SlideShare a Scribd company logo
Disp2Flow: Optical flow synthesis using
pre-trained disparity estimation networks
전기정보공학부 김준호
Disp2Flow: Optical flow synthesis using
pre-trained disparity estimation networks
전기정보공학부 김준호
Deep learning trends + My Research
전기정보공학부 김준호
Contents
• What is deep learning?
• Growing trends in deep learning
• Big players in deep learning
• Deep learning @Korea
• My research
What is deep learning?
What is deep learning?
What is machine learning?
• Data -> Learn -> Knowledge (Make predictions on unseen data)
• Examples
Support Vector Machines Gaussian Process Regression
What is machine learning?(cont.)
FAQ: How does unsupervised learning work?
Unsupervised learning is cool but…
• In many cases some form of supervision is necessary
• “Fully unsupervised” learning is impossible -> Some assumptions
about input data should be given!
• No free lunch theorem
• Let’s only focus on supervised learning for now!
Supervised learning
• Goal: Find a function “f” that maps input data to output domain
• Input & output domain could be anything
• Examples
• Input: Images -> Output: Label
• Input: Korean -> Output: English
What is deep learning?
• Consider a supervised learning problem where we want to predict
whether an image is a cat or not
• Again, we want to find “f”
• The relationship between an image and its label will be very complex
• Probably not “y = ax + b”
• We can build “complex” functions using composition!
• Stack “a lot” of functions -> deep learning
What is deep learning?
Y = f(a*f(c*f(e*f….(x)+g)+d) + b)
Growing(Bad) trends in deep learning
Hmmm…
Major AI research areas
Major AI research areas
Top-tier machine learning conferences
• Computer vision
• CVPR
• ICCV
• ECCV
• Natural language processing
• ACL
• EMNLP
• NAACL-HLT
• Machine learning
• NIPS
• ICML
• ICLR
Number of submissions
• CVPR – top tier conference in computer vision
• Acceptance rate: approx. 23%
Number of submissions
• NIPS – top tier machine learning conference
• Acceptance rate: approx. 20%
A typical review process
• Most machine learning conferences use a peer-review system
• Papers are submitted to different “areas”
• Ex) If one submits a paper on classifying cats, it will go under the category of
“image classification”
• Each “area” has an “area chair” – a person who is in charge of all
submission to that “area”
• “Area chairs” distribute the submitted papers to reviewers, who will
eventually decide accept/reject
More papers are good but…
• It means we need more reviewers
• However, the total number of reviewers is limited
• A lot of bad quality reviewers are present
Big players in deep learning
= Diamond sponsors of top-tier conferences
CVPR
ACL
Ilya Sutskever
• Research scientist @OpenAI
• Salary - $1.9 million
Ian Goodfellow
• Research scientist @ Google brain
• Salary - $800,000
Deep learning@Korea
Number of top-tier conference papers are
increasing!
• CVPR 2017, 2018 -> More than 20 papers accepted
• NIPS 2018 -> 20 papers accepted (~5 in NIPS 2017)
• SNU ECE: 3
• SNU CS: 1
• SNU 융기원: 2
• KAIST EE: 5
• KAIST CS: 3
• Yonsei EE: 1
• Yonsei CS: 1
• Kakao brain: 1
• NAVER: 1
• SK T-brain: 1
• Lunit: 1
“Four” companies
My research
Disparity
• Finding disparity leads to depth estimation in stereo vision
• In order to find disparity, we need rectified stereo pairs
• Matching points should be on the ‘same’ horizontal line
Rectified images
Optical flow
• Optical flow is a more general problem, where we want to find
individual movements of pixels
Optical flow -> Disparity
• A 90s paper
Disparity -> Optical flow
• Optical flow training data is hard to find
• In many cases synthetic data is used
• Could we use pre-trained models for disparity estimation to find
optical flow?
Disparity -> Optical flow
• Input: Image pair
• Output: Optical flow
• Novelty: Obtain optical flow estimation using networks trained on
stereo disparity estimation
• Method overview
• Pre-train a neural network(DispNet-Horizontal) on stereo disparity data
• Using basic rotation operations, obtain another neural network(DispNet-
Vertical) on rotated stereo disparity data
• Train a domain transfer network to map optical flow target images to stereo
images(automatic rectification)
• Fine-tune domain transfer network using optical flow ground truth
Disparity -> Optical flow (initial version)
Disparity -> Optical flow (new version)
Disparity -> Optical flow(TODO)
• Pre-train dispnet
• Download optical flow dataset
• Test adequate volume for discriminator
• Implement filter rotation
Questions?

More Related Content

Similar to Deep learning trends

Wastian, Brunmeir - Data Analyses in Industrial Applications: From Predictive...
Wastian, Brunmeir - Data Analyses in Industrial Applications: From Predictive...Wastian, Brunmeir - Data Analyses in Industrial Applications: From Predictive...
Wastian, Brunmeir - Data Analyses in Industrial Applications: From Predictive...Vienna Data Science Group
 
Intro to Neural Networks
Intro to Neural NetworksIntro to Neural Networks
Intro to Neural NetworksDean Wyatte
 
The (very) basics of AI for the Radiology resident
The (very) basics of AI for the Radiology residentThe (very) basics of AI for the Radiology resident
The (very) basics of AI for the Radiology residentPedro Staziaki
 
MLIP - Chapter 3 - Introduction to deep learning
MLIP - Chapter 3 - Introduction to deep learningMLIP - Chapter 3 - Introduction to deep learning
MLIP - Chapter 3 - Introduction to deep learningCharles Deledalle
 
Deep Learning, an interactive introduction for NLP-ers
Deep Learning, an interactive introduction for NLP-ersDeep Learning, an interactive introduction for NLP-ers
Deep Learning, an interactive introduction for NLP-ersRoelof Pieters
 
Introduction to Deep Learning for Image Analysis at Strata NYC, Sep 2015
Introduction to Deep Learning for Image Analysis at Strata NYC, Sep 2015Introduction to Deep Learning for Image Analysis at Strata NYC, Sep 2015
Introduction to Deep Learning for Image Analysis at Strata NYC, Sep 2015Turi, Inc.
 
Introduction to Recurrent Neural Network
Introduction to Recurrent Neural NetworkIntroduction to Recurrent Neural Network
Introduction to Recurrent Neural NetworkYan Xu
 
HiPEAC 2019 Workshop - Real-Time Modelling Visual Scenes with Biological Insp...
HiPEAC 2019 Workshop - Real-Time Modelling Visual Scenes with Biological Insp...HiPEAC 2019 Workshop - Real-Time Modelling Visual Scenes with Biological Insp...
HiPEAC 2019 Workshop - Real-Time Modelling Visual Scenes with Biological Insp...Tulipp. Eu
 
Deep Learning with Python (PyData Seattle 2015)
Deep Learning with Python (PyData Seattle 2015)Deep Learning with Python (PyData Seattle 2015)
Deep Learning with Python (PyData Seattle 2015)Alexander Korbonits
 
Deep Learning in Recommender Systems - RecSys Summer School 2017
Deep Learning in Recommender Systems - RecSys Summer School 2017Deep Learning in Recommender Systems - RecSys Summer School 2017
Deep Learning in Recommender Systems - RecSys Summer School 2017Balázs Hidasi
 
Object extraction from satellite imagery using deep learning
Object extraction from satellite imagery using deep learningObject extraction from satellite imagery using deep learning
Object extraction from satellite imagery using deep learningAly Abdelkareem
 
Computer vision introduction
Computer vision  introduction Computer vision  introduction
Computer vision introduction Wael Badawy
 
MDEC Data Matters Series: machine learning and Deep Learning, A Primer
MDEC Data Matters Series: machine learning and Deep Learning, A PrimerMDEC Data Matters Series: machine learning and Deep Learning, A Primer
MDEC Data Matters Series: machine learning and Deep Learning, A PrimerPoo Kuan Hoong
 
Deep learning introduction
Deep learning introductionDeep learning introduction
Deep learning introductionAdwait Bhave
 
Sean Kandel - Data profiling: Assessing the overall content and quality of a ...
Sean Kandel - Data profiling: Assessing the overall content and quality of a ...Sean Kandel - Data profiling: Assessing the overall content and quality of a ...
Sean Kandel - Data profiling: Assessing the overall content and quality of a ...huguk
 
Introduction talk to Computer Vision
Introduction talk to Computer Vision Introduction talk to Computer Vision
Introduction talk to Computer Vision Chen Sagiv
 
Promises of Deep Learning
Promises of Deep LearningPromises of Deep Learning
Promises of Deep LearningDavid Khosid
 
Introduction to Neural Network
Introduction to Neural NetworkIntroduction to Neural Network
Introduction to Neural NetworkYan Xu
 
Approximate nearest neighbor methods and vector models – NYC ML meetup
Approximate nearest neighbor methods and vector models – NYC ML meetupApproximate nearest neighbor methods and vector models – NYC ML meetup
Approximate nearest neighbor methods and vector models – NYC ML meetupErik Bernhardsson
 

Similar to Deep learning trends (20)

Wastian, Brunmeir - Data Analyses in Industrial Applications: From Predictive...
Wastian, Brunmeir - Data Analyses in Industrial Applications: From Predictive...Wastian, Brunmeir - Data Analyses in Industrial Applications: From Predictive...
Wastian, Brunmeir - Data Analyses in Industrial Applications: From Predictive...
 
Intro to Neural Networks
Intro to Neural NetworksIntro to Neural Networks
Intro to Neural Networks
 
The (very) basics of AI for the Radiology resident
The (very) basics of AI for the Radiology residentThe (very) basics of AI for the Radiology resident
The (very) basics of AI for the Radiology resident
 
MLIP - Chapter 3 - Introduction to deep learning
MLIP - Chapter 3 - Introduction to deep learningMLIP - Chapter 3 - Introduction to deep learning
MLIP - Chapter 3 - Introduction to deep learning
 
Deep Learning, an interactive introduction for NLP-ers
Deep Learning, an interactive introduction for NLP-ersDeep Learning, an interactive introduction for NLP-ers
Deep Learning, an interactive introduction for NLP-ers
 
Introduction to Deep Learning for Image Analysis at Strata NYC, Sep 2015
Introduction to Deep Learning for Image Analysis at Strata NYC, Sep 2015Introduction to Deep Learning for Image Analysis at Strata NYC, Sep 2015
Introduction to Deep Learning for Image Analysis at Strata NYC, Sep 2015
 
Introduction to Recurrent Neural Network
Introduction to Recurrent Neural NetworkIntroduction to Recurrent Neural Network
Introduction to Recurrent Neural Network
 
HiPEAC 2019 Workshop - Real-Time Modelling Visual Scenes with Biological Insp...
HiPEAC 2019 Workshop - Real-Time Modelling Visual Scenes with Biological Insp...HiPEAC 2019 Workshop - Real-Time Modelling Visual Scenes with Biological Insp...
HiPEAC 2019 Workshop - Real-Time Modelling Visual Scenes with Biological Insp...
 
Deep Learning with Python (PyData Seattle 2015)
Deep Learning with Python (PyData Seattle 2015)Deep Learning with Python (PyData Seattle 2015)
Deep Learning with Python (PyData Seattle 2015)
 
Deep Learning in Recommender Systems - RecSys Summer School 2017
Deep Learning in Recommender Systems - RecSys Summer School 2017Deep Learning in Recommender Systems - RecSys Summer School 2017
Deep Learning in Recommender Systems - RecSys Summer School 2017
 
Object extraction from satellite imagery using deep learning
Object extraction from satellite imagery using deep learningObject extraction from satellite imagery using deep learning
Object extraction from satellite imagery using deep learning
 
Computer vision introduction
Computer vision  introduction Computer vision  introduction
Computer vision introduction
 
MDEC Data Matters Series: machine learning and Deep Learning, A Primer
MDEC Data Matters Series: machine learning and Deep Learning, A PrimerMDEC Data Matters Series: machine learning and Deep Learning, A Primer
MDEC Data Matters Series: machine learning and Deep Learning, A Primer
 
Introduction to deep learning
Introduction to deep learningIntroduction to deep learning
Introduction to deep learning
 
Deep learning introduction
Deep learning introductionDeep learning introduction
Deep learning introduction
 
Sean Kandel - Data profiling: Assessing the overall content and quality of a ...
Sean Kandel - Data profiling: Assessing the overall content and quality of a ...Sean Kandel - Data profiling: Assessing the overall content and quality of a ...
Sean Kandel - Data profiling: Assessing the overall content and quality of a ...
 
Introduction talk to Computer Vision
Introduction talk to Computer Vision Introduction talk to Computer Vision
Introduction talk to Computer Vision
 
Promises of Deep Learning
Promises of Deep LearningPromises of Deep Learning
Promises of Deep Learning
 
Introduction to Neural Network
Introduction to Neural NetworkIntroduction to Neural Network
Introduction to Neural Network
 
Approximate nearest neighbor methods and vector models – NYC ML meetup
Approximate nearest neighbor methods and vector models – NYC ML meetupApproximate nearest neighbor methods and vector models – NYC ML meetup
Approximate nearest neighbor methods and vector models – NYC ML meetup
 

Recently uploaded

KIT-601 Lecture Notes-UNIT-4.pdf Frequent Itemsets and Clustering
KIT-601 Lecture Notes-UNIT-4.pdf Frequent Itemsets and ClusteringKIT-601 Lecture Notes-UNIT-4.pdf Frequent Itemsets and Clustering
KIT-601 Lecture Notes-UNIT-4.pdf Frequent Itemsets and ClusteringDr. Radhey Shyam
 
Pharmacy management system project report..pdf
Pharmacy management system project report..pdfPharmacy management system project report..pdf
Pharmacy management system project report..pdfKamal Acharya
 
Peek implant persentation - Copy (1).pdf
Peek implant persentation - Copy (1).pdfPeek implant persentation - Copy (1).pdf
Peek implant persentation - Copy (1).pdfAyahmorsy
 
NO1 Pandit Black Magic Removal in Uk kala jadu Specialist kala jadu for Love ...
NO1 Pandit Black Magic Removal in Uk kala jadu Specialist kala jadu for Love ...NO1 Pandit Black Magic Removal in Uk kala jadu Specialist kala jadu for Love ...
NO1 Pandit Black Magic Removal in Uk kala jadu Specialist kala jadu for Love ...Amil baba
 
Electrostatic field in a coaxial transmission line
Electrostatic field in a coaxial transmission lineElectrostatic field in a coaxial transmission line
Electrostatic field in a coaxial transmission lineJulioCesarSalazarHer1
 
Laundry management system project report.pdf
Laundry management system project report.pdfLaundry management system project report.pdf
Laundry management system project report.pdfKamal Acharya
 
NO1 Pandit Amil Baba In Bahawalpur, Sargodha, Sialkot, Sheikhupura, Rahim Yar...
NO1 Pandit Amil Baba In Bahawalpur, Sargodha, Sialkot, Sheikhupura, Rahim Yar...NO1 Pandit Amil Baba In Bahawalpur, Sargodha, Sialkot, Sheikhupura, Rahim Yar...
NO1 Pandit Amil Baba In Bahawalpur, Sargodha, Sialkot, Sheikhupura, Rahim Yar...Amil baba
 
shape functions of 1D and 2 D rectangular elements.pptx
shape functions of 1D and 2 D rectangular elements.pptxshape functions of 1D and 2 D rectangular elements.pptx
shape functions of 1D and 2 D rectangular elements.pptxVishalDeshpande27
 
Digital Signal Processing Lecture notes n.pdf
Digital Signal Processing Lecture notes n.pdfDigital Signal Processing Lecture notes n.pdf
Digital Signal Processing Lecture notes n.pdfAbrahamGadissa
 
School management system project report.pdf
School management system project report.pdfSchool management system project report.pdf
School management system project report.pdfKamal Acharya
 
HYDROPOWER - Hydroelectric power generation
HYDROPOWER - Hydroelectric power generationHYDROPOWER - Hydroelectric power generation
HYDROPOWER - Hydroelectric power generationRobbie Edward Sayers
 
Event Management System Vb Net Project Report.pdf
Event Management System Vb Net  Project Report.pdfEvent Management System Vb Net  Project Report.pdf
Event Management System Vb Net Project Report.pdfKamal Acharya
 
Cloud-Computing_CSE311_Computer-Networking CSE GUB BD - Shahidul.pptx
Cloud-Computing_CSE311_Computer-Networking CSE GUB BD - Shahidul.pptxCloud-Computing_CSE311_Computer-Networking CSE GUB BD - Shahidul.pptx
Cloud-Computing_CSE311_Computer-Networking CSE GUB BD - Shahidul.pptxMd. Shahidul Islam Prodhan
 
CFD Simulation of By-pass Flow in a HRSG module by R&R Consult.pptx
CFD Simulation of By-pass Flow in a HRSG module by R&R Consult.pptxCFD Simulation of By-pass Flow in a HRSG module by R&R Consult.pptx
CFD Simulation of By-pass Flow in a HRSG module by R&R Consult.pptxR&R Consult
 
2024 DevOps Pro Europe - Growing at the edge
2024 DevOps Pro Europe - Growing at the edge2024 DevOps Pro Europe - Growing at the edge
2024 DevOps Pro Europe - Growing at the edgePaco Orozco
 
RS Khurmi Machine Design Clutch and Brake Exercise Numerical Solutions
RS Khurmi Machine Design Clutch and Brake Exercise Numerical SolutionsRS Khurmi Machine Design Clutch and Brake Exercise Numerical Solutions
RS Khurmi Machine Design Clutch and Brake Exercise Numerical SolutionsAtif Razi
 
RESORT MANAGEMENT AND RESERVATION SYSTEM PROJECT REPORT.pdf
RESORT MANAGEMENT AND RESERVATION SYSTEM PROJECT REPORT.pdfRESORT MANAGEMENT AND RESERVATION SYSTEM PROJECT REPORT.pdf
RESORT MANAGEMENT AND RESERVATION SYSTEM PROJECT REPORT.pdfKamal Acharya
 
İTÜ CAD and Reverse Engineering Workshop
İTÜ CAD and Reverse Engineering WorkshopİTÜ CAD and Reverse Engineering Workshop
İTÜ CAD and Reverse Engineering WorkshopEmre Günaydın
 
BRAKING SYSTEM IN INDIAN RAILWAY AutoCAD DRAWING
BRAKING SYSTEM IN INDIAN RAILWAY AutoCAD DRAWINGBRAKING SYSTEM IN INDIAN RAILWAY AutoCAD DRAWING
BRAKING SYSTEM IN INDIAN RAILWAY AutoCAD DRAWINGKOUSTAV SARKAR
 

Recently uploaded (20)

KIT-601 Lecture Notes-UNIT-4.pdf Frequent Itemsets and Clustering
KIT-601 Lecture Notes-UNIT-4.pdf Frequent Itemsets and ClusteringKIT-601 Lecture Notes-UNIT-4.pdf Frequent Itemsets and Clustering
KIT-601 Lecture Notes-UNIT-4.pdf Frequent Itemsets and Clustering
 
Pharmacy management system project report..pdf
Pharmacy management system project report..pdfPharmacy management system project report..pdf
Pharmacy management system project report..pdf
 
Peek implant persentation - Copy (1).pdf
Peek implant persentation - Copy (1).pdfPeek implant persentation - Copy (1).pdf
Peek implant persentation - Copy (1).pdf
 
NO1 Pandit Black Magic Removal in Uk kala jadu Specialist kala jadu for Love ...
NO1 Pandit Black Magic Removal in Uk kala jadu Specialist kala jadu for Love ...NO1 Pandit Black Magic Removal in Uk kala jadu Specialist kala jadu for Love ...
NO1 Pandit Black Magic Removal in Uk kala jadu Specialist kala jadu for Love ...
 
Electrostatic field in a coaxial transmission line
Electrostatic field in a coaxial transmission lineElectrostatic field in a coaxial transmission line
Electrostatic field in a coaxial transmission line
 
Laundry management system project report.pdf
Laundry management system project report.pdfLaundry management system project report.pdf
Laundry management system project report.pdf
 
NO1 Pandit Amil Baba In Bahawalpur, Sargodha, Sialkot, Sheikhupura, Rahim Yar...
NO1 Pandit Amil Baba In Bahawalpur, Sargodha, Sialkot, Sheikhupura, Rahim Yar...NO1 Pandit Amil Baba In Bahawalpur, Sargodha, Sialkot, Sheikhupura, Rahim Yar...
NO1 Pandit Amil Baba In Bahawalpur, Sargodha, Sialkot, Sheikhupura, Rahim Yar...
 
shape functions of 1D and 2 D rectangular elements.pptx
shape functions of 1D and 2 D rectangular elements.pptxshape functions of 1D and 2 D rectangular elements.pptx
shape functions of 1D and 2 D rectangular elements.pptx
 
Digital Signal Processing Lecture notes n.pdf
Digital Signal Processing Lecture notes n.pdfDigital Signal Processing Lecture notes n.pdf
Digital Signal Processing Lecture notes n.pdf
 
School management system project report.pdf
School management system project report.pdfSchool management system project report.pdf
School management system project report.pdf
 
HYDROPOWER - Hydroelectric power generation
HYDROPOWER - Hydroelectric power generationHYDROPOWER - Hydroelectric power generation
HYDROPOWER - Hydroelectric power generation
 
Event Management System Vb Net Project Report.pdf
Event Management System Vb Net  Project Report.pdfEvent Management System Vb Net  Project Report.pdf
Event Management System Vb Net Project Report.pdf
 
Cloud-Computing_CSE311_Computer-Networking CSE GUB BD - Shahidul.pptx
Cloud-Computing_CSE311_Computer-Networking CSE GUB BD - Shahidul.pptxCloud-Computing_CSE311_Computer-Networking CSE GUB BD - Shahidul.pptx
Cloud-Computing_CSE311_Computer-Networking CSE GUB BD - Shahidul.pptx
 
Standard Reomte Control Interface - Neometrix
Standard Reomte Control Interface - NeometrixStandard Reomte Control Interface - Neometrix
Standard Reomte Control Interface - Neometrix
 
CFD Simulation of By-pass Flow in a HRSG module by R&R Consult.pptx
CFD Simulation of By-pass Flow in a HRSG module by R&R Consult.pptxCFD Simulation of By-pass Flow in a HRSG module by R&R Consult.pptx
CFD Simulation of By-pass Flow in a HRSG module by R&R Consult.pptx
 
2024 DevOps Pro Europe - Growing at the edge
2024 DevOps Pro Europe - Growing at the edge2024 DevOps Pro Europe - Growing at the edge
2024 DevOps Pro Europe - Growing at the edge
 
RS Khurmi Machine Design Clutch and Brake Exercise Numerical Solutions
RS Khurmi Machine Design Clutch and Brake Exercise Numerical SolutionsRS Khurmi Machine Design Clutch and Brake Exercise Numerical Solutions
RS Khurmi Machine Design Clutch and Brake Exercise Numerical Solutions
 
RESORT MANAGEMENT AND RESERVATION SYSTEM PROJECT REPORT.pdf
RESORT MANAGEMENT AND RESERVATION SYSTEM PROJECT REPORT.pdfRESORT MANAGEMENT AND RESERVATION SYSTEM PROJECT REPORT.pdf
RESORT MANAGEMENT AND RESERVATION SYSTEM PROJECT REPORT.pdf
 
İTÜ CAD and Reverse Engineering Workshop
İTÜ CAD and Reverse Engineering WorkshopİTÜ CAD and Reverse Engineering Workshop
İTÜ CAD and Reverse Engineering Workshop
 
BRAKING SYSTEM IN INDIAN RAILWAY AutoCAD DRAWING
BRAKING SYSTEM IN INDIAN RAILWAY AutoCAD DRAWINGBRAKING SYSTEM IN INDIAN RAILWAY AutoCAD DRAWING
BRAKING SYSTEM IN INDIAN RAILWAY AutoCAD DRAWING
 

Deep learning trends

  • 1. Disp2Flow: Optical flow synthesis using pre-trained disparity estimation networks 전기정보공학부 김준호
  • 2. Disp2Flow: Optical flow synthesis using pre-trained disparity estimation networks 전기정보공학부 김준호
  • 3. Deep learning trends + My Research 전기정보공학부 김준호
  • 4. Contents • What is deep learning? • Growing trends in deep learning • Big players in deep learning • Deep learning @Korea • My research
  • 5. What is deep learning?
  • 6. What is deep learning?
  • 7. What is machine learning? • Data -> Learn -> Knowledge (Make predictions on unseen data) • Examples Support Vector Machines Gaussian Process Regression
  • 8. What is machine learning?(cont.)
  • 9. FAQ: How does unsupervised learning work?
  • 10. Unsupervised learning is cool but… • In many cases some form of supervision is necessary • “Fully unsupervised” learning is impossible -> Some assumptions about input data should be given! • No free lunch theorem • Let’s only focus on supervised learning for now!
  • 11. Supervised learning • Goal: Find a function “f” that maps input data to output domain • Input & output domain could be anything • Examples • Input: Images -> Output: Label • Input: Korean -> Output: English
  • 12. What is deep learning? • Consider a supervised learning problem where we want to predict whether an image is a cat or not • Again, we want to find “f” • The relationship between an image and its label will be very complex • Probably not “y = ax + b” • We can build “complex” functions using composition! • Stack “a lot” of functions -> deep learning
  • 13. What is deep learning? Y = f(a*f(c*f(e*f….(x)+g)+d) + b)
  • 14. Growing(Bad) trends in deep learning
  • 18. Top-tier machine learning conferences • Computer vision • CVPR • ICCV • ECCV • Natural language processing • ACL • EMNLP • NAACL-HLT • Machine learning • NIPS • ICML • ICLR
  • 19. Number of submissions • CVPR – top tier conference in computer vision • Acceptance rate: approx. 23%
  • 20. Number of submissions • NIPS – top tier machine learning conference • Acceptance rate: approx. 20%
  • 21. A typical review process • Most machine learning conferences use a peer-review system • Papers are submitted to different “areas” • Ex) If one submits a paper on classifying cats, it will go under the category of “image classification” • Each “area” has an “area chair” – a person who is in charge of all submission to that “area” • “Area chairs” distribute the submitted papers to reviewers, who will eventually decide accept/reject
  • 22. More papers are good but… • It means we need more reviewers • However, the total number of reviewers is limited • A lot of bad quality reviewers are present
  • 23.
  • 24. Big players in deep learning
  • 25. = Diamond sponsors of top-tier conferences
  • 26. CVPR
  • 27. ACL
  • 28. Ilya Sutskever • Research scientist @OpenAI • Salary - $1.9 million
  • 29. Ian Goodfellow • Research scientist @ Google brain • Salary - $800,000
  • 31. Number of top-tier conference papers are increasing! • CVPR 2017, 2018 -> More than 20 papers accepted • NIPS 2018 -> 20 papers accepted (~5 in NIPS 2017) • SNU ECE: 3 • SNU CS: 1 • SNU 융기원: 2 • KAIST EE: 5 • KAIST CS: 3 • Yonsei EE: 1 • Yonsei CS: 1 • Kakao brain: 1 • NAVER: 1 • SK T-brain: 1 • Lunit: 1
  • 34. Disparity • Finding disparity leads to depth estimation in stereo vision • In order to find disparity, we need rectified stereo pairs • Matching points should be on the ‘same’ horizontal line
  • 36. Optical flow • Optical flow is a more general problem, where we want to find individual movements of pixels
  • 37. Optical flow -> Disparity • A 90s paper
  • 38. Disparity -> Optical flow • Optical flow training data is hard to find • In many cases synthetic data is used • Could we use pre-trained models for disparity estimation to find optical flow?
  • 39. Disparity -> Optical flow • Input: Image pair • Output: Optical flow • Novelty: Obtain optical flow estimation using networks trained on stereo disparity estimation • Method overview • Pre-train a neural network(DispNet-Horizontal) on stereo disparity data • Using basic rotation operations, obtain another neural network(DispNet- Vertical) on rotated stereo disparity data • Train a domain transfer network to map optical flow target images to stereo images(automatic rectification) • Fine-tune domain transfer network using optical flow ground truth
  • 40. Disparity -> Optical flow (initial version)
  • 41. Disparity -> Optical flow (new version)
  • 42. Disparity -> Optical flow(TODO) • Pre-train dispnet • Download optical flow dataset • Test adequate volume for discriminator • Implement filter rotation