Tuning-up Learning Parameters for Deep Convolutional Neural Network:A Case Study for Hand-Drawn Sketch Images

作     者：Shaukat Hayat Kun She Muhammad Mateen Parinya Suwansrikham Muhammad Abdullah Ahmed Alghaili Shaukat Hayat;Kun She;Muhammad Mateen;Parinya Suwansrikham;Muhammad Abdullah Ahmed Alghaili

作者机构：the School of Information and Software EngineeringUniversity of Electronic Science and Technology of ChinaChengdu 610054 the School of Big Data&Software EngineeringChongqing UniversityChongqing 400044 the College of Information Science and EngineeringHunan UniversityChangsha 410082 

出 版 物：《Journal of Electronic Science and Technology》 (电子科技学刊（英文版）)

年 卷 期：2022年第20卷第3期

页      面：305-318页

核心收录：

学科分类：0710[理学-生物学] 0711[理学-系统科学] 08[工学] 081104[工学-模式识别与智能系统] 080203[工学-机械设计及理论] 0802[工学-机械工程] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

主　　题：Deep learning(DL) hand-drawn sketches learning parameters 

摘      要：Several recent successes in deep learning(DL),such as state-of-the-art performance on several image classification benchmarks,have been achieved through the improved configuration.Hyperparameters(HPs)tuning is a key factor affecting the performance of machine learning(ML)algorithms.Various state-of-the-art DL models use different HPs in different ways for classification tasks on different datasets.This manuscript provides a brief overview of learning parameters and configuration techniques to show the benefits of using a large-scale handdrawn sketch dataset for classification problems.We analyzed the impact of different learning parameters and toplayer configurations with batch normalization(BN)and dropouts on the performance of the pre-trained visual geometry group 19(VGG-19).The analyzed learning parameters include different learning rates and momentum values of two different optimizers,such as stochastic gradient descent(SGD)and Adam.Our analysis demonstrates that using the SGD optimizer and learning parameters,such as small learning rates with high values of momentum,along with both BN and dropouts in top layers,has a good impact on the sketch image classification accuracy.