.C. , Farinha , N.C. , Hosokawa , K. , Mackin , C. , Tsai , H. , Ambrogio , S. , Chen , A. , Burr , G.W. : AI hardware acceleration with analog memory: Microarchitectures for low energy at high speed . IBM Journal of Research and Development 63 ( 6 ), 8 -- 1814 ( 2019 ) barticle

work page 2019
[45]

, Jie , W

bchapter Chang , R. , Jie , W. , Thakur , N. , Zhao , Z. , Pahwa , R.S. , Yang , X. : A unified and adaptive continual learning method for feature segmentation of buried packages in 3D XRM images . In: IEEE Electronic Components and Technology Conference (ECTC) , pp. 1872 -- 1879 ( 2024 ) bchapter

work page 2024
[46]

, Ford , J

bchapter Chavan , S. , Ford , J. , Yu , X. , Saniie , J. : Plant species image recognition using artificial intelligence on Jetson Nano computational platform . In: IEEE International Conference on Electro Information Technology (EIT) , pp. 350 -- 354 ( 2021 ) bchapter

work page 2021
[47]

, Ran , X

barticle Chen , J. , Ran , X. : Deep learning with edge computing: A review . Proceedings of the IEEE 107 ( 8 ), 1655 -- 1674 ( 2019 ) barticle

work page 2019
[48]

, Zhao , H.-M

barticle Chen , X.-L. , Zhao , H.-M. , Li , P.-X. , Yin , Z.-Y. : Remote sensing image-based analysis of the relationship between urban heat island and land use/cover changes . Remote Sensing of Environment 104 ( 2 ), 133 -- 146 ( 2006 ) barticle

work page 2006
[49]

, Zhao , Q

barticle Chen , Y. , Zhao , Q. , Hu , X. , Hu , B. : Multi-resolution parallel magnetic resonance image reconstruction in mobile computing-based IoT . IEEE Access 7 , 15623 -- 15633 ( 2019 ) barticle

work page 2019
[50]

, Zhou , Y

bchapter Chen , L. , Zhou , Y. , Zhou , H. , Zu , J. : Detection of polarizer surface defects based on an improved lightweight YOLOv3 model . In: International Conference on Intelligent Control, Measurement and Signal Processing (ICMSP) , pp. 138 -- 142 ( 2022 ) bchapter

work page 2022
[51]

, Zhong , F

bchapter Chen , Z. , Zhong , F. , Luo , Q. , Zhang , X. , Zheng , Y. : EdgeViT : Efficient visual modeling for edge computing . In: International Conference on Wireless Algorithms, Systems, and Applications (WASA) , pp. 393 -- 405 ( 2022 ) bchapter

work page 2022
[52]

, Bakhshi , A

bchapter Chen , B. , Bakhshi , A. , Batista , G. , Ng , B. , Chin , T.-J. : Update compression for deep neural networks on the edge . In: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) , pp. 3076 -- 3086 ( 2022 ) bchapter

work page 2022
[53]

, Scabora , L.C

barticle Chino , D.Y. , Scabora , L.C. , Cazzolato , M.T. , Jorge , A.E. , Traina-Jr , C. , Traina , A.J. : Segmenting skin ulcers and measuring the wound area using deep convolutional networks . Computer Methods and Programs in Biomedicine 191 , 105376 ( 2020 ) barticle

work page 2020
[54]

, Chen , W.-T

bchapter Chung , C.-C. , Chen , W.-T. , Chang , Y.-C. : Using quantization-aware training technique with post-training fine-tuning quantization to implement a MobileNet hardware accelerator . In: Indo-Taiwan International Conference on Computing, Analytics and Networks (Indo-Taiwan ICAN) , pp. 28 -- 32 ( 2020 ) bchapter

work page 2020
[55]

, Deliege , A

bchapter Cioppa , A. , Deliege , A. , Giancola , S. , Ghanem , B. , Droogenbroeck , M.V. , Gade , R. , Moeslund , T.B. : A context-aware loss function for action spotting in soccer videos . In: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) , pp. 13126 -- 13136 ( 2020 ) bchapter

work page 2020
[56]

, Jensen , C.D

barticle Corley , D.A. , Jensen , C.D. , Marks , A.R. , Zhao , W.K. , Lee , J.K. , Doubeni , C.A. , Zauber , A.G. , Boer , J. , Fireman , B.H. , Schottinger , J.E. , Quinn , V.P. , Ghai , N.R. , Levin , T.R. , Quesenberry , C.P. : Adenoma detection rate and risk of colorectal cancer and death . New England Journal of Medicine 370 ( 14 ), 1298 -- 1306 ( 20...

work page 2014
[57]

, Hu , R

barticle Cui , X. , Hu , R. : Application of intelligent edge computing technology for video surveillance in human movement recognition and Taekwondo training . Alexandria Engineering Journal 61 ( 4 ), 2899 -- 2908 ( 2022 ) barticle

work page 2022
[58]

: A neural network application for impedance-based plant monitoring: From a development framework towards edge computing

botherref Cum , F. : A neural network application for impedance-based plant monitoring: From a development framework towards edge computing. PhD Thesis, Politecnico di Torino (2022) botherref

work page 2022
[59]

, Spasi \'c , I

bchapter Dai , X. , Spasi \'c , I. , Meyer , B. , Chapman , S. , Andres , F. : Machine learning on mobile: An on-device inference app for skin cancer detection . In: International Conference on Fog and Mobile Edge Computing (FMEC) , pp. 301 -- 305 ( 2019 ) bchapter

work page 2019
[60]

, Mujeeb , A

barticle Dai , W. , Mujeeb , A. , Erdt , M. , Sourin , A. : Soldering defect detection in automatic optical inspection . Advanced Engineering Informatics 43 , 101004 ( 2020 ) barticle

work page 2020
[61]

, Hassan , S.I

barticle Dang , L.M. , Hassan , S.I. , Suhyeon , I. , Sangaiah , A. , Mehmood , I. , Rho , S. , Seo , S. , Moon , H. : UAV based wilt detection system via convolutional neural networks . Sustainable Computing: Informatics and Systems 28 , 100250 ( 2020 ) barticle

work page 2020
[62]

, Chakrabarti , B.K

barticle Das , A. , Chakrabarti , B.K. : Colloquium: Quantum annealing and analog quantum computation . Reviews of Modern Physics 80 ( 3 ), 1061 ( 2008 ) barticle

work page 2008
[63]

, Sharma , D.K

barticle Datta Gupta , K. , Sharma , D.K. , Ahmed , S. , Gupta , H. , Gupta , D. , Hsu , C.-H. : A novel lightweight deep learning-based histopathological image classification model for IoMT . Neural Processing Letters 55 ( 1 ), 205 -- 228 ( 2023 ) barticle

work page 2023
[64]

, Seliya , N

botherref Dave , R. , Seliya , N. , Siddiqui , N. : The benefits of edge computing in healthcare, smart cities, and IoT . arXiv:2112.01250 (2021) botherref

work page arXiv 2021
[65]

, Foggia , P

bchapter De Simone , G. , Foggia , P. , Saggese , A. , Vento , M. : Autonomous mobile robot for automatic out of stock detection in a supermarket . In: IEEE/CVF International Conference on Computer Vision (ICCV) , pp. 1829 -- 1838 ( 2023 ) bchapter

work page 2023
[66]

, Bessa , M.A

barticle Dekhovich , A. , Bessa , M.A. : Continual learning for surface defect segmentation by subnetwork creation and selection . Journal of Intelligent Manufacturing 36 , 3051 -- 3065 (2024) barticle

work page 2024
[67]

, Saab , K

bchapter Delbrouck , J.-b. , Saab , K. , Varma , M. , Eyuboglu , S. , Chambon , P. , Dunnmon , J. , Zambrano , J. , Chaudhari , A. , Langlotz , C. : ViLMedic : a framework for research at the intersection of vision and language in medical AI . In: Annual Meeting of the Association for Computational Linguistics (ACL): System Demonstrations , pp. 23 -- 34 (...

work page 2022
[68]

, Chiang , H.-H

barticle Deng , Z.-Y. , Chiang , H.-H. , Kang , L.-W. , Li , H.-C. : A lightweight deep learning model for real-time face recognition . IET Image Processing 17 ( 13 ), 3869 -- 3883 ( 2023 ) barticle

work page 2023
[69]

, Carrara , F

barticle Di Benedetto , M. , Carrara , F. , Ciampi , L. , Falchi , F. , Gennaro , C. , Amato , G. : An embedded toolset for human activity monitoring in critical environments . Expert Systems with Applications 199 , 117125 ( 2022 ) barticle

work page 2022
[70]

, Yao , Z

bchapter Dong , Z. , Yao , Z. , Gholami , A. , Mahoney , M.W. , Keutzer , K. : Hawq: Hessian aware quantization of neural networks with mixed-precision . In: IEEE/CVF International Conference on Computer Vision (ICCV) , pp. 293 -- 302 ( 2019 ) bchapter

work page 2019
[71]

, Ning , Z

barticle Dong , P. , Ning , Z. , Obaidat , M.S. , Jiang , X. , Guo , Y. , Hu , X. , Hu , B. , Sadoun , B. : Edge computing based healthcare systems: Enabling decentralized health monitoring in internet of medical things . IEEE Network 34 ( 5 ), 254 -- 261 ( 2020 ) barticle

work page 2020
[72]

, Wang , P

barticle Dong , S. , Wang , P. , Abbas , K. : A survey on deep learning and its applications . Computer Science Review 40 , 100379 ( 2021 ) barticle

work page 2021
[73]

, Li , T.Z

bchapter Dong , C. , Li , T.Z. , Xu , K. , Wang , Z. , Maldonado , F. , Sandler , K. , Landman , B.A. , Huo , Y. : Characterizing browser-based medical imaging AI with serverless edge computing: Towards addressing clinical data security constraints . In: SPIE Medical Imaging: Imaging Informatics for Healthcare, Research, and Applications , vol. 12469 ( 20...

work page 2023
[74]

, He , Q

bchapter Dong , Z. , He , Q. , Chen , F. , Jin , H. , Gu , T. , Yang , Y. : EdgeMove : Pipelining device-edge model training for mobile intelligence . In: ACM Web Conference , pp. 3142 -- 3153 ( 2023 ) bchapter

work page 2023
[75]

, Bharali , S

barticle Dutta , L. , Bharali , S. : TinyML meets IoT : A comprehensive survey . Internet of Things 16 , 100461 ( 2021 ) barticle

work page 2021
[76]

, Morganti , L

barticle D’Agostino , D. , Morganti , L. , Corni , E. , Cesini , D. , Merelli , I. : Combining edge and cloud computing for low-power, cost-effective metagenomics analysis . Future Generation Computer Systems 90 , 79 -- 85 ( 2019 ) barticle

work page 2019
[77]

, Ammoun , H

barticle Elmoufidi , A. , Ammoun , H. : Diabetic retinopathy prevention using EfficientNetB3 architecture and fundus photography . SN Computer Science 4 ( 1 ), 78 ( 2022 ) barticle

work page 2022
[78]

, Metzen , J.H

barticle Elsken , T. , Metzen , J.H. , Hutter , F. : Neural architecture search: A survey . Journal of Machine Learning Research 20 ( 55 ), 1 -- 21 ( 2019 ) barticle

work page 2019
[79]

, McKinstry , J.L

bchapter Esser , S.K. , McKinstry , J.L. , Bablani , D. , Appuswamy , R. , Modha , D.S. : Learned step size quantization . In: International Conference on Learning Representations (ICLR) ( 2020 ) bchapter

work page 2020
[80]

, Chou , K

barticle Esteva , A. , Chou , K. , Yeung , S. , Naik , N. , Madani , A. , Mottaghi , A. , Liu , Y. , Topol , E. , Dean , J. , Socher , R. : Deep learning-enabled medical computer vision . NPJ Digital Medicine 4 ( 1 ), 5 ( 2021 ) barticle

work page 2021

Showing first 80 references.