Text

Effective Training of Convolutional Neural Networks With Low-Bitwidth Weights and Activations

This paper tackles the problem of training a deep convolutional neural network of both low-bitwidth weights and activations. Optimizing a low-precision network is very challenging due to the non-differentiability of the quantizer, which may result in substantial accuracy loss. To address this, we propose three practical approaches, including (i) progressive quantization; (ii) stochastic precision; and (iii) joint knowledge distillation to improve the network training. First, for progressive quantization, we propose two schemes to progressively find good local minima. Specifically, we propose to first optimize a network with quantized weights and subsequently quantize activations. This is in contrast to the traditional methods which optimize them simultaneously. Furthermore, we propose a second progressive quantization scheme which gradually decreases the bitwidth from high-precision to low-precision during training. Second, to alleviate the excessive training burden due to the multi-round training stages, we further propose a one-stage stochastic precision strategy to randomly sample and quantize sub-networks while keeping other parts in full-precision. Finally, we adopt a novel learning scheme to jointly train a full-precision model alongside the low-precision one. By doing so, the full-precision model provides hints to guide the low-precision model training and significantly improves the performance of the low-precision network. Extensive experiments on various datasets (e.g., CIFAR-100, ImageNet) show the effectiveness of the proposed methods.

Ketersediaan

Informasi Detail

Judul Seri

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE; Vol.44 No.10 Part 1 October 2022

No. Panggil

-

Penerbit

: .,

Deskripsi Fisik

p. 6140-6152

Bahasa

English

ISBN/ISSN

-

Klasifikasi

NONE

Tipe Isi

-

Tipe Media

-

Tipe Pembawa

-

Edisi

-

Subjek

IMAGE CLASSIFICATION
KNOWLEDGE DISTILLATION
QUANTIZED NEURAL NETWORK
PROGRESSIVE QUANTIZATION
STOCHASTIC PRECISION

Info Detail Spesifik

DOI: 10.1109/TPAMI.2021.3088904

Pernyataan Tanggungjawab

Bohan Zhuang, Mingkui Tan, Jing Liu, Lingqiao Liu, Ian Reid, Chunhua Shen

Versi lain/terkait

Lampiran Berkas

Komentar