Robust Quantization: One Model to Rule Them All

Neural network quantization methods often involve simulating the quantization process during training, making the trained model highly dependent on the target bit-width and precise way quantization is performed. Robust quantization offers an alternative approach with improved tolerance to different...

Full description

Saved in:
Bibliographic Details
Main Authors Shkolnik, Moran, Chmiel, Brian, Banner, Ron, Shomron, Gil, Nahshan, Yury, Bronstein, Alex, Weiser, Uri
Format Journal Article
LanguageEnglish
Published 18.02.2020
Subjects
Computer Science - Computer Vision and Pattern Recognition
Computer Science - Learning
Statistics - Machine Learning
Online AccessGet full text

Cover

More Information
Summary:Neural network quantization methods often involve simulating the quantization process during training, making the trained model highly dependent on the target bit-width and precise way quantization is performed. Robust quantization offers an alternative approach with improved tolerance to different classes of data-types and quantization policies. It opens up new exciting applications where the quantization process is not static and can vary to meet different circumstances and implementations. To address this issue, we propose a method that provides intrinsic robustness to the model against a broad range of quantization processes. Our method is motivated by theoretical arguments and enables us to store a single generic model capable of operating at various bit-widths and quantization policies. We validate our method's effectiveness on different ImageNet models.
DOI:10.48550/arxiv.2002.07686