Presentation
30 May 2022 Transitory cross entropy for model training on unbalanced datasets
Venkateswara R. Dasari, Billy Geerhart III, Peng Wang
Author Affiliations +
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
© (2022) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
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
Advertisement
Advertisement
KEYWORDS
Data modeling

Back to Top