Multi-Grid Redundant Bounding Box Annotation for Accurate Object Detection

TL;DR

This paper introduces a novel multi-grid annotation method and an offline copy-paste data augmentation technique to improve the accuracy of object detection, outperforming current state-of-the-art detectors.

Contribution

It proposes a new mathematical approach for assigning multiple grids per object and an effective data augmentation method, enhancing detection precision.

Findings

Significant performance improvement over existing detectors

Effective multi-grid bounding box annotation method

Enhanced data augmentation technique

Abstract

Modern leading object detectors are either two-stage or one-stage networks repurposed from a deep CNN-based backbone classifier network. YOLOv3 is one such very-well known state-of-the-art one-shot detector that takes in an input image and divides it into an equal-sized grid matrix. The grid cell having the center of an object is the one responsible for detecting the particular object. This paper presents a new mathematical approach that assigns multiple grids per object for accurately tight-fit bounding box prediction. We also propose an effective offline copy-paste data augmentation for object detection. Our proposed method significantly outperforms some current state-of-the-art object detectors with a prospect for further better performance.