Quasar-ViT: Hardware-Oriented Quantization-Aware Architecture Search for Vision Transformers-Reference-Cited by-同舟云学术

Quasar-ViT: Hardware-Oriented Quantization-Aware Architecture Search for Vision Transformers

Published:2024-05-30 Issue: Volume:34 Page:324-337
ISSN:
Container-title:Proceedings of the 38th ACM International Conference on Supercomputing
language:
Short-container-title:

Author:

Li Zhengang¹^ORCID,Lu Alec²^ORCID,Xie Yanyue³^ORCID,Kong Zhenglun¹^ORCID,Sun Mengshu⁴^ORCID,Tang Hao⁵^ORCID,Xue Zhong Jia²^ORCID,Dong Peiyan³^ORCID,Ding Caiwen⁶^ORCID,Wang Yanzhi³^ORCID,Lin Xue³^ORCID,Fang Zhenman²^ORCID

Affiliation:

1. Northeastern University, USA

2. Simon Fraser University, Canada

3. Northeastern University, United States of America

4. Beijing University of Technology, China

5. ETH Zurich, Switzerland

6. University of Connecticut, United States of America

Funder

National Science Foundation

Army Research Office/Army Research Laboratory

NSERC Discovery

CFI John R. Evans Leaders Fund

SRC Artificial Intelligence Hardware program

NSERC Alliance

BC Knowledge Development Fund

Publisher

ACM

Link

https://dl.acm.org/doi/pdf/10.1145/3650200.3656622

Reference70 articles.

1. BinaryBERT: Pushing the Limit of BERT Quantization

2. Bowen Baker, Otkrist Gupta, Nikhil Naik, and Ramesh Raskar. 2017. Designing Neural Network Architectures using Reinforcement Learning. In International Conference on Learning Representations (ICLR).

3. Gabriel Bender, Pieter-Jan Kindermans, Barret Zoph, Vijay Vasudevan, and Quoc Le. 2018. Understanding and simplifying one-shot architecture search. In Proceedings of the International Conference on Machine Learning (ICML). 550–559.

4. Efficient Architecture Search by Network Transformation

5. Mix and Match: A Novel FPGA-Centric Deep Neural Network Quantization Framework