RCV2023 Challenges: Benchmarking Model Training and Inference for Resource-Constrained Deep Learning

Rishabh Tiwari; Arnav Chavan; Deepak Gupta; Gowreesh Mago; Animesh Gupta; Akash Gupta; Suraj Sharan; Yukun Yang; Shanwei Zhao; Shihao Wang; Youngjun Kwak; Seonghun Jeong; Yunseung Lee; Changick Kim; Subin Kim; Ganzorig Gankhuyag; Ho Jung; Junwhan Ryu; Hae Moon Kim; Byeong H. Kim; Tu Vo; Sheir Zaheer; Alexander Holston; Chan Park; Dheemant Dixit; Nahush Lele; Kushagra Bhushan; Debjani Bhowmick; Devanshu Arya; Sadaf Gulshad; Amirhossein Habibian; Amir Ghodrati; Babak Bejnordi; Jai Gupta; Zhuang Liu; Jiahui Yu; Dilip Prasad; Zhiqiang Shen

doi:10.1109/ICCVW60793.2023.00168

RCV2023 Challenges: Benchmarking Model Training and Inference for Resource-Constrained Deep Learning

Rishabh Tiwari, Arnav Chavan, Deepak Gupta, Gowreesh Mago, Animesh Gupta, Akash Gupta, Suraj Sharan, Yukun Yang, Shanwei Zhao, Shihao Wang, Youngjun Kwak, Seonghun Jeong, Yunseung Lee, Changick Kim, Subin Kim, Ganzorig Gankhuyag, Ho Jung, Junwhan Ryu, Hae Moon Kim, Byeong H. KimTu Vo, Sheir Zaheer, Alexander Holston, Chan Park, Dheemant Dixit, Nahush Lele, Kushagra Bhushan, Debjani Bhowmick, Devanshu Arya, Sadaf Gulshad, Amirhossein Habibian, Amir Ghodrati, Babak Bejnordi, Jai Gupta, Zhuang Liu, Jiahui Yu, Dilip Prasad, Zhiqiang Shen

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

1 Scopus citations

Abstract

This paper delves into the results of two resource-constrained deep learning challenges, part of the workshop on Resource-Efficient Deep Learning for Computer Vision (RCV) at ICCV 2023, focusing on memory and time limitations. The challenges garnered significant global participation and showcased a range of intriguing solutions. The paper outlines the problem statements for both tracks, summarizes baseline and top-performing approaches, and provides a detailed analysis of the methods used. While the presented solutions constitute promising initial progress, they represent the beginning of efforts needed to address this complex issue. We conclude by emphasizing the importance of sustained research efforts to fully address the challenges of resource-constrained deep learning.

Original language	English (US)
Title of host publication	Proceedings - 2023 IEEE/CVF International Conference on Computer Vision Workshops, ICCVW 2023
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	1526-1535
Number of pages	10
ISBN (Electronic)	9798350307443
DOIs	https://doi.org/10.1109/ICCVW60793.2023.00168
State	Published - 2023
Externally published	Yes
Event	2023 IEEE/CVF International Conference on Computer Vision Workshops, ICCVW 2023 - Paris, France Duration: Oct 2 2023 → Oct 6 2023

Publication series

Name	Proceedings - 2023 IEEE/CVF International Conference on Computer Vision Workshops, ICCVW 2023

Conference

Conference	2023 IEEE/CVF International Conference on Computer Vision Workshops, ICCVW 2023
Country/Territory	France
City	Paris
Period	10/2/23 → 10/6/23

All Science Journal Classification (ASJC) codes

Artificial Intelligence
Computer Science Applications
Computer Vision and Pattern Recognition

Access to Document

10.1109/ICCVW60793.2023.00168

Cite this

Tiwari, R., Chavan, A., Gupta, D., Mago, G., Gupta, A., Gupta, A., Sharan, S., Yang, Y., Zhao, S., Wang, S., Kwak, Y., Jeong, S., Lee, Y., Kim, C., Kim, S., Gankhuyag, G., Jung, H., Ryu, J., Kim, H. M., ... Shen, Z. (2023). RCV2023 Challenges: Benchmarking Model Training and Inference for Resource-Constrained Deep Learning. In Proceedings - 2023 IEEE/CVF International Conference on Computer Vision Workshops, ICCVW 2023 (pp. 1526-1535). (Proceedings - 2023 IEEE/CVF International Conference on Computer Vision Workshops, ICCVW 2023). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICCVW60793.2023.00168

Tiwari, Rishabh ; Chavan, Arnav ; Gupta, Deepak et al. / RCV2023 Challenges : Benchmarking Model Training and Inference for Resource-Constrained Deep Learning. Proceedings - 2023 IEEE/CVF International Conference on Computer Vision Workshops, ICCVW 2023. Institute of Electrical and Electronics Engineers Inc., 2023. pp. 1526-1535 (Proceedings - 2023 IEEE/CVF International Conference on Computer Vision Workshops, ICCVW 2023).

@inproceedings{eac47bc14c3740a7b327805d5b09de71,

title = "RCV2023 Challenges: Benchmarking Model Training and Inference for Resource-Constrained Deep Learning",

abstract = "This paper delves into the results of two resource-constrained deep learning challenges, part of the workshop on Resource-Efficient Deep Learning for Computer Vision (RCV) at ICCV 2023, focusing on memory and time limitations. The challenges garnered significant global participation and showcased a range of intriguing solutions. The paper outlines the problem statements for both tracks, summarizes baseline and top-performing approaches, and provides a detailed analysis of the methods used. While the presented solutions constitute promising initial progress, they represent the beginning of efforts needed to address this complex issue. We conclude by emphasizing the importance of sustained research efforts to fully address the challenges of resource-constrained deep learning.",

author = "Rishabh Tiwari and Arnav Chavan and Deepak Gupta and Gowreesh Mago and Animesh Gupta and Akash Gupta and Suraj Sharan and Yukun Yang and Shanwei Zhao and Shihao Wang and Youngjun Kwak and Seonghun Jeong and Yunseung Lee and Changick Kim and Subin Kim and Ganzorig Gankhuyag and Ho Jung and Junwhan Ryu and Kim, \{Hae Moon\} and Kim, \{Byeong H.\} and Tu Vo and Sheir Zaheer and Alexander Holston and Chan Park and Dheemant Dixit and Nahush Lele and Kushagra Bhushan and Debjani Bhowmick and Devanshu Arya and Sadaf Gulshad and Amirhossein Habibian and Amir Ghodrati and Babak Bejnordi and Jai Gupta and Zhuang Liu and Jiahui Yu and Dilip Prasad and Zhiqiang Shen",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 2023 IEEE/CVF International Conference on Computer Vision Workshops, ICCVW 2023 ; Conference date: 02-10-2023 Through 06-10-2023",

year = "2023",

doi = "10.1109/ICCVW60793.2023.00168",

language = "English (US)",

series = "Proceedings - 2023 IEEE/CVF International Conference on Computer Vision Workshops, ICCVW 2023",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "1526--1535",

booktitle = "Proceedings - 2023 IEEE/CVF International Conference on Computer Vision Workshops, ICCVW 2023",

address = "United States",

}

Tiwari, R, Chavan, A, Gupta, D, Mago, G, Gupta, A, Gupta, A, Sharan, S, Yang, Y, Zhao, S, Wang, S, Kwak, Y, Jeong, S, Lee, Y, Kim, C, Kim, S, Gankhuyag, G, Jung, H, Ryu, J, Kim, HM, Kim, BH, Vo, T, Zaheer, S, Holston, A, Park, C, Dixit, D, Lele, N, Bhushan, K, Bhowmick, D, Arya, D, Gulshad, S, Habibian, A, Ghodrati, A, Bejnordi, B, Gupta, J, Liu, Z, Yu, J, Prasad, D & Shen, Z 2023, RCV2023 Challenges: Benchmarking Model Training and Inference for Resource-Constrained Deep Learning. in Proceedings - 2023 IEEE/CVF International Conference on Computer Vision Workshops, ICCVW 2023. Proceedings - 2023 IEEE/CVF International Conference on Computer Vision Workshops, ICCVW 2023, Institute of Electrical and Electronics Engineers Inc., pp. 1526-1535, 2023 IEEE/CVF International Conference on Computer Vision Workshops, ICCVW 2023, Paris, France, 10/2/23. https://doi.org/10.1109/ICCVW60793.2023.00168

RCV2023 Challenges: Benchmarking Model Training and Inference for Resource-Constrained Deep Learning. / Tiwari, Rishabh; Chavan, Arnav; Gupta, Deepak et al.
Proceedings - 2023 IEEE/CVF International Conference on Computer Vision Workshops, ICCVW 2023. Institute of Electrical and Electronics Engineers Inc., 2023. p. 1526-1535 (Proceedings - 2023 IEEE/CVF International Conference on Computer Vision Workshops, ICCVW 2023).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - RCV2023 Challenges

T2 - 2023 IEEE/CVF International Conference on Computer Vision Workshops, ICCVW 2023

AU - Tiwari, Rishabh

AU - Chavan, Arnav

AU - Gupta, Deepak

AU - Mago, Gowreesh

AU - Gupta, Animesh

AU - Gupta, Akash

AU - Sharan, Suraj

AU - Yang, Yukun

AU - Zhao, Shanwei

AU - Wang, Shihao

AU - Kwak, Youngjun

AU - Jeong, Seonghun

AU - Lee, Yunseung

AU - Kim, Changick

AU - Kim, Subin

AU - Gankhuyag, Ganzorig

AU - Jung, Ho

AU - Ryu, Junwhan

AU - Kim, Hae Moon

AU - Kim, Byeong H.

AU - Vo, Tu

AU - Zaheer, Sheir

AU - Holston, Alexander

AU - Park, Chan

AU - Dixit, Dheemant

AU - Lele, Nahush

AU - Bhushan, Kushagra

AU - Bhowmick, Debjani

AU - Arya, Devanshu

AU - Gulshad, Sadaf

AU - Habibian, Amirhossein

AU - Ghodrati, Amir

AU - Bejnordi, Babak

AU - Gupta, Jai

AU - Liu, Zhuang

AU - Yu, Jiahui

AU - Prasad, Dilip

AU - Shen, Zhiqiang

PY - 2023

Y1 - 2023

N2 - This paper delves into the results of two resource-constrained deep learning challenges, part of the workshop on Resource-Efficient Deep Learning for Computer Vision (RCV) at ICCV 2023, focusing on memory and time limitations. The challenges garnered significant global participation and showcased a range of intriguing solutions. The paper outlines the problem statements for both tracks, summarizes baseline and top-performing approaches, and provides a detailed analysis of the methods used. While the presented solutions constitute promising initial progress, they represent the beginning of efforts needed to address this complex issue. We conclude by emphasizing the importance of sustained research efforts to fully address the challenges of resource-constrained deep learning.

AB - This paper delves into the results of two resource-constrained deep learning challenges, part of the workshop on Resource-Efficient Deep Learning for Computer Vision (RCV) at ICCV 2023, focusing on memory and time limitations. The challenges garnered significant global participation and showcased a range of intriguing solutions. The paper outlines the problem statements for both tracks, summarizes baseline and top-performing approaches, and provides a detailed analysis of the methods used. While the presented solutions constitute promising initial progress, they represent the beginning of efforts needed to address this complex issue. We conclude by emphasizing the importance of sustained research efforts to fully address the challenges of resource-constrained deep learning.

UR - https://www.scopus.com/pages/publications/85182941514

UR - https://www.scopus.com/inward/citedby.url?scp=85182941514&partnerID=8YFLogxK

U2 - 10.1109/ICCVW60793.2023.00168

DO - 10.1109/ICCVW60793.2023.00168

M3 - Conference contribution

AN - SCOPUS:85182941514

T3 - Proceedings - 2023 IEEE/CVF International Conference on Computer Vision Workshops, ICCVW 2023

SP - 1526

EP - 1535

BT - Proceedings - 2023 IEEE/CVF International Conference on Computer Vision Workshops, ICCVW 2023

PB - Institute of Electrical and Electronics Engineers Inc.

Y2 - 2 October 2023 through 6 October 2023

ER -

Tiwari R, Chavan A, Gupta D, Mago G, Gupta A, Gupta A et al. RCV2023 Challenges: Benchmarking Model Training and Inference for Resource-Constrained Deep Learning. In Proceedings - 2023 IEEE/CVF International Conference on Computer Vision Workshops, ICCVW 2023. Institute of Electrical and Electronics Engineers Inc. 2023. p. 1526-1535. (Proceedings - 2023 IEEE/CVF International Conference on Computer Vision Workshops, ICCVW 2023). doi: 10.1109/ICCVW60793.2023.00168

RCV2023 Challenges: Benchmarking Model Training and Inference for Resource-Constrained Deep Learning

Abstract

Publication series

Conference

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this