Hao Cheng

Mr. Hao Cheng


Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 May 2019 in Entropy
Verified
Journal Article
Open access
PDF file
HCHao Cheng
Hao Cheng
DLDongze Lian
Dongze Lian
SGShenghua Gao
Shenghua Gao
Yanlin GengYanlin Geng
Yanlin Geng
Inspired by the pioneering work of the information bottleneck (IB) principle for Deep Neural Networks’ (DNNs) analysis, we thoroughly study the relationship among the model accuracy, I ( X ; T ) and I ( T ; Y ) , where I ( X ; T ) and I ( T ; Y ) are the mutual information of DNN’s output T with input X and label Y. Then, we design an information plane-based framework to evaluate the capability of DNNs (including CNNs) for image classification. Instead of each hidden layer’s output, our framework focuses on the model output T. We successfully apply our framework to many application scenarios arising in deep learning and image classification problems, such as image classification with unbalanced data distribution, model selection, and transfer learning. The experimental results verify the effectiveness of the information plane-based framework: Our framework may facilitate a quick model selection and determine the number of samples needed for each class in the unbalanced classification problem. Furthermore, the framework explains the efficiency of transfer learning in the deep learning area.


20 July 2025
Verified
Conference Paper
Open access
YWYaxuan Wang
Yaxuan Wang
HCHao Cheng
Hao Cheng
JXJing Xiong
Jing Xiong
QWQingsong Wen
Qingsong Wen
HJHan Jia
Han Jia
YLYang Liu
Yang Liu