Impact of Evidence Theory Uncertainty on Training Object Detection Models

TL;DR

This paper explores how incorporating Evidence Theory to quantify uncertainty can improve the training efficiency and performance of object detection models by dynamically weighting feedback during training.

Contribution

It introduces a novel approach using Evidence Theory to incorporate uncertainty into the training process of object detection models, enhancing efficiency and accuracy.

Findings

Uncertainty-based feedback reduces training time.

Improved object detection performance with uncertainty weighting.

Effective strategies identified for uncertainty-driven training.

Abstract

This paper investigates the use of Evidence Theory to enhance the training efficiency of object detection models by incorporating uncertainty into the feedback loop. In each training iteration, during the validation phase, Evidence Theory is applied to establish a relationship between ground truth labels and predictions. The Dempster-Shafer rule of combination is used to quantify uncertainty based on the evidence from these predictions. This uncertainty measure is then utilized to weight the feedback loss for the subsequent iteration, allowing the model to adjust its learning dynamically. By experimenting with various uncertainty-weighting strategies, this study aims to determine the most effective method for optimizing feedback to accelerate the training process. The results demonstrate that using uncertainty-based feedback not only reduces training time but can also enhance model performance compared to traditional approaches. This research offers insights into the role of uncertainty in improving machine learning workflows, particularly in object detection, and suggests broader applications for uncertainty-driven training across other AI disciplines.