Transitory cross entropy for model training on unbalanced datasets

Venkateswara R. Dasari; Billy Geerhart III; Peng Wang

doi:10.1117/12.2618556

30 May 2022 Transitory cross entropy for model training on unbalanced datasets

Venkateswara R. Dasari, Billy Geerhart III, Peng Wang

Proceedings Volume PC12117, Disruptive Technologies in Information Sciences VI; PC1211703 (2022) https://doi.org/10.1117/12.2618556
Event: SPIE Defense + Commercial Sensing, 2022, Orlando, Florida, United States

Abstract

The proposed transitory cross entropy loss function performs a weighted average of the cross entropy using both the truth labels and the predicted labels; this is a variation of the weighted cross entropy loss function that performs a weighted average using just the truth labels. We tested the transitory cross entropy loss function by training ICNet on the CityScapes dataset and saw an increase in the mean-intersection-over-union relative to the model trained using the standard weighted cross entropy loss function. We further propose modifying the weights based on dynamic performance metrics rather than just static distribution metrics.

Conference Presentation

Citation Download Citation

Venkateswara R. Dasari, Billy Geerhart III, and Peng Wang "Transitory cross entropy for model training on unbalanced datasets", Proc. SPIE PC12117, Disruptive Technologies in Information Sciences VI, PC1211703 (30 May 2022); https://doi.org/10.1117/12.2618556

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available