Next Article in Journal
Bridge Node Detection between Communities Based on GNN
Previous Article in Journal
Influence of Construction of the following Tunnel on the Preceding Tunnel in the Reinforced Soil Layer
 
 
Article
Peer-Review Record

Hierarchical Prototypes Polynomial Softmax Loss Function for Visual Classification

Appl. Sci. 2022, 12(20), 10336; https://doi.org/10.3390/app122010336
by Chengcheng Xiao 1,2, Xiaowen Liu 1,2,*, Chi Sun 1,2, Zhongyu Liu 3 and Enjie Ding 1,2
Reviewer 1:
Reviewer 2:
Appl. Sci. 2022, 12(20), 10336; https://doi.org/10.3390/app122010336
Submission received: 20 September 2022 / Revised: 8 October 2022 / Accepted: 10 October 2022 / Published: 13 October 2022

Round 1

Reviewer 1 Report

In this paper, authors presents a hierarchical prototype loss function by adding loss functions to different layers of the deep neural network. They improved the performance of the semantic feature extraction at the bottom of the network and they calculated loss method with a polynomial function, which is a kernel method that can effectively improve linear separability of the low-dimensional space. Through various experiments using multiple public datasets, it was proven that the proposed method is effective. 

 

The paper is well written and very interested for the reader. 

Author Response

Please see the attachment.

Author Response File: Author Response.docx

Reviewer 2 Report

Please see attached file

Comments for author File: Comments.pdf

Author Response

Please see the attachment.

Author Response File: Author Response.docx

Round 2

Reviewer 2 Report

The authors have included all my comments and suggestions successfully. We recommend for publication in Applied Sciences. 

Back to TopTop