SlideShare a Scribd company logo
Semantic Segmentation
"Conditional Random Fields Meet Deep Neural Network for Semantic Segmentation"
: https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8254255
 Proposed the spatially-adaptive normalization
-> Effective layer for synthesizing photorealistic images given an input semantic layout.
 Previous methods Problem : Normalization layers tend to "wash away" semantic information.
 Finally, our model allows user control over both semantic and style.
Abstract
𝑚𝑚 ∈ 𝕃𝕃𝐻𝐻×𝑊𝑊
: Semantic Segmentation Mask
where 𝕃𝕃 is a set of integers denoting the semantic labels, 𝐻𝐻 and 𝑊𝑊 are the image height and
width.
Each entry in 𝒎𝒎 denotes the semantic label of a pixel.
We aim to learn a mapping function that can convert an input segmentation mask 𝒎𝒎 to a
photorealistic image.
Semantic Image Synthesis
 임의의 삼각형을 임의의 삼각형으로 매핑시킬 수 있는 변환.
 제약 조건 : 같은 평면에 있어야한다.
 평행 이동, 회전, 크기 변형, 비틀기
Affine transformation
https://darkpgmr.tistory.com/79
(Unconditional) Batch Normalization
Conditional Batch Normalization
Adaptive Instance Normalization(AdalN)
style
content
Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization
: https://arxiv.org/abs/1703.06868
SPatially-Adaptive DEnormalization(SPADE)
https://nvlabs.github.io/SPADE/
activaton
mean
std
SPADE generator
noise
downsampling
With the SPADE, there is no need to feed the segmentation map to the first layer of the generator, since
the learned modulation parameters have encoded enough information about the label layout.
SPADE generator
SPADE
output a mean vector µ
output a variance vector σ
 A short answer is that it can better preserve semantic information against common
normalization layers.
 Specifically, while normalization layers such as the InstanceNorm are essential pieces in
almost all the state-of-the-art conditional image synthesis models, they tend to wash away
semantic information when applied to uniform or flat segmentation masks.
Why does the SPADE work better?
생성자에 모든 동일한 라벨을 가지는 Mask를 넣는 경우
InstanceNorm이 통과되면 모든 값이 0이 된다.
-> pix2pix generator는 semantic mask를 입력으로 넣
어서 InstanceNorm을 통과하게 된다.
-> SPADE generator는 Semantic mask의 정규화 부분
이 없다. 이전 layer의 활성화만 정규화 된다.
Why does the SPADE work better?
 By using a random vector as the input of the
generator, our architecture provides a simple
way for multi-modal synthesis.
 Namely, one can attach an encoder that
processes a real image into a random vector,
which will be then fed to the generator.
 The encoder and generator form a VAE.
 For training, we add a KL-Divergence loss
term.
Multi-modal synthesis
두 확률분포의 다른 정도를 측정
Multi-modal synthesis
 Apply the Spectral Norm to all the layers in the Generator and Discriminator.
 Learning rate : Generator - 0.0001, Discriminator - 0.0004
 ADAM : 𝛽𝛽1 = 0, 𝛽𝛽2 = 0.999
 synchronized BatchNorm - these statistics are collected from all the GPUs.
Experiments - Implementation details
 If the output images are realistic, a well-trained semantic segmentation model should be
able to predict the ground truth label.
 Cascaded Refinement Network(CRN)
 Semiparametric Image Synthesis method(SIMS)
 공평한 평가를 위해
 CRN, pix2pixHD models -> 저자가 구현한 모델을 사용
 SIMS -> 논문에서 결과를 가져옴
Experiments - Performance metrics
Experiments - Qualitative results
Experiments - Human evaluation
We use the Amazon Mechanical Turk (AMT) to compare the perceived visual fidelity of our method against
existing approaches.
Specifically, we give the AMT workers an input segmentation mask and two synthesis outputs from
different methods and ask them to choose the output image that looks more like a corresponding image of
the segmentation mask.
Randomly generate 500 questions for each dataset
Experiments - Effectiveness of the SPADE
 Proposed the spatially-adaptive normalization, which utilizes the input semantic layout while
performing the affine transformation in the normalization layers.
 The proposed normalization leads to the first semantic image synthesis model that can
produce photorealistic outputs for diverse scenes including indoor, outdoor, landscape, and
street scenes.
 We further demonstrate its application for multi-modal synthesis and guided image synthesis.
Conclusion

More Related Content

What's hot

2022-01-17-Rethinking_Bisenet.pptx
2022-01-17-Rethinking_Bisenet.pptx2022-01-17-Rethinking_Bisenet.pptx
2022-01-17-Rethinking_Bisenet.pptx
JAEMINJEONG5
 
2020 12-2-detr
2020 12-2-detr2020 12-2-detr
2020 12-2-detr
JAEMINJEONG5
 
2020 12-1-adam w
2020 12-1-adam w2020 12-1-adam w
2020 12-1-adam w
JAEMINJEONG5
 
2020 12-04-shake shake
2020 12-04-shake shake2020 12-04-shake shake
2020 12-04-shake shake
JAEMINJEONG5
 
2021 03-02-transformer interpretability
2021 03-02-transformer interpretability2021 03-02-transformer interpretability
2021 03-02-transformer interpretability
JAEMINJEONG5
 
MobileNet - PR044
MobileNet - PR044MobileNet - PR044
MobileNet - PR044
Jinwon Lee
 
2020 11 2_automated sleep stage scoring of the sleep heart
2020 11 2_automated sleep stage scoring of the sleep heart2020 11 2_automated sleep stage scoring of the sleep heart
2020 11 2_automated sleep stage scoring of the sleep heart
JAEMINJEONG5
 
2021 01-04-learning filter-basis
2021 01-04-learning filter-basis2021 01-04-learning filter-basis
2021 01-04-learning filter-basis
JAEMINJEONG5
 
PR095: Modularity Matters: Learning Invariant Relational Reasoning Tasks
PR095: Modularity Matters: Learning Invariant Relational Reasoning TasksPR095: Modularity Matters: Learning Invariant Relational Reasoning Tasks
PR095: Modularity Matters: Learning Invariant Relational Reasoning Tasks
Jinwon Lee
 
Deep Learning Fast MRI Using Channel Attention in Magnitude Domain
Deep Learning Fast MRI Using Channel Attention in Magnitude DomainDeep Learning Fast MRI Using Channel Attention in Magnitude Domain
Deep Learning Fast MRI Using Channel Attention in Magnitude Domain
Joonhyung Lee
 
PR-108: MobileNetV2: Inverted Residuals and Linear Bottlenecks
PR-108: MobileNetV2: Inverted Residuals and Linear BottlenecksPR-108: MobileNetV2: Inverted Residuals and Linear Bottlenecks
PR-108: MobileNetV2: Inverted Residuals and Linear Bottlenecks
Jinwon Lee
 
MobileNet V3
MobileNet V3MobileNet V3
MobileNet V3
Wonbeom Jang
 
Introduction to Grad-CAM (short version)
Introduction to Grad-CAM (short version)Introduction to Grad-CAM (short version)
Introduction to Grad-CAM (short version)
Hsing-chuan Hsieh
 
Mobilenetv1 v2 slide
Mobilenetv1 v2 slideMobilenetv1 v2 slide
Mobilenetv1 v2 slide
威智 黃
 
Efficient anomaly detection via matrix sketching
Efficient anomaly detection via matrix sketchingEfficient anomaly detection via matrix sketching
Efficient anomaly detection via matrix sketching
Hsing-chuan Hsieh
 
PR-330: How To Train Your ViT? Data, Augmentation, and Regularization in Visi...
PR-330: How To Train Your ViT? Data, Augmentation, and Regularization in Visi...PR-330: How To Train Your ViT? Data, Augmentation, and Regularization in Visi...
PR-330: How To Train Your ViT? Data, Augmentation, and Regularization in Visi...
Jinwon Lee
 
Rethinking Attention with Performers
Rethinking Attention with PerformersRethinking Attention with Performers
Rethinking Attention with Performers
Joonhyung Lee
 
PR-270: PP-YOLO: An Effective and Efficient Implementation of Object Detector
PR-270: PP-YOLO: An Effective and Efficient Implementation of Object DetectorPR-270: PP-YOLO: An Effective and Efficient Implementation of Object Detector
PR-270: PP-YOLO: An Effective and Efficient Implementation of Object Detector
Jinwon Lee
 
Machine Learning - Convolutional Neural Network
Machine Learning - Convolutional Neural NetworkMachine Learning - Convolutional Neural Network
Machine Learning - Convolutional Neural Network
Richard Kuo
 
Locating texture boundaries using a fast unsupervised approach based on clust...
Locating texture boundaries using a fast unsupervised approach based on clust...Locating texture boundaries using a fast unsupervised approach based on clust...
Locating texture boundaries using a fast unsupervised approach based on clust...
Mehryar (Mike) E., Ph.D.
 

What's hot (20)

2022-01-17-Rethinking_Bisenet.pptx
2022-01-17-Rethinking_Bisenet.pptx2022-01-17-Rethinking_Bisenet.pptx
2022-01-17-Rethinking_Bisenet.pptx
 
2020 12-2-detr
2020 12-2-detr2020 12-2-detr
2020 12-2-detr
 
2020 12-1-adam w
2020 12-1-adam w2020 12-1-adam w
2020 12-1-adam w
 
2020 12-04-shake shake
2020 12-04-shake shake2020 12-04-shake shake
2020 12-04-shake shake
 
2021 03-02-transformer interpretability
2021 03-02-transformer interpretability2021 03-02-transformer interpretability
2021 03-02-transformer interpretability
 
MobileNet - PR044
MobileNet - PR044MobileNet - PR044
MobileNet - PR044
 
2020 11 2_automated sleep stage scoring of the sleep heart
2020 11 2_automated sleep stage scoring of the sleep heart2020 11 2_automated sleep stage scoring of the sleep heart
2020 11 2_automated sleep stage scoring of the sleep heart
 
2021 01-04-learning filter-basis
2021 01-04-learning filter-basis2021 01-04-learning filter-basis
2021 01-04-learning filter-basis
 
PR095: Modularity Matters: Learning Invariant Relational Reasoning Tasks
PR095: Modularity Matters: Learning Invariant Relational Reasoning TasksPR095: Modularity Matters: Learning Invariant Relational Reasoning Tasks
PR095: Modularity Matters: Learning Invariant Relational Reasoning Tasks
 
Deep Learning Fast MRI Using Channel Attention in Magnitude Domain
Deep Learning Fast MRI Using Channel Attention in Magnitude DomainDeep Learning Fast MRI Using Channel Attention in Magnitude Domain
Deep Learning Fast MRI Using Channel Attention in Magnitude Domain
 
PR-108: MobileNetV2: Inverted Residuals and Linear Bottlenecks
PR-108: MobileNetV2: Inverted Residuals and Linear BottlenecksPR-108: MobileNetV2: Inverted Residuals and Linear Bottlenecks
PR-108: MobileNetV2: Inverted Residuals and Linear Bottlenecks
 
MobileNet V3
MobileNet V3MobileNet V3
MobileNet V3
 
Introduction to Grad-CAM (short version)
Introduction to Grad-CAM (short version)Introduction to Grad-CAM (short version)
Introduction to Grad-CAM (short version)
 
Mobilenetv1 v2 slide
Mobilenetv1 v2 slideMobilenetv1 v2 slide
Mobilenetv1 v2 slide
 
Efficient anomaly detection via matrix sketching
Efficient anomaly detection via matrix sketchingEfficient anomaly detection via matrix sketching
Efficient anomaly detection via matrix sketching
 
PR-330: How To Train Your ViT? Data, Augmentation, and Regularization in Visi...
PR-330: How To Train Your ViT? Data, Augmentation, and Regularization in Visi...PR-330: How To Train Your ViT? Data, Augmentation, and Regularization in Visi...
PR-330: How To Train Your ViT? Data, Augmentation, and Regularization in Visi...
 
Rethinking Attention with Performers
Rethinking Attention with PerformersRethinking Attention with Performers
Rethinking Attention with Performers
 
PR-270: PP-YOLO: An Effective and Efficient Implementation of Object Detector
PR-270: PP-YOLO: An Effective and Efficient Implementation of Object DetectorPR-270: PP-YOLO: An Effective and Efficient Implementation of Object Detector
PR-270: PP-YOLO: An Effective and Efficient Implementation of Object Detector
 
Machine Learning - Convolutional Neural Network
Machine Learning - Convolutional Neural NetworkMachine Learning - Convolutional Neural Network
Machine Learning - Convolutional Neural Network
 
Locating texture boundaries using a fast unsupervised approach based on clust...
Locating texture boundaries using a fast unsupervised approach based on clust...Locating texture boundaries using a fast unsupervised approach based on clust...
Locating texture boundaries using a fast unsupervised approach based on clust...
 

Similar to 2021 03-02-spade

Math of Explaining SAM
Math of Explaining SAMMath of Explaining SAM
Math of Explaining SAM
Lian Sabella Castillo
 
Decomposing image generation into layout priction and conditional synthesis
Decomposing image generation into layout priction and conditional synthesisDecomposing image generation into layout priction and conditional synthesis
Decomposing image generation into layout priction and conditional synthesis
Naeem Shehzad
 
A Novel Approach to Image Denoising and Image in Painting
A Novel Approach to Image Denoising and Image in PaintingA Novel Approach to Image Denoising and Image in Painting
A Novel Approach to Image Denoising and Image in Painting
Eswar Publications
 
Kq3518291832
Kq3518291832Kq3518291832
Kq3518291832
IJERA Editor
 
Reading group nfm - 20170312
Reading group  nfm - 20170312Reading group  nfm - 20170312
Reading group nfm - 20170312
Shuai Zhang
 
Introduction to Grad-CAM (complete version)
Introduction to Grad-CAM (complete version)Introduction to Grad-CAM (complete version)
Introduction to Grad-CAM (complete version)
Hsing-chuan Hsieh
 
Structure Unstructured Data
Structure Unstructured DataStructure Unstructured Data
Structure Unstructured Data
Carmine Paolino
 
IRJET - Hand Gesture Recognition to Perform System Operations
IRJET -  	  Hand Gesture Recognition to Perform System OperationsIRJET -  	  Hand Gesture Recognition to Perform System Operations
IRJET - Hand Gesture Recognition to Perform System Operations
IRJET Journal
 
Image Masking.pdf
Image Masking.pdfImage Masking.pdf
Image Masking.pdf
farin11
 
A Smart Camera Processing Pipeline for Image Applications Utilizing Marching ...
A Smart Camera Processing Pipeline for Image Applications Utilizing Marching ...A Smart Camera Processing Pipeline for Image Applications Utilizing Marching ...
A Smart Camera Processing Pipeline for Image Applications Utilizing Marching ...
sipij
 
Automatic Detection of Window Regions in Indoor Point Clouds Using R-CNN
Automatic Detection of Window Regions in Indoor Point Clouds Using R-CNNAutomatic Detection of Window Regions in Indoor Point Clouds Using R-CNN
Automatic Detection of Window Regions in Indoor Point Clouds Using R-CNN
Zihao(Gerald) Zhang
 
Video Stitching using Improved RANSAC and SIFT
Video Stitching using Improved RANSAC and SIFTVideo Stitching using Improved RANSAC and SIFT
Video Stitching using Improved RANSAC and SIFT
IRJET Journal
 
Image attendance system
Image attendance systemImage attendance system
Image attendance system
Mayank Garg
 
Realtime pothole detection system using improved CNN Models
Realtime pothole detection system using improved CNN ModelsRealtime pothole detection system using improved CNN Models
Realtime pothole detection system using improved CNN Models
nithinsai2992
 
IRJET- Automatic Data Collection from Forms using Optical Character Recognition
IRJET- Automatic Data Collection from Forms using Optical Character RecognitionIRJET- Automatic Data Collection from Forms using Optical Character Recognition
IRJET- Automatic Data Collection from Forms using Optical Character Recognition
IRJET Journal
 
Java image processing ieee projects 2012 @ Seabirds ( Chennai, Bangalore, Hyd...
Java image processing ieee projects 2012 @ Seabirds ( Chennai, Bangalore, Hyd...Java image processing ieee projects 2012 @ Seabirds ( Chennai, Bangalore, Hyd...
Java image processing ieee projects 2012 @ Seabirds ( Chennai, Bangalore, Hyd...
SBGC
 
All projects
All projectsAll projects
All projects
Karishma Jain
 
Final year automobile projects in bangalore
Final year automobile projects in bangaloreFinal year automobile projects in bangalore
Final year automobile projects in bangalore
Thirumal Krishnan
 
Final year automobile projects in bangalore
Final year automobile projects in bangaloreFinal year automobile projects in bangalore
Final year automobile projects in bangalore
Thirumal Krishnan
 
DIGEST PODCAST
DIGEST PODCASTDIGEST PODCAST
DIGEST PODCAST
IRJET Journal
 

Similar to 2021 03-02-spade (20)

Math of Explaining SAM
Math of Explaining SAMMath of Explaining SAM
Math of Explaining SAM
 
Decomposing image generation into layout priction and conditional synthesis
Decomposing image generation into layout priction and conditional synthesisDecomposing image generation into layout priction and conditional synthesis
Decomposing image generation into layout priction and conditional synthesis
 
A Novel Approach to Image Denoising and Image in Painting
A Novel Approach to Image Denoising and Image in PaintingA Novel Approach to Image Denoising and Image in Painting
A Novel Approach to Image Denoising and Image in Painting
 
Kq3518291832
Kq3518291832Kq3518291832
Kq3518291832
 
Reading group nfm - 20170312
Reading group  nfm - 20170312Reading group  nfm - 20170312
Reading group nfm - 20170312
 
Introduction to Grad-CAM (complete version)
Introduction to Grad-CAM (complete version)Introduction to Grad-CAM (complete version)
Introduction to Grad-CAM (complete version)
 
Structure Unstructured Data
Structure Unstructured DataStructure Unstructured Data
Structure Unstructured Data
 
IRJET - Hand Gesture Recognition to Perform System Operations
IRJET -  	  Hand Gesture Recognition to Perform System OperationsIRJET -  	  Hand Gesture Recognition to Perform System Operations
IRJET - Hand Gesture Recognition to Perform System Operations
 
Image Masking.pdf
Image Masking.pdfImage Masking.pdf
Image Masking.pdf
 
A Smart Camera Processing Pipeline for Image Applications Utilizing Marching ...
A Smart Camera Processing Pipeline for Image Applications Utilizing Marching ...A Smart Camera Processing Pipeline for Image Applications Utilizing Marching ...
A Smart Camera Processing Pipeline for Image Applications Utilizing Marching ...
 
Automatic Detection of Window Regions in Indoor Point Clouds Using R-CNN
Automatic Detection of Window Regions in Indoor Point Clouds Using R-CNNAutomatic Detection of Window Regions in Indoor Point Clouds Using R-CNN
Automatic Detection of Window Regions in Indoor Point Clouds Using R-CNN
 
Video Stitching using Improved RANSAC and SIFT
Video Stitching using Improved RANSAC and SIFTVideo Stitching using Improved RANSAC and SIFT
Video Stitching using Improved RANSAC and SIFT
 
Image attendance system
Image attendance systemImage attendance system
Image attendance system
 
Realtime pothole detection system using improved CNN Models
Realtime pothole detection system using improved CNN ModelsRealtime pothole detection system using improved CNN Models
Realtime pothole detection system using improved CNN Models
 
IRJET- Automatic Data Collection from Forms using Optical Character Recognition
IRJET- Automatic Data Collection from Forms using Optical Character RecognitionIRJET- Automatic Data Collection from Forms using Optical Character Recognition
IRJET- Automatic Data Collection from Forms using Optical Character Recognition
 
Java image processing ieee projects 2012 @ Seabirds ( Chennai, Bangalore, Hyd...
Java image processing ieee projects 2012 @ Seabirds ( Chennai, Bangalore, Hyd...Java image processing ieee projects 2012 @ Seabirds ( Chennai, Bangalore, Hyd...
Java image processing ieee projects 2012 @ Seabirds ( Chennai, Bangalore, Hyd...
 
All projects
All projectsAll projects
All projects
 
Final year automobile projects in bangalore
Final year automobile projects in bangaloreFinal year automobile projects in bangalore
Final year automobile projects in bangalore
 
Final year automobile projects in bangalore
Final year automobile projects in bangaloreFinal year automobile projects in bangalore
Final year automobile projects in bangalore
 
DIGEST PODCAST
DIGEST PODCASTDIGEST PODCAST
DIGEST PODCAST
 

More from JAEMINJEONG5

Jaemin_230701_Simple_Copy_paste.pptx
Jaemin_230701_Simple_Copy_paste.pptxJaemin_230701_Simple_Copy_paste.pptx
Jaemin_230701_Simple_Copy_paste.pptx
JAEMINJEONG5
 
2021 04-04-google nmt
2021 04-04-google nmt2021 04-04-google nmt
2021 04-04-google nmt
JAEMINJEONG5
 
2021 03-02-distributed representations-of_words_and_phrases
2021 03-02-distributed representations-of_words_and_phrases2021 03-02-distributed representations-of_words_and_phrases
2021 03-02-distributed representations-of_words_and_phrases
JAEMINJEONG5
 
2021 01-02-linformer
2021 01-02-linformer2021 01-02-linformer
2021 01-02-linformer
JAEMINJEONG5
 
2020 11 1_sleep_net
2020 11 1_sleep_net2020 11 1_sleep_net
2020 11 1_sleep_net
JAEMINJEONG5
 
2020 11 3_face_detection
2020 11 3_face_detection2020 11 3_face_detection
2020 11 3_face_detection
JAEMINJEONG5
 
white blood cell classification
white blood cell classificationwhite blood cell classification
white blood cell classification
JAEMINJEONG5
 

More from JAEMINJEONG5 (7)

Jaemin_230701_Simple_Copy_paste.pptx
Jaemin_230701_Simple_Copy_paste.pptxJaemin_230701_Simple_Copy_paste.pptx
Jaemin_230701_Simple_Copy_paste.pptx
 
2021 04-04-google nmt
2021 04-04-google nmt2021 04-04-google nmt
2021 04-04-google nmt
 
2021 03-02-distributed representations-of_words_and_phrases
2021 03-02-distributed representations-of_words_and_phrases2021 03-02-distributed representations-of_words_and_phrases
2021 03-02-distributed representations-of_words_and_phrases
 
2021 01-02-linformer
2021 01-02-linformer2021 01-02-linformer
2021 01-02-linformer
 
2020 11 1_sleep_net
2020 11 1_sleep_net2020 11 1_sleep_net
2020 11 1_sleep_net
 
2020 11 3_face_detection
2020 11 3_face_detection2020 11 3_face_detection
2020 11 3_face_detection
 
white blood cell classification
white blood cell classificationwhite blood cell classification
white blood cell classification
 

Recently uploaded

Certificates - Mahmoud Mohamed Moursi Ahmed
Certificates - Mahmoud Mohamed Moursi AhmedCertificates - Mahmoud Mohamed Moursi Ahmed
Certificates - Mahmoud Mohamed Moursi Ahmed
Mahmoud Morsy
 
Generative AI leverages algorithms to create various forms of content
Generative AI leverages algorithms to create various forms of contentGenerative AI leverages algorithms to create various forms of content
Generative AI leverages algorithms to create various forms of content
Hitesh Mohapatra
 
Material for memory and display system h
Material for memory and display system hMaterial for memory and display system h
Material for memory and display system h
gowrishankartb2005
 
Use PyCharm for remote debugging of WSL on a Windo cf5c162d672e4e58b4dde5d797...
Use PyCharm for remote debugging of WSL on a Windo cf5c162d672e4e58b4dde5d797...Use PyCharm for remote debugging of WSL on a Windo cf5c162d672e4e58b4dde5d797...
Use PyCharm for remote debugging of WSL on a Windo cf5c162d672e4e58b4dde5d797...
shadow0702a
 
Unit-III-ELECTROCHEMICAL STORAGE DEVICES.ppt
Unit-III-ELECTROCHEMICAL STORAGE DEVICES.pptUnit-III-ELECTROCHEMICAL STORAGE DEVICES.ppt
Unit-III-ELECTROCHEMICAL STORAGE DEVICES.ppt
KrishnaveniKrishnara1
 
一比一原版(CalArts毕业证)加利福尼亚艺术学院毕业证如何办理
一比一原版(CalArts毕业证)加利福尼亚艺术学院毕业证如何办理一比一原版(CalArts毕业证)加利福尼亚艺术学院毕业证如何办理
一比一原版(CalArts毕业证)加利福尼亚艺术学院毕业证如何办理
ecqow
 
哪里办理(csu毕业证书)查尔斯特大学毕业证硕士学历原版一模一样
哪里办理(csu毕业证书)查尔斯特大学毕业证硕士学历原版一模一样哪里办理(csu毕业证书)查尔斯特大学毕业证硕士学历原版一模一样
哪里办理(csu毕业证书)查尔斯特大学毕业证硕士学历原版一模一样
insn4465
 
Advanced control scheme of doubly fed induction generator for wind turbine us...
Advanced control scheme of doubly fed induction generator for wind turbine us...Advanced control scheme of doubly fed induction generator for wind turbine us...
Advanced control scheme of doubly fed induction generator for wind turbine us...
IJECEIAES
 
4. Mosca vol I -Fisica-Tipler-5ta-Edicion-Vol-1.pdf
4. Mosca vol I -Fisica-Tipler-5ta-Edicion-Vol-1.pdf4. Mosca vol I -Fisica-Tipler-5ta-Edicion-Vol-1.pdf
4. Mosca vol I -Fisica-Tipler-5ta-Edicion-Vol-1.pdf
Gino153088
 
CEC 352 - SATELLITE COMMUNICATION UNIT 1
CEC 352 - SATELLITE COMMUNICATION UNIT 1CEC 352 - SATELLITE COMMUNICATION UNIT 1
CEC 352 - SATELLITE COMMUNICATION UNIT 1
PKavitha10
 
Software Quality Assurance-se412-v11.ppt
Software Quality Assurance-se412-v11.pptSoftware Quality Assurance-se412-v11.ppt
Software Quality Assurance-se412-v11.ppt
TaghreedAltamimi
 
Comparative analysis between traditional aquaponics and reconstructed aquapon...
Comparative analysis between traditional aquaponics and reconstructed aquapon...Comparative analysis between traditional aquaponics and reconstructed aquapon...
Comparative analysis between traditional aquaponics and reconstructed aquapon...
bijceesjournal
 
原版制作(Humboldt毕业证书)柏林大学毕业证学位证一模一样
原版制作(Humboldt毕业证书)柏林大学毕业证学位证一模一样原版制作(Humboldt毕业证书)柏林大学毕业证学位证一模一样
原版制作(Humboldt毕业证书)柏林大学毕业证学位证一模一样
ydzowc
 
ISPM 15 Heat Treated Wood Stamps and why your shipping must have one
ISPM 15 Heat Treated Wood Stamps and why your shipping must have oneISPM 15 Heat Treated Wood Stamps and why your shipping must have one
ISPM 15 Heat Treated Wood Stamps and why your shipping must have one
Las Vegas Warehouse
 
Introduction to AI Safety (public presentation).pptx
Introduction to AI Safety (public presentation).pptxIntroduction to AI Safety (public presentation).pptx
Introduction to AI Safety (public presentation).pptx
MiscAnnoy1
 
Curve Fitting in Numerical Methods Regression
Curve Fitting in Numerical Methods RegressionCurve Fitting in Numerical Methods Regression
Curve Fitting in Numerical Methods Regression
Nada Hikmah
 
Welding Metallurgy Ferrous Materials.pdf
Welding Metallurgy Ferrous Materials.pdfWelding Metallurgy Ferrous Materials.pdf
Welding Metallurgy Ferrous Materials.pdf
AjmalKhan50578
 
LLM Fine Tuning with QLoRA Cassandra Lunch 4, presented by Anant
LLM Fine Tuning with QLoRA Cassandra Lunch 4, presented by AnantLLM Fine Tuning with QLoRA Cassandra Lunch 4, presented by Anant
LLM Fine Tuning with QLoRA Cassandra Lunch 4, presented by Anant
Anant Corporation
 
AI assisted telemedicine KIOSK for Rural India.pptx
AI assisted telemedicine KIOSK for Rural India.pptxAI assisted telemedicine KIOSK for Rural India.pptx
AI assisted telemedicine KIOSK for Rural India.pptx
architagupta876
 
Null Bangalore | Pentesters Approach to AWS IAM
Null Bangalore | Pentesters Approach to AWS IAMNull Bangalore | Pentesters Approach to AWS IAM
Null Bangalore | Pentesters Approach to AWS IAM
Divyanshu
 

Recently uploaded (20)

Certificates - Mahmoud Mohamed Moursi Ahmed
Certificates - Mahmoud Mohamed Moursi AhmedCertificates - Mahmoud Mohamed Moursi Ahmed
Certificates - Mahmoud Mohamed Moursi Ahmed
 
Generative AI leverages algorithms to create various forms of content
Generative AI leverages algorithms to create various forms of contentGenerative AI leverages algorithms to create various forms of content
Generative AI leverages algorithms to create various forms of content
 
Material for memory and display system h
Material for memory and display system hMaterial for memory and display system h
Material for memory and display system h
 
Use PyCharm for remote debugging of WSL on a Windo cf5c162d672e4e58b4dde5d797...
Use PyCharm for remote debugging of WSL on a Windo cf5c162d672e4e58b4dde5d797...Use PyCharm for remote debugging of WSL on a Windo cf5c162d672e4e58b4dde5d797...
Use PyCharm for remote debugging of WSL on a Windo cf5c162d672e4e58b4dde5d797...
 
Unit-III-ELECTROCHEMICAL STORAGE DEVICES.ppt
Unit-III-ELECTROCHEMICAL STORAGE DEVICES.pptUnit-III-ELECTROCHEMICAL STORAGE DEVICES.ppt
Unit-III-ELECTROCHEMICAL STORAGE DEVICES.ppt
 
一比一原版(CalArts毕业证)加利福尼亚艺术学院毕业证如何办理
一比一原版(CalArts毕业证)加利福尼亚艺术学院毕业证如何办理一比一原版(CalArts毕业证)加利福尼亚艺术学院毕业证如何办理
一比一原版(CalArts毕业证)加利福尼亚艺术学院毕业证如何办理
 
哪里办理(csu毕业证书)查尔斯特大学毕业证硕士学历原版一模一样
哪里办理(csu毕业证书)查尔斯特大学毕业证硕士学历原版一模一样哪里办理(csu毕业证书)查尔斯特大学毕业证硕士学历原版一模一样
哪里办理(csu毕业证书)查尔斯特大学毕业证硕士学历原版一模一样
 
Advanced control scheme of doubly fed induction generator for wind turbine us...
Advanced control scheme of doubly fed induction generator for wind turbine us...Advanced control scheme of doubly fed induction generator for wind turbine us...
Advanced control scheme of doubly fed induction generator for wind turbine us...
 
4. Mosca vol I -Fisica-Tipler-5ta-Edicion-Vol-1.pdf
4. Mosca vol I -Fisica-Tipler-5ta-Edicion-Vol-1.pdf4. Mosca vol I -Fisica-Tipler-5ta-Edicion-Vol-1.pdf
4. Mosca vol I -Fisica-Tipler-5ta-Edicion-Vol-1.pdf
 
CEC 352 - SATELLITE COMMUNICATION UNIT 1
CEC 352 - SATELLITE COMMUNICATION UNIT 1CEC 352 - SATELLITE COMMUNICATION UNIT 1
CEC 352 - SATELLITE COMMUNICATION UNIT 1
 
Software Quality Assurance-se412-v11.ppt
Software Quality Assurance-se412-v11.pptSoftware Quality Assurance-se412-v11.ppt
Software Quality Assurance-se412-v11.ppt
 
Comparative analysis between traditional aquaponics and reconstructed aquapon...
Comparative analysis between traditional aquaponics and reconstructed aquapon...Comparative analysis between traditional aquaponics and reconstructed aquapon...
Comparative analysis between traditional aquaponics and reconstructed aquapon...
 
原版制作(Humboldt毕业证书)柏林大学毕业证学位证一模一样
原版制作(Humboldt毕业证书)柏林大学毕业证学位证一模一样原版制作(Humboldt毕业证书)柏林大学毕业证学位证一模一样
原版制作(Humboldt毕业证书)柏林大学毕业证学位证一模一样
 
ISPM 15 Heat Treated Wood Stamps and why your shipping must have one
ISPM 15 Heat Treated Wood Stamps and why your shipping must have oneISPM 15 Heat Treated Wood Stamps and why your shipping must have one
ISPM 15 Heat Treated Wood Stamps and why your shipping must have one
 
Introduction to AI Safety (public presentation).pptx
Introduction to AI Safety (public presentation).pptxIntroduction to AI Safety (public presentation).pptx
Introduction to AI Safety (public presentation).pptx
 
Curve Fitting in Numerical Methods Regression
Curve Fitting in Numerical Methods RegressionCurve Fitting in Numerical Methods Regression
Curve Fitting in Numerical Methods Regression
 
Welding Metallurgy Ferrous Materials.pdf
Welding Metallurgy Ferrous Materials.pdfWelding Metallurgy Ferrous Materials.pdf
Welding Metallurgy Ferrous Materials.pdf
 
LLM Fine Tuning with QLoRA Cassandra Lunch 4, presented by Anant
LLM Fine Tuning with QLoRA Cassandra Lunch 4, presented by AnantLLM Fine Tuning with QLoRA Cassandra Lunch 4, presented by Anant
LLM Fine Tuning with QLoRA Cassandra Lunch 4, presented by Anant
 
AI assisted telemedicine KIOSK for Rural India.pptx
AI assisted telemedicine KIOSK for Rural India.pptxAI assisted telemedicine KIOSK for Rural India.pptx
AI assisted telemedicine KIOSK for Rural India.pptx
 
Null Bangalore | Pentesters Approach to AWS IAM
Null Bangalore | Pentesters Approach to AWS IAMNull Bangalore | Pentesters Approach to AWS IAM
Null Bangalore | Pentesters Approach to AWS IAM
 

2021 03-02-spade

  • 1.
  • 2. Semantic Segmentation "Conditional Random Fields Meet Deep Neural Network for Semantic Segmentation" : https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8254255
  • 3.  Proposed the spatially-adaptive normalization -> Effective layer for synthesizing photorealistic images given an input semantic layout.  Previous methods Problem : Normalization layers tend to "wash away" semantic information.  Finally, our model allows user control over both semantic and style. Abstract
  • 4. 𝑚𝑚 ∈ 𝕃𝕃𝐻𝐻×𝑊𝑊 : Semantic Segmentation Mask where 𝕃𝕃 is a set of integers denoting the semantic labels, 𝐻𝐻 and 𝑊𝑊 are the image height and width. Each entry in 𝒎𝒎 denotes the semantic label of a pixel. We aim to learn a mapping function that can convert an input segmentation mask 𝒎𝒎 to a photorealistic image. Semantic Image Synthesis
  • 5.  임의의 삼각형을 임의의 삼각형으로 매핑시킬 수 있는 변환.  제약 조건 : 같은 평면에 있어야한다.  평행 이동, 회전, 크기 변형, 비틀기 Affine transformation https://darkpgmr.tistory.com/79
  • 8. Adaptive Instance Normalization(AdalN) style content Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization : https://arxiv.org/abs/1703.06868
  • 10. SPADE generator noise downsampling With the SPADE, there is no need to feed the segmentation map to the first layer of the generator, since the learned modulation parameters have encoded enough information about the label layout.
  • 12. SPADE output a mean vector µ output a variance vector σ
  • 13.  A short answer is that it can better preserve semantic information against common normalization layers.  Specifically, while normalization layers such as the InstanceNorm are essential pieces in almost all the state-of-the-art conditional image synthesis models, they tend to wash away semantic information when applied to uniform or flat segmentation masks. Why does the SPADE work better? 생성자에 모든 동일한 라벨을 가지는 Mask를 넣는 경우 InstanceNorm이 통과되면 모든 값이 0이 된다. -> pix2pix generator는 semantic mask를 입력으로 넣 어서 InstanceNorm을 통과하게 된다. -> SPADE generator는 Semantic mask의 정규화 부분 이 없다. 이전 layer의 활성화만 정규화 된다.
  • 14. Why does the SPADE work better?
  • 15.  By using a random vector as the input of the generator, our architecture provides a simple way for multi-modal synthesis.  Namely, one can attach an encoder that processes a real image into a random vector, which will be then fed to the generator.  The encoder and generator form a VAE.  For training, we add a KL-Divergence loss term. Multi-modal synthesis 두 확률분포의 다른 정도를 측정
  • 17.  Apply the Spectral Norm to all the layers in the Generator and Discriminator.  Learning rate : Generator - 0.0001, Discriminator - 0.0004  ADAM : 𝛽𝛽1 = 0, 𝛽𝛽2 = 0.999  synchronized BatchNorm - these statistics are collected from all the GPUs. Experiments - Implementation details
  • 18.  If the output images are realistic, a well-trained semantic segmentation model should be able to predict the ground truth label.  Cascaded Refinement Network(CRN)  Semiparametric Image Synthesis method(SIMS)  공평한 평가를 위해  CRN, pix2pixHD models -> 저자가 구현한 모델을 사용  SIMS -> 논문에서 결과를 가져옴 Experiments - Performance metrics
  • 20. Experiments - Human evaluation We use the Amazon Mechanical Turk (AMT) to compare the perceived visual fidelity of our method against existing approaches. Specifically, we give the AMT workers an input segmentation mask and two synthesis outputs from different methods and ask them to choose the output image that looks more like a corresponding image of the segmentation mask. Randomly generate 500 questions for each dataset
  • 22.  Proposed the spatially-adaptive normalization, which utilizes the input semantic layout while performing the affine transformation in the normalization layers.  The proposed normalization leads to the first semantic image synthesis model that can produce photorealistic outputs for diverse scenes including indoor, outdoor, landscape, and street scenes.  We further demonstrate its application for multi-modal synthesis and guided image synthesis. Conclusion