DeepAI AI Chat
Log In Sign Up

Multi-Grid Redundant Bounding Box Annotation for Accurate Object Detection

01/05/2022
by   Solomon Negussie Tesema, et al.
Université de Bourgogne
0

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.

READ FULL TEXT

page 3

page 6

page 8

02/09/2021

Ensembling object detectors for image and video data analysis

In this paper, we propose a method for ensembling the outputs of multipl...
03/23/2018

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 ...
11/02/2021

Boundary Distribution Estimation to Precise Object Detection

In principal modern detectors, the task of object localization is implem...
02/07/2022

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

Object detection serves as a significant step in improving performance o...
01/03/2018

Spot the Difference by Object Detection

In this paper, we propose a simple yet effective solution to a change de...
05/27/2021

PSRR-MaxpoolNMS: Pyramid Shifted MaxpoolNMS with Relationship Recovery

Non-maximum Suppression (NMS) is an essential postprocessing step in mod...
08/03/2018

CornerNet: Detecting Objects as Paired Keypoints

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