Multi-Grid Redundant Bounding Box Annotation for Accurate Object Detection

2022-01-05 · Solomon Negussie Tesema, El-Bay Bourennane

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.

📄 PDF Abstract BibTeX arXiv:2201.01857

Code (0)

등록된 구현이 없습니다.

Tasks

Data AugmentationObjectobject-detection Object Detection

Methods 이 논문이 사용한 방법론

Average Pooling 설명 없음

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Global Average Pooling Global Average Pooling is a pooling operation designed to replace fully connected layers in classical CNNs. The idea is to generate one feature map for each corresponding…

Batch Normalization 설명 없음

k-Means Clustering k-Means Clustering is a clustering algorithm that divides a training set into $k$ different clusters of examples that are near each other. It works by initializing $k$…

1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…

Residual Connection 설명 없음

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

P2P-Loc: Point to Point Tiny Person Localization

2021-12-31 · Xuehui Yu, Di wu, Qixiang Ye, Jianbin Jiao 외

Bounding-box annotation form has been the most frequently used method for visual object localization tasks. However, bounding-box annotation relies on a large amount of precisely annotating bounding boxes, and it is expe…

Object Object Localization

Robust Object Detection With Inaccurate Bounding Boxes

2022-07-20 · Chengxin Liu, Kewei Wang, Hao Lu, Zhiguo Cao 외

Learning accurate object detectors often requires large-scale training data with precise object bounding boxes. However, labeling such data is expensive and time-consuming. As the crowd-sourcing labeling process and the …

Multiple Instance Learning Object object-detection Object Detection+1

Lean Crowdsourcing: Combining Humans and Machines in an Online System

2017-07-01 · CVPR 2017 7 · Steve Branson, Grant van Horn, Pietro Perona

We introduce a method to greatly reduce the amount of redundant annotations required when crowdsourcing annotations such as bounding boxes, parts, and class labels. For example, if two Mechanical Turkers happen to click …

RMPE: Regional Multi-person Pose Estimation

2016-12-01 · ICCV 2017 10 · Hao-Shu Fang, Shuqin Xie, Yu-Wing Tai, Cewu Lu

Multi-person pose estimation in the wild is challenging. Although state-of-the-art human detectors have demonstrated good performance, small errors in localization and recognition are inevitable. These errors can cause f…

2D Human Pose Estimation Human Detection Keypoint Detection Multi-Person Pose Estimation+1

Video Annotation for Visual Tracking via Selection and Refinement

2021-08-09 · ICCV 2021 10 · Kenan Dai, Jie Zhao, Lijun Wang, Dong Wang 외

Deep learning based visual trackers entail offline pre-training on large volumes of video datasets with accurate bounding box annotations that are labor-expensive to achieve. We present a new framework to facilitate boun…

Visual Tracking