Incremental Network Quantization: Towards Lossless CNNs with Low-Precision Weights

02/10/2017
by   Aojun Zhou, et al.
0

This paper presents incremental network quantization (INQ), a novel method, targeting to efficiently convert any pre-trained full-precision convolutional neural network (CNN) model into a low-precision version whose weights are constrained to be either powers of two or zero. Unlike existing methods which are struggled in noticeable accuracy loss, our INQ has the potential to resolve this issue, as benefiting from two innovations. On one hand, we introduce three interdependent operations, namely weight partition, group-wise quantization and re-training. A well-proven measure is employed to divide the weights in each layer of a pre-trained CNN model into two disjoint groups. The weights in the first group are responsible to form a low-precision base, thus they are quantized by a variable-length encoding method. The weights in the other group are responsible to compensate for the accuracy loss from the quantization, thus they are the ones to be re-trained. On the other hand, these three operations are repeated on the latest re-trained group in an iterative manner until all the weights are converted into low-precision ones, acting as an incremental network quantization and accuracy enhancement procedure. Extensive experiments on the ImageNet classification task using almost all known deep CNN architectures including AlexNet, VGG-16, GoogleNet and ResNets well testify the efficacy of the proposed method. Specifically, at 5-bit quantization, our models have improved accuracy than the 32-bit floating-point references. Taking ResNet-18 as an example, we further show that our quantized models with 4-bit, 3-bit and 2-bit ternary weights have improved or very similar accuracy against its 32-bit floating-point baseline. Besides, impressive results with the combination of network pruning and INQ are also reported. The code is available at https://github.com/Zhouaojun/Incremental-Network-Quantization.

READ FULL TEXT
03/11/2020

Kernel Quantization for Efficient Network Compression

This paper presents a novel network compression framework Kernel Quantiz...
02/03/2021

Fixed-point Quantization of Convolutional Neural Networks for Quantized Inference on Embedded Platforms

Convolutional Neural Networks (CNNs) have proven to be a powerful state-...
06/26/2022

CTMQ: Cyclic Training of Convolutional Neural Networks with Multiple Quantization Steps

This paper proposes a training method having multiple cyclic training fo...
10/18/2021

Sub-bit Neural Networks: Learning to Compress and Accelerate Binary Neural Networks

In the low-bit quantization field, training Binary Neural Networks (BNNs...
10/26/2021

Qu-ANTI-zation: Exploiting Quantization Artifacts for Achieving Adversarial Outcomes

Quantization is a popular technique that transforms the parameter repres...
03/19/2019

Trained Uniform Quantization for Accurate and Efficient Neural Network Inference on Fixed-Point Hardware

We propose a method of training quantization clipping thresholds for uni...
02/15/2021

FAT: Learning Low-Bitwidth Parametric Representation via Frequency-Aware Transformation

Learning convolutional neural networks (CNNs) with low bitwidth is chall...

Code Repositories

Project

Incremental Network Quantization, Kmeans quantization, Iterative Pruning, Dynamic Network Surgery


view repo