Unimodal regularisation based on beta distribution for deep ordinal regression

Hits: 6027
Research areas:
Year:
2022
Type of Publication:
Article
Keywords:
Ordinal regression, Unimodal distribution, Convolutional network, Beta distribution, Stick-breaking
Authors:
Journal:
Pattern Recognition
Volume:
122
Pages:
108310
Month:
February
ISSN:
0031-3203
BibTex:
Note:
JCR(2022): 8.0 Position: 22/145 (Q1) Category: COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE
Abstract:
Currently, the use of deep learning for solving ordinal classification problems, where categories follow a natural order, has not received much attention. In this paper, we propose an unimodal regularisation based on the beta distribution applied to the cross-entropy loss. This regularisation encourages the distribution of the labels to be a soft unimodal distribution, more appropriate for ordinal problems. Given that the beta distribution has two parameters that must be adjusted, a method to automatically determine them is proposed. The regularised loss function is used to train a deep neural network model with an ordinal scheme in the output layer. The results obtained are statistically analysed and show that the combination of these methods increases the performance in ordinal problems. Moreover, the proposed beta distribution performs better than other distributions proposed in previous works, achieving also a reduced computational cost.
Comments:
JCR(2022): 8.0 Position: 22/145 (Q1) Category: COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE
Back