Deep Learning for Generic Object Detection: A Survey
Глубокое обучение для универсального обнаружения объектов: обзор
2019-10-31
SCID: 54.1/bjqyxef8
Discuss with AI
context modelingdeep learningevaluation metricsgeneric object detectionobject proposal generation
Figures from the paper
Abstract (AI)
Abstract Object detection, one of the most fundamental and challenging problems in computer vision, seeks to locate object instances from a large number of predefined categories in natural images. Deep learning techniques have emerged as a powerful strategy for learning feature representations directly from data and have led to remarkable breakthroughs in the field of generic object detection. Given this period of rapid evolution, the goal of this paper is to provide a comprehensive survey of the recent achievements in this field brought about by deep learning techniques. More than 300 research contributions are included in this survey, covering many aspects of generic object detection: detection frameworks, object feature representation, object proposal generation, context modeling, training strategies, and evaluation metrics. We finish the survey by identifying promising directions for future research.
Key Findings
1
Deep learning techniques have driven remarkable breakthroughs in generic object detection by learning feature representations directly from data.
2
Generic object detection remains a fundamental and challenging computer vision problem involving locating instances from many predefined categories in natural images.
3
The paper provides a comprehensive synthesis of recent achievements in deep learning–based object detection and identifies promising future research directions.
4
The survey covers over 300 research contributions across detection frameworks, feature representation, proposal generation, context modeling, training strategies, and evaluation metrics.
Research Object
Generic object detection in natural images
Research Subject
Advances enabled by deep learning in detection frameworks, feature representations, object proposal generation, context modeling, training strategies, and evaluation metrics for locating object instances from many predefined categories
Publication Details
Publication Date
2019-10-31
Journal
Publisher
ISSN
Cited by
2964
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest
References available in scid.ai18
Deep Residual Learning for Image Recognition2016
ImageNet classification with deep convolutional neural networks2017
Very Deep Convolutional Networks for Large-Scale Image Recognition2014
ImageNet: A large-scale hierarchical image database2009
Gradient-based learning applied to document recognition1998
Squeeze-and-Excitation Networks2018
Rethinking the Inception Architecture for Computer Vision2016
Distilling the Knowledge in a Neural Network2015
Learning Multiple Layers of Features from Tiny Images2024
Reducing the Dimensionality of Data with Neural Networks2006
Representation Learning: A Review and New Perspectives2013
Aggregated Residual Transformations for Deep Neural Networks2017
A Comprehensive Survey on Graph Neural Networks2020
Learning Deep Features for Discriminative Localization2016
ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices2018
Graph neural networks: A review of methods and applications2020
PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation2016
Graph Neural Networks: A Review of Methods and Applications2018
Cited by8
SwinIR: Image Restoration Using Swin Transformer2021
A Survey of Autonomous Driving: Common Practices and Emerging Technologies2020
Detection and Tracking Meet Drones Challenge2021
Sensor and Sensor Fusion Technology in Autonomous Vehicles: A Review2021
Artificial intelligence in the creative industries: a review2021
Computer vision algorithms and hardware implementations: A survey2019
X-Ray Baggage Inspection With Computer Vision: A Survey2020
A Survey on Audio-Video Based Defect Detection Through Deep Learning in Railway Maintenance2022