SlideShare a Scribd company logo
Modern Convolutional
Object Detectors
Kwanghee Choi
Sogang Univ.
Contents
- Prior Knowledge
- Object Detection
- R-CNN
- History
- Meta-architectures
- Faster R-CNN
- R-FCN
- YOLO
- Object Detection Benchmarks
- Accuracy
- Time
- Memory
Prior Knowledge: Neural Network
Ref. Fei-Fei Li & Andrej Karpathy & Justin Johnson, CS231n: Convolutional Neural Networks for Visual Recognition, Stanford Univ.
Prior Knowledge: Convolution
Ref. Aaditya Prakash, One by One Convolution: counter-intuitively useful, iamaaditya.github.io/2016/03/one-by-one-convolution
Prior Knowledge: Convolutional Neural Network
Ref. Fei-Fei Li & Andrej Karpathy & Justin Johnson, CS231n: Convolutional Neural Networks for Visual Recognition, Stanford Univ.
Prior Knowledge: Classification vs. Regression
Ref. Cyrille Rossant, IPython Interactive Computing and Visualization Cookbook, Packt Publishing
Prior Knowledge: Computer Vision Tasks
Ref. Fei-Fei Li & Andrej Karpathy & Justin Johnson, CS231n: Convolutional Neural Networks for Visual Recognition, Stanford Univ.
Object Detection: Demo
Ref. Joseph Redmon, YOLO v2, https://www.youtube.com/watch?v=VOC3huqHrss
Object Detection: History
Ref. Sam Albanie, R-FCN: Region-based Fully Convolutional Networks, VGG Reading Group
R-CNN: Pipeline
Ref. Ross Girshick et al., Rich feature hierarchies for accurate object detection and semantic segmentation, arXiv:1311.2524v5 [cs.CV] 22 Oct 2014
R-CNN: Selective Search
Ref. J. R. R. Uijlings et al., Selective Search for Object Recognition, IJCV 2013
Object Detection: History
Ref. Sam Albanie, R-FCN: Region-based Fully Convolutional Networks, VGG Reading Group
Object Detection: Meta-architectures
Ref. Jonathan Huang et al., Speed/accuracy trade-offs for modern convolutional object detectors, arXiv:1611.10012v3 [cs.CV] 25 Apr 2017
Faster R-CNN: Architecture
Ref. Shaoqing Ren et al., Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks, arXiv:1506.01497v3 [cs.CV] 6 Jan 2016
Faster R-CNN: Region Proposal Network
Ref. Shaoqing Ren et al., Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks, arXiv:1506.01497v3 [cs.CV] 6 Jan 2016
Object Detection: Meta-architectures
Ref. Jonathan Huang et al., Speed/accuracy trade-offs for modern convolutional object detectors, arXiv:1611.10012v3 [cs.CV] 25 Apr 2017
R-FCN: Architecture
Ref. Jifeng Dai et al., R-FCN: Object Detection via Region-based Fully Convolutional Network, arXiv:1605.06409v2 [cs.CV] 21 Jun 2016
R-FCN: Position-Sensitive Score Maps
Ref. Jifeng Dai et al., R-FCN: Object Detection via Region-based Fully Convolutional Network, arXiv:1605.06409v2 [cs.CV] 21 Jun 2016
Object Detection: Meta-architectures
Ref. Jonathan Huang et al., Speed/accuracy trade-offs for modern convolutional object detectors, arXiv:1611.10012v3 [cs.CV] 25 Apr 2017
YOLO: Architecture
Ref. Joseph Redmond et al., You Only Look Once: Unified, Real-Time Object Detection, arXiv:1506.02640v5 [cs.CV] 9 May 2016
YOLO: Regression Model
Ref. Joseph Redmond et al., You Only Look Once: Unified, Real-Time Object Detection, arXiv:1506.02640v5 [cs.CV] 9 May 2016
Object Detection: Meta-architectures
Ref. Jonathan Huang et al., Speed/accuracy trade-offs for modern convolutional object detectors, arXiv:1611.10012v3 [cs.CV] 25 Apr 2017
Object Detection Benchmarks: Accuracy
Ref. Jonathan Huang et al., Speed/accuracy trade-offs for modern convolutional object detectors, arXiv:1611.10012v3 [cs.CV] 25 Apr 2017
Object Detection Benchmarks: GPU Time
Ref. Jonathan Huang et al., Speed/accuracy trade-offs for modern convolutional object detectors, arXiv:1611.10012v3 [cs.CV] 25 Apr 2017
Object Detection Benchmarks: Memory Usage
Ref. Jonathan Huang et al., Speed/accuracy trade-offs for modern convolutional object detectors, arXiv:1611.10012v3 [cs.CV] 25 Apr 2017
Object Detection Benchmarks: Accuracy vs. Time
Ref. Jonathan Huang et al., Speed/accuracy trade-offs for modern convolutional object detectors, arXiv:1611.10012v3 [cs.CV] 25 Apr 2017
Welcome to the world where computer understands images.

More Related Content

PDF
[CVPR 2018] Utilizing unlabeled or noisy labeled data (classification, detect...
PDF
PR-110: An Analysis of Scale Invariance in Object Detection – SNIP
PPTX
PR-146: CornerNet detecting objects as paired keypoints
PPTX
EDF2012 Peter Boncz - LOD benchmarking SRbench
PDF
Faster R-CNN: Towards real-time object detection with region proposal network...
PPTX
Deep learning for object detection
PDF
Mobile Visual Search: Object Re-Identification Against Large Repositories
PPTX
Presentation2.pptx of sota seminar iit kanpur
[CVPR 2018] Utilizing unlabeled or noisy labeled data (classification, detect...
PR-110: An Analysis of Scale Invariance in Object Detection – SNIP
PR-146: CornerNet detecting objects as paired keypoints
EDF2012 Peter Boncz - LOD benchmarking SRbench
Faster R-CNN: Towards real-time object detection with region proposal network...
Deep learning for object detection
Mobile Visual Search: Object Re-Identification Against Large Repositories
Presentation2.pptx of sota seminar iit kanpur

Similar to Modern convolutional object detectors (20)

PPT
The Concurrent Constraint Programming Research Programmes -- Redux
PDF
Object Detection - Míriam Bellver - UPC Barcelona 2018
PDF
2015 sibgrapi-contactlenses
PDF
Convolutional Features for Instance Search
PPTX
object-detection.pptx
PDF
rips-hk-lenovo (1)
PPTX
Semantic Data Retrieval: Search, Ranking, and Summarization
PDF
Intermediate inception network for person re-identification
PDF
Recognition and Detection of Real-Time Objects Using Unified Network of Faste...
PPT
Cyberinfrastructure to Support Ocean Observatories
PDF
IRJET - Object Detection using Deep Learning with OpenCV and Python
PDF
Ieee 2016 cs project topics list mtech
PDF
OpenML.org: Networked Science and IoT Data Streams by Jan van Rijn, Universit...
PPTX
reducing firearms based on deep learning
PDF
CV of gongpu lan 20150712
PPT
Creating High Performance Lambda Collaboratories
PDF
Project Chronos Presentation - Machine Learning Italy MeetUp in Turin
PPTX
Faster R-CNN
PDF
IRJET- A Survey on Object Detection using Deep Learning Techniques
PDF
ni2018.pdf
The Concurrent Constraint Programming Research Programmes -- Redux
Object Detection - Míriam Bellver - UPC Barcelona 2018
2015 sibgrapi-contactlenses
Convolutional Features for Instance Search
object-detection.pptx
rips-hk-lenovo (1)
Semantic Data Retrieval: Search, Ranking, and Summarization
Intermediate inception network for person re-identification
Recognition and Detection of Real-Time Objects Using Unified Network of Faste...
Cyberinfrastructure to Support Ocean Observatories
IRJET - Object Detection using Deep Learning with OpenCV and Python
Ieee 2016 cs project topics list mtech
OpenML.org: Networked Science and IoT Data Streams by Jan van Rijn, Universit...
reducing firearms based on deep learning
CV of gongpu lan 20150712
Creating High Performance Lambda Collaboratories
Project Chronos Presentation - Machine Learning Italy MeetUp in Turin
Faster R-CNN
IRJET- A Survey on Object Detection using Deep Learning Techniques
ni2018.pdf
Ad

More from Kwanghee Choi (19)

PDF
Visual Transformers
PDF
Trends of ICASSP 2022
PDF
추천 시스템 한 발짝 떨어져 살펴보기 (3)
PDF
Recommendation systems: Vertical and Horizontal Scrolls
PDF
추천 시스템 한 발짝 떨어져 살펴보기 (1)
PDF
추천 시스템 한 발짝 떨어져 살펴보기 (2)
PDF
Before and After the AI Winter - Recap
PDF
Mastering Gomoku - Recap
PDF
Teachings of Ada Lovelace
PDF
div, grad, curl, and all that - a review
PDF
Gaussian processes
PDF
Neural Architecture Search: Learning How to Learn
PDF
Duality between OOP and RL
PDF
JFEF encoding
PDF
Bandit algorithms for website optimization - A summary
PDF
Dummy log generation using poisson sampling
PDF
Azure functions: Quickstart
PDF
Usage of Moving Average
PPTX
Jpl coding standard for the c programming language
Visual Transformers
Trends of ICASSP 2022
추천 시스템 한 발짝 떨어져 살펴보기 (3)
Recommendation systems: Vertical and Horizontal Scrolls
추천 시스템 한 발짝 떨어져 살펴보기 (1)
추천 시스템 한 발짝 떨어져 살펴보기 (2)
Before and After the AI Winter - Recap
Mastering Gomoku - Recap
Teachings of Ada Lovelace
div, grad, curl, and all that - a review
Gaussian processes
Neural Architecture Search: Learning How to Learn
Duality between OOP and RL
JFEF encoding
Bandit algorithms for website optimization - A summary
Dummy log generation using poisson sampling
Azure functions: Quickstart
Usage of Moving Average
Jpl coding standard for the c programming language
Ad

Recently uploaded (20)

PPTX
Microsoft-Fabric-Unifying-Analytics-for-the-Modern-Enterprise Solution.pptx
PPTX
1_Introduction to advance data techniques.pptx
PDF
TRAFFIC-MANAGEMENT-AND-ACCIDENT-INVESTIGATION-WITH-DRIVING-PDF-FILE.pdf
PDF
22.Patil - Early prediction of Alzheimer’s disease using convolutional neural...
PDF
BF and FI - Blockchain, fintech and Financial Innovation Lesson 2.pdf
PDF
Recruitment and Placement PPT.pdfbjfibjdfbjfobj
PDF
Galatica Smart Energy Infrastructure Startup Pitch Deck
PPTX
Introduction to machine learning and Linear Models
PDF
Foundation of Data Science unit number two notes
PPT
Reliability_Chapter_ presentation 1221.5784
PPTX
Business Acumen Training GuidePresentation.pptx
PPTX
Introduction to Basics of Ethical Hacking and Penetration Testing -Unit No. 1...
PPT
Quality review (1)_presentation of this 21
PPTX
climate analysis of Dhaka ,Banglades.pptx
PPTX
Supervised vs unsupervised machine learning algorithms
PPTX
01_intro xxxxxxxxxxfffffffffffaaaaaaaaaaafg
PPTX
IBA_Chapter_11_Slides_Final_Accessible.pptx
PDF
Business Analytics and business intelligence.pdf
PPTX
Acceptance and paychological effects of mandatory extra coach I classes.pptx
Microsoft-Fabric-Unifying-Analytics-for-the-Modern-Enterprise Solution.pptx
1_Introduction to advance data techniques.pptx
TRAFFIC-MANAGEMENT-AND-ACCIDENT-INVESTIGATION-WITH-DRIVING-PDF-FILE.pdf
22.Patil - Early prediction of Alzheimer’s disease using convolutional neural...
BF and FI - Blockchain, fintech and Financial Innovation Lesson 2.pdf
Recruitment and Placement PPT.pdfbjfibjdfbjfobj
Galatica Smart Energy Infrastructure Startup Pitch Deck
Introduction to machine learning and Linear Models
Foundation of Data Science unit number two notes
Reliability_Chapter_ presentation 1221.5784
Business Acumen Training GuidePresentation.pptx
Introduction to Basics of Ethical Hacking and Penetration Testing -Unit No. 1...
Quality review (1)_presentation of this 21
climate analysis of Dhaka ,Banglades.pptx
Supervised vs unsupervised machine learning algorithms
01_intro xxxxxxxxxxfffffffffffaaaaaaaaaaafg
IBA_Chapter_11_Slides_Final_Accessible.pptx
Business Analytics and business intelligence.pdf
Acceptance and paychological effects of mandatory extra coach I classes.pptx

Modern convolutional object detectors