DeepAI AI Chat
Log In Sign Up

Multi-Grid Redundant Bounding Box Annotation for Accurate Object Detection

by   Solomon Negussie Tesema, et al.
Université de Bourgogne

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.


page 3

page 6

page 8


Ensembling object detectors for image and video data analysis

In this paper, we propose a method for ensembling the outputs of multipl...

Optimizing the Trade-off between Single-Stage and Two-Stage Object Detectors using Image Difficulty Prediction

There are mainly two types of state-of-the-art object detectors. On one ...

Boundary Distribution Estimation to Precise Object Detection

In principal modern detectors, the task of object localization is implem...

Recent Trends in 2D Object Detection and Applications in Video Event Recognition

Object detection serves as a significant step in improving performance o...

Spot the Difference by Object Detection

In this paper, we propose a simple yet effective solution to a change de...

PSRR-MaxpoolNMS: Pyramid Shifted MaxpoolNMS with Relationship Recovery

Non-maximum Suppression (NMS) is an essential postprocessing step in mod...

CornerNet: Detecting Objects as Paired Keypoints

We propose CornerNet, a new approach to object detection where we detect...