Low-Bit Quantization of Neural Network Based on Exponential Moving Average Knowledge Distillation

Low-Bit Quantization of Neural Network Based on Exponential Moving Average Knowledge Distillation

LÜ Junhuan, XU Ke, WANG Dong

PDF(681 KB)

Pattern Recognition and Artificial Intelligence ›› 2021, Vol. 34 ›› Issue (12) : 1143-1151. DOI: 10.16451/j.cnki.issn1003-6059.202112007

Researches and Applications

Low-Bit Quantization of Neural Network Based on Exponential Moving Average Knowledge Distillation

{{article.zuoZhe_EN}}

Author information +

History +

HeighLight

{{article.keyPoints_en}}

Abstract

{{article.zhaiyao_en}}

Key words

Cite this article

Download Citations

{{article.zuoZheEn_L}}. {{article.title_en}}. {{journal.qiKanMingCheng_EN}}. 2021, 34(12): 1143-1151 https://doi.org/10.16451/j.cnki.issn1003-6059.202112007

References

Publishing order | Descend order by publishing year | Descend order by cited within

References

{{article.reference}}

Funding

RIGHTS & PERMISSIONS

{{article.copyrightStatement_en}}

{{article.copyrightLicense_en}}

PDF(681 KB)

Accesses

Citation

Detail

Sections

Recommended

/

〈

〉