Feature Affinity Assisted Knowledge Distillation and Quantization of Deep Neural Networks on Label-Free Data

Feature Affinity Assisted Knowledge Distillation and Quantization of Deep Neural Networks on Label-Free Data

In this paper, we propose a feature affinity (FA) assisted knowledge distillation (KD) method to improve quantization-aware training of deep neural networks (DNN). The FA loss on intermediate feature maps of DNNs plays the role of teaching middle steps of a solution to a student instead of only givi...

Full description

Bibliographic Details
Main Authors: Zhijian Li, Biao Yang, Penghang Yin, Yingyong Qi, Jack Xin
Format: Article
Language:English
Published: IEEE 2023-01-01
Series:IEEE Access
Subjects:
Model compression
quantization
knowledge distillation
image classification
convolutional neural networks
Online Access:https://ieeexplore.ieee.org/document/10189851/

Internet

https://ieeexplore.ieee.org/document/10189851/

Similar Items