Conference item icon

Conference item

HyperBlock floating point: generalised quantization scheme for gradient and inference computation

Abstract:

Prior quantization methods focus on producing networks for fast and lightweight inference. However, the cost of unquantised training is overlooked, despite requiring significantly more time and energy than inference. We present a method for quantizing convolutional neural networks for efficient training. Quantizing gradients is challenging because it requires higher granularity and their values span a wider range than the weight and feature maps. We propose an extension of the Channel-wise Bl...

Expand abstract
Publication status:
Published
Peer review status:
Peer reviewed

Actions


Access Document


Files:
Publisher copy:
10.1109/wacv56688.2023.00630

Authors


More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Engineering Science
Role:
Author
More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Engineering Science
Role:
Author
Publisher:
IEEE
Host title:
Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV 2023)
Pages:
6353-6362
Publication date:
2023-02-06
Event title:
IEEE/CVF Winter Conference on Applications of Computer Vision (WACV 2023)
Event location:
Waikoloa, Hawaii
Event website:
https://wacv2023.thecvf.com/home
Event start date:
2023-01-02
Event end date:
2023-01-07
DOI:
EISSN:
2642-9381
ISSN:
2472-6737
EISBN:
978-1-6654-9346-8
ISBN:
978-1-6654-9347-5
Language:
English
Keywords:
Pubs id:
1335408
Local pid:
pubs:1335408
Deposit date:
2023-04-03

Terms of use


Views and Downloads






If you are the owner of this record, you can report an update to it here: Report update to this record

TO TOP