Quantization-Guided Training for Compact TinyML Models

03/10/2021
by   Sedigh Ghamari, et al.
0

We propose a Quantization Guided Training (QGT) method to guide DNN training towards optimized low-bit-precision targets and reach extreme compression levels below 8-bit precision. Unlike standard quantization-aware training (QAT) approaches, QGT uses customized regularization to encourage weight values towards a distribution that maximizes accuracy while reducing quantization errors. One of the main benefits of this approach is the ability to identify compression bottlenecks. We validate QGT using state-of-the-art model architectures on vision datasets. We also demonstrate the effectiveness of QGT with an 81KB tiny model for person detection down to 2-bit precision (representing 17.7x size reduction), while maintaining an accuracy drop of only 3

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 5

10/07/2019

Bit Efficient Quantization for Deep Neural Networks

Quantization for deep neural networks have afforded models for edge devi...
02/27/2019

Cluster Regularized Quantization for Deep Networks Compression

Deep neural networks (DNNs) have achieved great success in a wide range ...
05/21/2018

DEEPEYE: A Compact and Accurate Video Comprehension at Terminal Devices Compressed with Quantization and Tensorization

As it requires a huge number of parameters when exposed to high dimensio...
03/13/2017

Guetzli: Perceptually Guided JPEG Encoder

Guetzli is a new JPEG encoder that aims to produce visually indistinguis...
04/15/2020

Training with Quantization Noise for Extreme Fixed-Point Compression

We tackle the problem of producing compact models, maximizing their accu...
04/15/2020

Training with Quantization Noise for Extreme Model Compression

We tackle the problem of producing compact models, maximizing their accu...
09/05/2021

Cluster-Promoting Quantization with Bit-Drop for Minimizing Network Quantization Loss

Network quantization, which aims to reduce the bit-lengths of the networ...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.