Improved interpretable method with experimental verification based on adaptive temperature

被引：0

作者：

Ben K. ^{[1
]}

Wang T. ^{[1
]}

Zhang X. ^{[1
]}

机构：

[1] College of Electronic Engineering, Navy University of Engineering, Wuhan

来源：

Huazhong Keji Daxue Xuebao (Ziran Kexue Ban)/Journal of Huazhong University of Science and Technology (Natural Science Edition) | 2022年 / 50卷 / 02期

关键词：

Adaptive temperature; Ex-post interpretable method; Interpretability; Model distillation; Small teacher network;

D O I：

10.13245/j.hust.220219

中图分类号：

学科分类号：

摘要：

Aiming at the low efficiency problem and high time cost of hyperparameter temperature in teacher-student network, an interpretable model based on adaptive temperature assisted training of the small teacher network was proposed. On the basis of the original teacher-student model structure, firstly, it shows that the temperature hyperparameter is only related to the training convergence speed of the student model. Secondly, the small teacher model structure was added to save the training time of the interpretation model. In the verification experiment of image classification, the accuracy of the interpretation model in cifar-100 is increased by 2.45% compared with the original model, and the processing time is saved by 26.33%. The proposed method can make a global approximation to the interpretation model, and it is an ex-post interpretable method with a short processing time. © 2022, Editorial Board of Journal of Huazhong University of Science and Technology. All right reserved.

引用

页码：124 / 129

页数：5

共 12 条

[11] ASHOKA, RHINEHART N, BEAINY F, Et al., N2N learning: network to network compression via policy gradient reinforcement learning, Proc of International Conference on Learning Representations (ICLR), pp. 2745-2753, (2018)
[12] RADOSAVOVIC I, KOSARAJU R, GIRSHICK R, Et al., Designing network design spaces, Proc of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10425-10433, (2020)

← 1 2 →