SlideShare una empresa de Scribd logo
1 de 16
Descargar para leer sin conexión
PR-100:
SeedNet: Automatic Seed Generation with Deep
Reinforcement Learning for Robust Interactive Segmentation
CVPR2018
Gwangmo Song, Heesoo Myeong, Kyoung Mu Lee
인공지능연구원
이광희
2
논문 선정의 이유..
Chen, Tao, et al. "PhotoSketch: Internet image montage." SIGGRAPH Asia (2009).
3
논문 선정의 이유..
스케치
배경
오브젝트
사진 선택
이미지 조합
사용될 이미지 생성
팔레트
최종 결과물
텍스트소나무
+
전체 스타일 변환 (팔레트)
브러시
부분 수정 및 조정 (브러시)
이미지 생성 모델
스타일 변환 모델
검색
4
논문 선정의 이유..
5
Related Works : Interactive Segmentation
Deep extreme cut: From extreme points to object segmentation. CVPR2018
Grabcut: Interactive foreground extraction using iterated graph cuts. Siggraph2003
Methods:
Grabcut
Random walk
Geodesic
Deep extremecut
.
.
.
Seed types:
Rectangle
Scribble
Contour
Extreme point
.
.
6
 Classification, image captioning, video tracking, face
hallucination, …
Related Works : RL in Computer Vision
Active Object Localization with Deep Reinforcement Learning. ICCV2015
Distort-and-Recover: Color enhancement using deep reinforcement learning. CVPR2018
7
 An automatic seed generation technique with deep RL to solve the interactive segmentation
problem
 Robust and consistent object extraction with less human effort
 User first select two points- foreground & background
 A sequence of artificial user input is automatically generated
 Markov Decision Process(MDP) / Deep Q-Network(DQN)
Motivation
8
 Introduction of a MDP formulation for the interactive segmentation
task
 The novel reward function design: Intersection Over Union(IOU)
score
 Why deep RL?
• Cannot define globally optimal seed at some stage of interactive segmentation
Contributions
9
Automatic Seed Generation System
Markov Decision Process(MDP)
- State: input image + segmented mask by new seeds
- Action: 800 actions, label(fg/bg), position of the seed in the 2D grid(20x20)
- Reward:
Segmentation method: Random Walk(RW) segmentation
Binary Mask
- Compute reward signal
- An observation of the next iteration
Termination: 10 seed points
DQN architecture
SF: Strong Foreground
SB: Strong Background
WF: Weak Foreground
WB: Weak Background
10
Experiments
 MSRA10K saliency dataset
 Training: 9000 images, Test: 1000 images, Total: 10000 images
 Image size: about 400x300 pixels
 Training/testing Input size: 84x84
 Segmentation
• Training: 84x84(for accelerate), seed point size(3 pixels)
• Testing: original size, seed point size(13 pixels)
 Termination: 10 times (average number of seeds until saturation:
5.39)
11
Interactive Segmentation Results
12
 Comparison with supervised methods
 FCN/iFCN
 Fully-connected layer to convolutional layer
 80x80 input image
Interactive Segmentation Results
13
Ablation Experiments-Reward
14
Ablation Experiments-Segmentation
15
Unseen Dataset Experiments
PR12 1기 멤버분들 모두
1년동안 수고 많으셨습니다.

Más contenido relacionado

La actualidad más candente

深度學習在AOI的應用
深度學習在AOI的應用深度學習在AOI的應用
深度學習在AOI的應用CHENHuiMei
 
Obscenity Detection in Images
Obscenity Detection in ImagesObscenity Detection in Images
Obscenity Detection in ImagesAnil Kumar Gupta
 
[CVPR2020] Simple but effective image enhancement techniques
[CVPR2020] Simple but effective image enhancement techniques[CVPR2020] Simple but effective image enhancement techniques
[CVPR2020] Simple but effective image enhancement techniquesJaeJun Yoo
 
Color based image processing , tracking and automation using matlab
Color based image processing , tracking and automation using matlabColor based image processing , tracking and automation using matlab
Color based image processing , tracking and automation using matlabKamal Pradhan
 
Face Detection System on Ada boost Algorithm Using Haar Classifiers
Face Detection System on Ada boost Algorithm Using Haar ClassifiersFace Detection System on Ada boost Algorithm Using Haar Classifiers
Face Detection System on Ada boost Algorithm Using Haar ClassifiersIJMER
 
Review : Structure Boundary Preserving Segmentation
for Medical Image with Am...
Review : Structure Boundary Preserving Segmentation
for Medical Image with Am...Review : Structure Boundary Preserving Segmentation
for Medical Image with Am...
Review : Structure Boundary Preserving Segmentation
for Medical Image with Am...Dongmin Choi
 
Pratik ibm-open power-ppt
Pratik ibm-open power-pptPratik ibm-open power-ppt
Pratik ibm-open power-pptVaibhav R
 
Deep learning for person re-identification
Deep learning for person re-identificationDeep learning for person re-identification
Deep learning for person re-identification哲东 郑
 
Modeling perceptual similarity and shift invariance in deep networks
Modeling perceptual similarity and shift invariance in deep networksModeling perceptual similarity and shift invariance in deep networks
Modeling perceptual similarity and shift invariance in deep networksNAVER Engineering
 
Automatic Image Annotation (AIA)
Automatic Image Annotation (AIA)Automatic Image Annotation (AIA)
Automatic Image Annotation (AIA)Farzaneh Rezaei
 
An Introduction to Computer Vision
An Introduction to Computer VisionAn Introduction to Computer Vision
An Introduction to Computer Visionguestd1b1b5
 
Performance analysis on color image mosaicing techniques on FPGA
Performance analysis on color image mosaicing techniques on FPGAPerformance analysis on color image mosaicing techniques on FPGA
Performance analysis on color image mosaicing techniques on FPGAIJECEIAES
 
[PR12] Generative Models as Distributions of Functions
[PR12] Generative Models as Distributions of Functions[PR12] Generative Models as Distributions of Functions
[PR12] Generative Models as Distributions of FunctionsJaeJun Yoo
 
Object detection presentation
Object detection presentationObject detection presentation
Object detection presentationAshwinBicholiya
 
NIPS2015 reading - Learning visual biases from human imagination
NIPS2015 reading - Learning visual biases from human imaginationNIPS2015 reading - Learning visual biases from human imagination
NIPS2015 reading - Learning visual biases from human imaginationAkisato Kimura
 
Tracking Chessboard Corners Using Projective Transformation for Augmented Rea...
Tracking Chessboard Corners Using Projective Transformation for Augmented Rea...Tracking Chessboard Corners Using Projective Transformation for Augmented Rea...
Tracking Chessboard Corners Using Projective Transformation for Augmented Rea...CSCJournals
 
“An Introduction to Data Augmentation Techniques in ML Frameworks,” a Present...
“An Introduction to Data Augmentation Techniques in ML Frameworks,” a Present...“An Introduction to Data Augmentation Techniques in ML Frameworks,” a Present...
“An Introduction to Data Augmentation Techniques in ML Frameworks,” a Present...Edge AI and Vision Alliance
 
BOIL: Towards Representation Change for Few-shot Learning
BOIL: Towards Representation Change for Few-shot LearningBOIL: Towards Representation Change for Few-shot Learning
BOIL: Towards Representation Change for Few-shot LearningHyungjun Yoo
 

La actualidad más candente (20)

深度學習在AOI的應用
深度學習在AOI的應用深度學習在AOI的應用
深度學習在AOI的應用
 
Step zhedong
Step zhedongStep zhedong
Step zhedong
 
Obscenity Detection in Images
Obscenity Detection in ImagesObscenity Detection in Images
Obscenity Detection in Images
 
[CVPR2020] Simple but effective image enhancement techniques
[CVPR2020] Simple but effective image enhancement techniques[CVPR2020] Simple but effective image enhancement techniques
[CVPR2020] Simple but effective image enhancement techniques
 
Color based image processing , tracking and automation using matlab
Color based image processing , tracking and automation using matlabColor based image processing , tracking and automation using matlab
Color based image processing , tracking and automation using matlab
 
Face Detection System on Ada boost Algorithm Using Haar Classifiers
Face Detection System on Ada boost Algorithm Using Haar ClassifiersFace Detection System on Ada boost Algorithm Using Haar Classifiers
Face Detection System on Ada boost Algorithm Using Haar Classifiers
 
Review : Structure Boundary Preserving Segmentation
for Medical Image with Am...
Review : Structure Boundary Preserving Segmentation
for Medical Image with Am...Review : Structure Boundary Preserving Segmentation
for Medical Image with Am...
Review : Structure Boundary Preserving Segmentation
for Medical Image with Am...
 
Pratik ibm-open power-ppt
Pratik ibm-open power-pptPratik ibm-open power-ppt
Pratik ibm-open power-ppt
 
Deep learning for person re-identification
Deep learning for person re-identificationDeep learning for person re-identification
Deep learning for person re-identification
 
Modeling perceptual similarity and shift invariance in deep networks
Modeling perceptual similarity and shift invariance in deep networksModeling perceptual similarity and shift invariance in deep networks
Modeling perceptual similarity and shift invariance in deep networks
 
Automatic Image Annotation (AIA)
Automatic Image Annotation (AIA)Automatic Image Annotation (AIA)
Automatic Image Annotation (AIA)
 
An Introduction to Computer Vision
An Introduction to Computer VisionAn Introduction to Computer Vision
An Introduction to Computer Vision
 
Performance analysis on color image mosaicing techniques on FPGA
Performance analysis on color image mosaicing techniques on FPGAPerformance analysis on color image mosaicing techniques on FPGA
Performance analysis on color image mosaicing techniques on FPGA
 
[PR12] Generative Models as Distributions of Functions
[PR12] Generative Models as Distributions of Functions[PR12] Generative Models as Distributions of Functions
[PR12] Generative Models as Distributions of Functions
 
Object detection presentation
Object detection presentationObject detection presentation
Object detection presentation
 
NIPS2015 reading - Learning visual biases from human imagination
NIPS2015 reading - Learning visual biases from human imaginationNIPS2015 reading - Learning visual biases from human imagination
NIPS2015 reading - Learning visual biases from human imagination
 
Tracking Chessboard Corners Using Projective Transformation for Augmented Rea...
Tracking Chessboard Corners Using Projective Transformation for Augmented Rea...Tracking Chessboard Corners Using Projective Transformation for Augmented Rea...
Tracking Chessboard Corners Using Projective Transformation for Augmented Rea...
 
Image analytics - A Primer
Image analytics - A PrimerImage analytics - A Primer
Image analytics - A Primer
 
“An Introduction to Data Augmentation Techniques in ML Frameworks,” a Present...
“An Introduction to Data Augmentation Techniques in ML Frameworks,” a Present...“An Introduction to Data Augmentation Techniques in ML Frameworks,” a Present...
“An Introduction to Data Augmentation Techniques in ML Frameworks,” a Present...
 
BOIL: Towards Representation Change for Few-shot Learning
BOIL: Towards Representation Change for Few-shot LearningBOIL: Towards Representation Change for Few-shot Learning
BOIL: Towards Representation Change for Few-shot Learning
 

Similar a PR100: SeedNet: Automatic Seed Generation with Deep Reinforcement Learning for Robust Interactive Segmentation

Seed net automatic seed generation with deep reinforcement learning for robus...
Seed net automatic seed generation with deep reinforcement learning for robus...Seed net automatic seed generation with deep reinforcement learning for robus...
Seed net automatic seed generation with deep reinforcement learning for robus...NAVER Engineering
 
Learning with Relative Attributes
Learning with Relative AttributesLearning with Relative Attributes
Learning with Relative AttributesVikas Jain
 
#6 PyData Warsaw: Deep learning for image segmentation
#6 PyData Warsaw: Deep learning for image segmentation#6 PyData Warsaw: Deep learning for image segmentation
#6 PyData Warsaw: Deep learning for image segmentationMatthew Opala
 
Recent advances of AI for medical imaging : Engineering perspectives
Recent advances of AI for medical imaging : Engineering perspectivesRecent advances of AI for medical imaging : Engineering perspectives
Recent advances of AI for medical imaging : Engineering perspectivesNamkug Kim
 
Course Title CS591-Advance Artificial Intelligence
Course Title CS591-Advance Artificial Intelligence           Course Title CS591-Advance Artificial Intelligence
Course Title CS591-Advance Artificial Intelligence CruzIbarra161
 
Avihu Efrat's Viola and Jones face detection slides
Avihu Efrat's Viola and Jones face detection slidesAvihu Efrat's Viola and Jones face detection slides
Avihu Efrat's Viola and Jones face detection slideswolf
 
ML Paper Tutorial - Video Face Manipulation Detection Through Ensemble of CNN...
ML Paper Tutorial - Video Face Manipulation Detection Through Ensemble of CNN...ML Paper Tutorial - Video Face Manipulation Detection Through Ensemble of CNN...
ML Paper Tutorial - Video Face Manipulation Detection Through Ensemble of CNN...Pei-Yuan Chien
 
Performance evaluation of GANs in a semisupervised OCR use case
Performance evaluation of GANs in a semisupervised OCR use casePerformance evaluation of GANs in a semisupervised OCR use case
Performance evaluation of GANs in a semisupervised OCR use caseFlorian Wilhelm
 
Performance evaluation of GANs in a semisupervised OCR use case
Performance evaluation of GANs in a semisupervised OCR use casePerformance evaluation of GANs in a semisupervised OCR use case
Performance evaluation of GANs in a semisupervised OCR use caseinovex GmbH
 
Rapid object detection using boosted cascade of simple features
Rapid object detection using boosted  cascade of simple featuresRapid object detection using boosted  cascade of simple features
Rapid object detection using boosted cascade of simple featuresHirantha Pradeep
 
Unsupervised Computer Vision: The Current State of the Art
Unsupervised Computer Vision: The Current State of the ArtUnsupervised Computer Vision: The Current State of the Art
Unsupervised Computer Vision: The Current State of the ArtTJ Torres
 
Atari Game State Representation using Convolutional Neural Networks
Atari Game State Representation using Convolutional Neural NetworksAtari Game State Representation using Convolutional Neural Networks
Atari Game State Representation using Convolutional Neural Networksjohnstamford
 
B4UConference_machine learning_deeplearning
B4UConference_machine learning_deeplearningB4UConference_machine learning_deeplearning
B4UConference_machine learning_deeplearningHoa Le
 
K-Means Clustering in Moving Objects Extraction with Selective Background
K-Means Clustering in Moving Objects Extraction with Selective BackgroundK-Means Clustering in Moving Objects Extraction with Selective Background
K-Means Clustering in Moving Objects Extraction with Selective BackgroundIJCSIS Research Publications
 
brief Introduction to Different Kinds of GANs
brief Introduction to Different Kinds of GANsbrief Introduction to Different Kinds of GANs
brief Introduction to Different Kinds of GANsParham Zilouchian
 
Image classification with Deep Neural Networks
Image classification with Deep Neural NetworksImage classification with Deep Neural Networks
Image classification with Deep Neural NetworksYogendra Tamang
 

Similar a PR100: SeedNet: Automatic Seed Generation with Deep Reinforcement Learning for Robust Interactive Segmentation (20)

Seed net automatic seed generation with deep reinforcement learning for robus...
Seed net automatic seed generation with deep reinforcement learning for robus...Seed net automatic seed generation with deep reinforcement learning for robus...
Seed net automatic seed generation with deep reinforcement learning for robus...
 
final ppt
final pptfinal ppt
final ppt
 
Learning with Relative Attributes
Learning with Relative AttributesLearning with Relative Attributes
Learning with Relative Attributes
 
#6 PyData Warsaw: Deep learning for image segmentation
#6 PyData Warsaw: Deep learning for image segmentation#6 PyData Warsaw: Deep learning for image segmentation
#6 PyData Warsaw: Deep learning for image segmentation
 
Recent advances of AI for medical imaging : Engineering perspectives
Recent advances of AI for medical imaging : Engineering perspectivesRecent advances of AI for medical imaging : Engineering perspectives
Recent advances of AI for medical imaging : Engineering perspectives
 
Course Title CS591-Advance Artificial Intelligence
Course Title CS591-Advance Artificial Intelligence           Course Title CS591-Advance Artificial Intelligence
Course Title CS591-Advance Artificial Intelligence
 
Avihu Efrat's Viola and Jones face detection slides
Avihu Efrat's Viola and Jones face detection slidesAvihu Efrat's Viola and Jones face detection slides
Avihu Efrat's Viola and Jones face detection slides
 
ML Paper Tutorial - Video Face Manipulation Detection Through Ensemble of CNN...
ML Paper Tutorial - Video Face Manipulation Detection Through Ensemble of CNN...ML Paper Tutorial - Video Face Manipulation Detection Through Ensemble of CNN...
ML Paper Tutorial - Video Face Manipulation Detection Through Ensemble of CNN...
 
AI and Deep Learning
AI and Deep Learning AI and Deep Learning
AI and Deep Learning
 
Performance evaluation of GANs in a semisupervised OCR use case
Performance evaluation of GANs in a semisupervised OCR use casePerformance evaluation of GANs in a semisupervised OCR use case
Performance evaluation of GANs in a semisupervised OCR use case
 
Performance evaluation of GANs in a semisupervised OCR use case
Performance evaluation of GANs in a semisupervised OCR use casePerformance evaluation of GANs in a semisupervised OCR use case
Performance evaluation of GANs in a semisupervised OCR use case
 
Rapid object detection using boosted cascade of simple features
Rapid object detection using boosted  cascade of simple featuresRapid object detection using boosted  cascade of simple features
Rapid object detection using boosted cascade of simple features
 
Unsupervised Computer Vision: The Current State of the Art
Unsupervised Computer Vision: The Current State of the ArtUnsupervised Computer Vision: The Current State of the Art
Unsupervised Computer Vision: The Current State of the Art
 
Atari Game State Representation using Convolutional Neural Networks
Atari Game State Representation using Convolutional Neural NetworksAtari Game State Representation using Convolutional Neural Networks
Atari Game State Representation using Convolutional Neural Networks
 
N046047780
N046047780N046047780
N046047780
 
B4UConference_machine learning_deeplearning
B4UConference_machine learning_deeplearningB4UConference_machine learning_deeplearning
B4UConference_machine learning_deeplearning
 
K-Means Clustering in Moving Objects Extraction with Selective Background
K-Means Clustering in Moving Objects Extraction with Selective BackgroundK-Means Clustering in Moving Objects Extraction with Selective Background
K-Means Clustering in Moving Objects Extraction with Selective Background
 
brief Introduction to Different Kinds of GANs
brief Introduction to Different Kinds of GANsbrief Introduction to Different Kinds of GANs
brief Introduction to Different Kinds of GANs
 
Eren_Golge_MS_Thesis_2014
Eren_Golge_MS_Thesis_2014Eren_Golge_MS_Thesis_2014
Eren_Golge_MS_Thesis_2014
 
Image classification with Deep Neural Networks
Image classification with Deep Neural NetworksImage classification with Deep Neural Networks
Image classification with Deep Neural Networks
 

Último

IaC & GitOps in a Nutshell - a FridayInANuthshell Episode.pdf
IaC & GitOps in a Nutshell - a FridayInANuthshell Episode.pdfIaC & GitOps in a Nutshell - a FridayInANuthshell Episode.pdf
IaC & GitOps in a Nutshell - a FridayInANuthshell Episode.pdfDaniel Santiago Silva Capera
 
IESVE Software for Florida Code Compliance Using ASHRAE 90.1-2019
IESVE Software for Florida Code Compliance Using ASHRAE 90.1-2019IESVE Software for Florida Code Compliance Using ASHRAE 90.1-2019
IESVE Software for Florida Code Compliance Using ASHRAE 90.1-2019IES VE
 
ADOPTING WEB 3 FOR YOUR BUSINESS: A STEP-BY-STEP GUIDE
ADOPTING WEB 3 FOR YOUR BUSINESS: A STEP-BY-STEP GUIDEADOPTING WEB 3 FOR YOUR BUSINESS: A STEP-BY-STEP GUIDE
ADOPTING WEB 3 FOR YOUR BUSINESS: A STEP-BY-STEP GUIDELiveplex
 
VoIP Service and Marketing using Odoo and Asterisk PBX
VoIP Service and Marketing using Odoo and Asterisk PBXVoIP Service and Marketing using Odoo and Asterisk PBX
VoIP Service and Marketing using Odoo and Asterisk PBXTarek Kalaji
 
UiPath Solutions Management Preview - Northern CA Chapter - March 22.pdf
UiPath Solutions Management Preview - Northern CA Chapter - March 22.pdfUiPath Solutions Management Preview - Northern CA Chapter - March 22.pdf
UiPath Solutions Management Preview - Northern CA Chapter - March 22.pdfDianaGray10
 
Meet the new FSP 3000 M-Flex800™
Meet the new FSP 3000 M-Flex800™Meet the new FSP 3000 M-Flex800™
Meet the new FSP 3000 M-Flex800™Adtran
 
AI Fame Rush Review – Virtual Influencer Creation In Just Minutes
AI Fame Rush Review – Virtual Influencer Creation In Just MinutesAI Fame Rush Review – Virtual Influencer Creation In Just Minutes
AI Fame Rush Review – Virtual Influencer Creation In Just MinutesMd Hossain Ali
 
OpenShift Commons Paris - Choose Your Own Observability Adventure
OpenShift Commons Paris - Choose Your Own Observability AdventureOpenShift Commons Paris - Choose Your Own Observability Adventure
OpenShift Commons Paris - Choose Your Own Observability AdventureEric D. Schabell
 
KubeConEU24-Monitoring Kubernetes and Cloud Spend with OpenCost
KubeConEU24-Monitoring Kubernetes and Cloud Spend with OpenCostKubeConEU24-Monitoring Kubernetes and Cloud Spend with OpenCost
KubeConEU24-Monitoring Kubernetes and Cloud Spend with OpenCostMatt Ray
 
Bird eye's view on Camunda open source ecosystem
Bird eye's view on Camunda open source ecosystemBird eye's view on Camunda open source ecosystem
Bird eye's view on Camunda open source ecosystemAsko Soukka
 
Computer 10: Lesson 10 - Online Crimes and Hazards
Computer 10: Lesson 10 - Online Crimes and HazardsComputer 10: Lesson 10 - Online Crimes and Hazards
Computer 10: Lesson 10 - Online Crimes and HazardsSeth Reyes
 
NIST Cybersecurity Framework (CSF) 2.0 Workshop
NIST Cybersecurity Framework (CSF) 2.0 WorkshopNIST Cybersecurity Framework (CSF) 2.0 Workshop
NIST Cybersecurity Framework (CSF) 2.0 WorkshopBachir Benyammi
 
Secure your environment with UiPath and CyberArk technologies - Session 1
Secure your environment with UiPath and CyberArk technologies - Session 1Secure your environment with UiPath and CyberArk technologies - Session 1
Secure your environment with UiPath and CyberArk technologies - Session 1DianaGray10
 
Comparing Sidecar-less Service Mesh from Cilium and Istio
Comparing Sidecar-less Service Mesh from Cilium and IstioComparing Sidecar-less Service Mesh from Cilium and Istio
Comparing Sidecar-less Service Mesh from Cilium and IstioChristian Posta
 
UWB Technology for Enhanced Indoor and Outdoor Positioning in Physiological M...
UWB Technology for Enhanced Indoor and Outdoor Positioning in Physiological M...UWB Technology for Enhanced Indoor and Outdoor Positioning in Physiological M...
UWB Technology for Enhanced Indoor and Outdoor Positioning in Physiological M...UbiTrack UK
 
Designing A Time bound resource download URL
Designing A Time bound resource download URLDesigning A Time bound resource download URL
Designing A Time bound resource download URLRuncy Oommen
 
Cybersecurity Workshop #1.pptx
Cybersecurity Workshop #1.pptxCybersecurity Workshop #1.pptx
Cybersecurity Workshop #1.pptxGDSC PJATK
 
Videogame localization & technology_ how to enhance the power of translation.pdf
Videogame localization & technology_ how to enhance the power of translation.pdfVideogame localization & technology_ how to enhance the power of translation.pdf
Videogame localization & technology_ how to enhance the power of translation.pdfinfogdgmi
 
Linked Data in Production: Moving Beyond Ontologies
Linked Data in Production: Moving Beyond OntologiesLinked Data in Production: Moving Beyond Ontologies
Linked Data in Production: Moving Beyond OntologiesDavid Newbury
 
Basic Building Blocks of Internet of Things.
Basic Building Blocks of Internet of Things.Basic Building Blocks of Internet of Things.
Basic Building Blocks of Internet of Things.YounusS2
 

Último (20)

IaC & GitOps in a Nutshell - a FridayInANuthshell Episode.pdf
IaC & GitOps in a Nutshell - a FridayInANuthshell Episode.pdfIaC & GitOps in a Nutshell - a FridayInANuthshell Episode.pdf
IaC & GitOps in a Nutshell - a FridayInANuthshell Episode.pdf
 
IESVE Software for Florida Code Compliance Using ASHRAE 90.1-2019
IESVE Software for Florida Code Compliance Using ASHRAE 90.1-2019IESVE Software for Florida Code Compliance Using ASHRAE 90.1-2019
IESVE Software for Florida Code Compliance Using ASHRAE 90.1-2019
 
ADOPTING WEB 3 FOR YOUR BUSINESS: A STEP-BY-STEP GUIDE
ADOPTING WEB 3 FOR YOUR BUSINESS: A STEP-BY-STEP GUIDEADOPTING WEB 3 FOR YOUR BUSINESS: A STEP-BY-STEP GUIDE
ADOPTING WEB 3 FOR YOUR BUSINESS: A STEP-BY-STEP GUIDE
 
VoIP Service and Marketing using Odoo and Asterisk PBX
VoIP Service and Marketing using Odoo and Asterisk PBXVoIP Service and Marketing using Odoo and Asterisk PBX
VoIP Service and Marketing using Odoo and Asterisk PBX
 
UiPath Solutions Management Preview - Northern CA Chapter - March 22.pdf
UiPath Solutions Management Preview - Northern CA Chapter - March 22.pdfUiPath Solutions Management Preview - Northern CA Chapter - March 22.pdf
UiPath Solutions Management Preview - Northern CA Chapter - March 22.pdf
 
Meet the new FSP 3000 M-Flex800™
Meet the new FSP 3000 M-Flex800™Meet the new FSP 3000 M-Flex800™
Meet the new FSP 3000 M-Flex800™
 
AI Fame Rush Review – Virtual Influencer Creation In Just Minutes
AI Fame Rush Review – Virtual Influencer Creation In Just MinutesAI Fame Rush Review – Virtual Influencer Creation In Just Minutes
AI Fame Rush Review – Virtual Influencer Creation In Just Minutes
 
OpenShift Commons Paris - Choose Your Own Observability Adventure
OpenShift Commons Paris - Choose Your Own Observability AdventureOpenShift Commons Paris - Choose Your Own Observability Adventure
OpenShift Commons Paris - Choose Your Own Observability Adventure
 
KubeConEU24-Monitoring Kubernetes and Cloud Spend with OpenCost
KubeConEU24-Monitoring Kubernetes and Cloud Spend with OpenCostKubeConEU24-Monitoring Kubernetes and Cloud Spend with OpenCost
KubeConEU24-Monitoring Kubernetes and Cloud Spend with OpenCost
 
Bird eye's view on Camunda open source ecosystem
Bird eye's view on Camunda open source ecosystemBird eye's view on Camunda open source ecosystem
Bird eye's view on Camunda open source ecosystem
 
Computer 10: Lesson 10 - Online Crimes and Hazards
Computer 10: Lesson 10 - Online Crimes and HazardsComputer 10: Lesson 10 - Online Crimes and Hazards
Computer 10: Lesson 10 - Online Crimes and Hazards
 
NIST Cybersecurity Framework (CSF) 2.0 Workshop
NIST Cybersecurity Framework (CSF) 2.0 WorkshopNIST Cybersecurity Framework (CSF) 2.0 Workshop
NIST Cybersecurity Framework (CSF) 2.0 Workshop
 
Secure your environment with UiPath and CyberArk technologies - Session 1
Secure your environment with UiPath and CyberArk technologies - Session 1Secure your environment with UiPath and CyberArk technologies - Session 1
Secure your environment with UiPath and CyberArk technologies - Session 1
 
Comparing Sidecar-less Service Mesh from Cilium and Istio
Comparing Sidecar-less Service Mesh from Cilium and IstioComparing Sidecar-less Service Mesh from Cilium and Istio
Comparing Sidecar-less Service Mesh from Cilium and Istio
 
UWB Technology for Enhanced Indoor and Outdoor Positioning in Physiological M...
UWB Technology for Enhanced Indoor and Outdoor Positioning in Physiological M...UWB Technology for Enhanced Indoor and Outdoor Positioning in Physiological M...
UWB Technology for Enhanced Indoor and Outdoor Positioning in Physiological M...
 
Designing A Time bound resource download URL
Designing A Time bound resource download URLDesigning A Time bound resource download URL
Designing A Time bound resource download URL
 
Cybersecurity Workshop #1.pptx
Cybersecurity Workshop #1.pptxCybersecurity Workshop #1.pptx
Cybersecurity Workshop #1.pptx
 
Videogame localization & technology_ how to enhance the power of translation.pdf
Videogame localization & technology_ how to enhance the power of translation.pdfVideogame localization & technology_ how to enhance the power of translation.pdf
Videogame localization & technology_ how to enhance the power of translation.pdf
 
Linked Data in Production: Moving Beyond Ontologies
Linked Data in Production: Moving Beyond OntologiesLinked Data in Production: Moving Beyond Ontologies
Linked Data in Production: Moving Beyond Ontologies
 
Basic Building Blocks of Internet of Things.
Basic Building Blocks of Internet of Things.Basic Building Blocks of Internet of Things.
Basic Building Blocks of Internet of Things.
 

PR100: SeedNet: Automatic Seed Generation with Deep Reinforcement Learning for Robust Interactive Segmentation

  • 1. PR-100: SeedNet: Automatic Seed Generation with Deep Reinforcement Learning for Robust Interactive Segmentation CVPR2018 Gwangmo Song, Heesoo Myeong, Kyoung Mu Lee 인공지능연구원 이광희
  • 2. 2 논문 선정의 이유.. Chen, Tao, et al. "PhotoSketch: Internet image montage." SIGGRAPH Asia (2009).
  • 3. 3 논문 선정의 이유.. 스케치 배경 오브젝트 사진 선택 이미지 조합 사용될 이미지 생성 팔레트 최종 결과물 텍스트소나무 + 전체 스타일 변환 (팔레트) 브러시 부분 수정 및 조정 (브러시) 이미지 생성 모델 스타일 변환 모델 검색
  • 5. 5 Related Works : Interactive Segmentation Deep extreme cut: From extreme points to object segmentation. CVPR2018 Grabcut: Interactive foreground extraction using iterated graph cuts. Siggraph2003 Methods: Grabcut Random walk Geodesic Deep extremecut . . . Seed types: Rectangle Scribble Contour Extreme point . .
  • 6. 6  Classification, image captioning, video tracking, face hallucination, … Related Works : RL in Computer Vision Active Object Localization with Deep Reinforcement Learning. ICCV2015 Distort-and-Recover: Color enhancement using deep reinforcement learning. CVPR2018
  • 7. 7  An automatic seed generation technique with deep RL to solve the interactive segmentation problem  Robust and consistent object extraction with less human effort  User first select two points- foreground & background  A sequence of artificial user input is automatically generated  Markov Decision Process(MDP) / Deep Q-Network(DQN) Motivation
  • 8. 8  Introduction of a MDP formulation for the interactive segmentation task  The novel reward function design: Intersection Over Union(IOU) score  Why deep RL? • Cannot define globally optimal seed at some stage of interactive segmentation Contributions
  • 9. 9 Automatic Seed Generation System Markov Decision Process(MDP) - State: input image + segmented mask by new seeds - Action: 800 actions, label(fg/bg), position of the seed in the 2D grid(20x20) - Reward: Segmentation method: Random Walk(RW) segmentation Binary Mask - Compute reward signal - An observation of the next iteration Termination: 10 seed points DQN architecture SF: Strong Foreground SB: Strong Background WF: Weak Foreground WB: Weak Background
  • 10. 10 Experiments  MSRA10K saliency dataset  Training: 9000 images, Test: 1000 images, Total: 10000 images  Image size: about 400x300 pixels  Training/testing Input size: 84x84  Segmentation • Training: 84x84(for accelerate), seed point size(3 pixels) • Testing: original size, seed point size(13 pixels)  Termination: 10 times (average number of seeds until saturation: 5.39)
  • 12. 12  Comparison with supervised methods  FCN/iFCN  Fully-connected layer to convolutional layer  80x80 input image Interactive Segmentation Results
  • 16. PR12 1기 멤버분들 모두 1년동안 수고 많으셨습니다.