Meta-Cognition-Based Simple And Effective Approach To Object Detection

TL;DR

This paper introduces a meta-cognitive learning strategy for object detection that enhances generalization and accuracy without sacrificing speed, using YOLO v3 Tiny and the MS COCO dataset.

Contribution

It proposes a novel meta-cognitive sampling method that reduces overfitting and improves detection precision while maintaining real-time inference speed.

Findings

Precision improved by 2.6% to 4.4%.

No additional inference overhead.

Effective on MS COCO dataset.

Abstract

Recently, many researchers have attempted to improve deep learning-based object detection models, both in terms of accuracy and operational speeds. However, frequently, there is a trade-off between speed and accuracy of such models, which encumbers their use in practical applications such as autonomous navigation. In this paper, we explore a meta-cognitive learning strategy for object detection to improve generalization ability while at the same time maintaining detection speed. The meta-cognitive method selectively samples the object instances in the training dataset to reduce overfitting. We use YOLO v3 Tiny as a base model for the work and evaluate the performance using the MS COCO dataset. The experimental results indicate an improvement in absolute precision of 2.6% (minimum), and 4.4% (maximum), with no overhead to inference time.