Utilizing Information Bottleneck to Evaluate the Capability of Deep Neural Networks for Image Classification†
Shanghai Institute of Microsystem and Information Technology, Chinese Academy of Sciences, Shanghai 200050, China
University of Chinese Academy of Sciences, Beijing 100049, China
School of Information Science and Technology, ShanghaiTech University, Shanghai 201210, China
State Key Laboratory of ISN, Xidian University, Xi’an 710071, China
Author to whom correspondence should be addressed.
This paper is an extended version of our paper published in the 15th European Conference on Computer Vision (ECCV), Munich, Germany, 8–14 September 2018
Received: 10 February 2019 / Revised: 12 April 2019 / Accepted: 28 April 2019 / Published: 1 May 2019
PDF [687 KB, uploaded 16 May 2019]
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,
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.
This is an open access article distributed under the Creative Commons Attribution License
which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).
Share & Cite This Article
MDPI and ACS Style
Cheng, H.; Lian, D.; Gao, S.; Geng, Y. Utilizing Information Bottleneck to Evaluate the Capability of Deep Neural Networks for Image Classification. Entropy 2019, 21, 456.
Cheng H, Lian D, Gao S, Geng Y. Utilizing Information Bottleneck to Evaluate the Capability of Deep Neural Networks for Image Classification. Entropy. 2019; 21(5):456.
Cheng, Hao; Lian, Dongze; Gao, Shenghua; Geng, Yanlin. 2019. "Utilizing Information Bottleneck to Evaluate the Capability of Deep Neural Networks for Image Classification." Entropy 21, no. 5: 456.
Show more citation formats
Show less citations formats
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.
[Return to top]
For more information on the journal statistics, click here
Multiple requests from the same IP address are counted as one view.