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, HaeMoon 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; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops, 2023, pp. 1534-1543

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.

Related Material

[pdf]
[bibtex]
@InProceedings{Tiwari_2023_ICCV, author = {Tiwari, Rishabh and Chavan, Arnav and Gupta, Deepak and Mago, Gowreesh and Gupta, Animesh and Gupta, Akash and Sharan, Suraj and Yang, Yukun and Zhao, Shanwei and Wang, Shihao and Kwak, Youngjun and Jeong, Seonghun and Lee, Yunseung and Kim, Changick and Kim, Subin and Gankhuyag, Ganzorig and Jung, Ho and Ryu, Junwhan and Kim, HaeMoon and Kim, Byeong H. and Vo, Tu and Zaheer, Sheir and Holston, Alexander and Park, Chan and Dixit, Dheemant and Lele, Nahush and Bhushan, Kushagra and Bhowmick, Debjani and Arya, Devanshu and Gulshad, Sadaf and Habibian, Amirhossein and Ghodrati, Amir and Bejnordi, Babak and Gupta, Jai and Liu, Zhuang and Yu, Jiahui and Prasad, Dilip and Shen, Zhiqiang}, title = {RCV2023 Challenges: Benchmarking Model Training and Inference for Resource-Constrained Deep Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2023}, pages = {1534-1543} }