SlideShare a Scribd company logo
1 of 29
Download to read offline
Transfer Learning Model
for Image Segmentation
by Integrating U-Net++ and SE Block
GCCE2020 1
2nd Satoshi Yamane
Institute of Science and Engineering, Kanazawa University
1st Yuta Suzuki
Graduate School of Natural Science and Technology, Kanazawa University
Contents
1. Introduction
2. Rerated Works
3. Proposed Method
4. Experiments and Results
5. Conclusion
GCCE2020 2
Contents
1. Introduction
2. Rerated Works
3. Proposed Method
4. Experiments and Results
5. Conclusion
GCCE2020 3
Segmentation
Introduction
The Development of Deep Learning
Classification Object DetecHon
GCCE2020 4
Apply to various image recogni8on tasks
・・・
Example
Classifica0on
Rabbit 98%
GCCE2020 5
• Classification is the task of identifying an object in an image
Predict
Object Detection
GCCE2020 6
• Object detection is a task to identify objects in an image and predict
their rectangular positions
Predict
Rabbit 93%
Segmentation
GCCE2020 7
• Segmentation is the task of identifying objects in an image in pixels
Predict
ImageNet
• Over 14 million images.
• Names of objects in the image (class labels) are added
• Over 20,000 different object names (class labels)
GCCE2020 8
ImageNet is a very large dataset for image classifica8on
ImageNet-trained models
Transfer
Learning
Apply to new tasks
Transfer Learning
GCCE2020 9
Re-training with new data
Transfer Learning is a method of applying a model learned in one task to another task.
• Often effective at CNN
• Pre-training task need to be large
• Useful when you can't prepare a lot of data for training
Fine-Tuning
GCCE2020 10
• The lower layers of CNN are learning general features ➡ Freeze the training
• SegmentaGon doesn't oHen work
Re-training with new data
Freeze the training
Fine tuning is a transfer learning technique commonly used in CNNs for image classifica8on tasks
Contents
1. Introduction
2. Rerated Works
3. Proposed Method
4. Experiments and Results
5. Conclusion
GCCE2020 11
U-Net
GCCE2020 12
U-Net is a representative model for segmentation
• Learn Local Features by Convolution
• Learn location information by skip connections
O. Ronneberger, P. Fischer and T. Brox, U-Net: Convolu@onal Networks for Biomedical Image Segmenta@on, arXiv:1505.04597, 2015.
Encoder
Decoder
Transfer Learning in U-Net
• Using Pre-trained models for the encoder part of U-Net
GCCE2020 13
Vladimir Iglovikov, Alexey Shvets, TernausNet: U-Net with VGG11 Encoder Pre-Trained on ImageNet for Image Segmentation, arXiv:1801.05746, 2018.
Using pre-trained models
in ImageNet
U-Net++
U-Net++ is an improved model of U-Net
GCCE2020 14
Zongwei Zhou, Md Mahfuzur Rahman Siddiquee, Nima Tajbakhsh, Jianming Liang, UNet++: A Nested U-Net Architecture for Medical Image SegmentaGon, arXiv:1807.10165, 2018.
• Decode from each scale's Encoder part and connect them to the Decoder by skip connection
• Reduce feature map gaps between Encoder and Decoder
Problems to be solved (1)
Segmenta8on tasks are expensive to produce data for training
GCCE2020 15
Transfer learning with a trained model in a ImageNet(classification task)
There are differences in learning feature
between classification and segmentation
Problems to be solved (2)
GCCE2020 16
Rabbit 98%
Predict
Predict
classification
segmentation
local features
local features
+
location information
Learning features
Learning features
We need to learn to
bridge this difference
Contents
1. Introduction
2. Rerated Works
3. Proposed Method
4. Experiments and Results
5. Conclusion
GCCE2020 17
Proposed SE-U-Net++
GCCE2020 18
• SE-Block was attached to the encoder part of U-Net++
Efficient learning of local features and locaGon informaGon
SE-Block
GCCE2020 19
Jie Hu, Li Shen,Samuel Albanie, Gang Sun,Enhua Wu, Squeeze-and-Excitation Networks, arXiv:1709.01507v3, 2018.
• Weighting channels in the CNN feature map
Emphasize high-value feature maps and suppress low-value feature maps
Emphasize
location information
Emphasize
local features
Proposed Transfer Learning Algorithm
GCCE2020 20
Cosine similarity
Visualize the learning features difference between
ImageNet and segmentation
Freeze training in areas with similar learning features
Apply fine tuning to models with U-Net structure
Contents
1. Introduction
2. Rerated Works
3. Proposed Method
4. Experiments and Results
5. Conclusion
GCCE2020 21
Experiments data
GCCE2020 22
Kaggle’s 2018 Data Science Bowl
• It is a task to detect the nucleus of a cell
• It has 670 training data.
Predict
https://www.kaggle.com/c/data-science-bowl-2018/data
Experiments model
GCCE2020 23
The models used are U-Net, U-Net++, and SE-U-Net++ with a VGG16 encoder
consisGng of 13 convoluGonal layers
VGG16
Result of SE-U-Net++
GCCE2020 24
unsupervised supervised
U-Net 0.9246 0.9336
U-Net++ 0.9302 0.9443
SE-U-Net++ 0.9363 0.9445
RESULT OF 200 EPOCHs (Mean IoU)
RESULT OF 1000 EPOCHs (Mean IoU)
unsupervised supervised
U-Net 0.9735 0.9756
U-Net++ 0.9754 0.9788
SE-U-Net++ 0.9769 0.9786
SE-U-Net++ is
more efficient
in learning
The learning features difference between
ImageNet and segmentation
GCCE2020 25
In the first half of the encoder, the U-Net structural model is very different from ImageNet in terms of training features.
Learning Features of SE-U-Net++ and Traditional Fine Tuning
GCCE2020 26
Freezing a large difference area in learning features reduce performance.
t
Freeze this area
Result of Proposed Transfer Learning Algorithm
GCCE2020 27
supervised proposed
U-Net 0.9336 0.9341
U-Net++ 0.9443 0.9453
SE-U-Net++ 0.9445 0.9454
RESULT OF 200 EPOCHs (Mean IoU)
supervised proposed
U-Net 0.9756 0.9757
U-Net++ 0.9788 0.9789
SE-U-Net++ 0.9786 0.9787
RESULT OF 1000 EPOCHs (Mean IoU)
Fine tuning
has been
applied to
the U-Net
structural
model
Contents
1. Introduction
2. Rerated Works
3. Proposed Method
4. Experiments and Results
5. Conclusion
GCCE2020 28
Conclusion
• we proposed SE-U-Net++, which efficiently learns both local features
and location information by attaching SE blocks
• we also proposed a transfer learning algorithm that bridges the
difference between the tasks by comparing parameters in the
convolutional layer
• As a result, SE-U-Net++ showed better performance than U-Net++
• As a result, we were able to apply fine tuning to models with a U-Net
structure
GCCE2020 29

More Related Content

What's hot

Image Segmentation Using Deep Learning : A survey
Image Segmentation Using Deep Learning : A surveyImage Segmentation Using Deep Learning : A survey
Image Segmentation Using Deep Learning : A surveyNUPUR YADAV
 
Image processing9 segmentation(pointslinesedges)
Image processing9 segmentation(pointslinesedges)Image processing9 segmentation(pointslinesedges)
Image processing9 segmentation(pointslinesedges)John Williams
 
U-Netpresentation.pptx
U-Netpresentation.pptxU-Netpresentation.pptx
U-Netpresentation.pptxNoorUlHaq47
 
A Beginner's Guide to Monocular Depth Estimation
A Beginner's Guide to Monocular Depth EstimationA Beginner's Guide to Monocular Depth Estimation
A Beginner's Guide to Monocular Depth EstimationRyo Takahashi
 
Neural Radiance Fields & Neural Rendering.pdf
Neural Radiance Fields & Neural Rendering.pdfNeural Radiance Fields & Neural Rendering.pdf
Neural Radiance Fields & Neural Rendering.pdfNavneetPaul2
 
Visualizaing and understanding convolutional networks
Visualizaing and understanding convolutional networksVisualizaing and understanding convolutional networks
Visualizaing and understanding convolutional networksSungminYou
 
Image classification on Imagenet (D1L4 2017 UPC Deep Learning for Computer Vi...
Image classification on Imagenet (D1L4 2017 UPC Deep Learning for Computer Vi...Image classification on Imagenet (D1L4 2017 UPC Deep Learning for Computer Vi...
Image classification on Imagenet (D1L4 2017 UPC Deep Learning for Computer Vi...Universitat Politècnica de Catalunya
 
Image segmentation techniques
Image segmentation techniquesImage segmentation techniques
Image segmentation techniquesgmidhubala
 
Fuzzy image processing- fuzzy C-mean clustering
Fuzzy image processing- fuzzy C-mean clusteringFuzzy image processing- fuzzy C-mean clustering
Fuzzy image processing- fuzzy C-mean clusteringFarah M. Altufaili
 
Do's and Don'ts of using t-SNE.pdf
Do's and Don'ts of using t-SNE.pdfDo's and Don'ts of using t-SNE.pdf
Do's and Don'ts of using t-SNE.pdfFrankClat
 
Image segmentation with deep learning
Image segmentation with deep learningImage segmentation with deep learning
Image segmentation with deep learningAntonio Rueda-Toicen
 
Mask-RCNN for Instance Segmentation
Mask-RCNN for Instance SegmentationMask-RCNN for Instance Segmentation
Mask-RCNN for Instance SegmentationDat Nguyen
 
Lecture 4 Relationship between pixels
Lecture 4 Relationship between pixelsLecture 4 Relationship between pixels
Lecture 4 Relationship between pixelsVARUN KUMAR
 
EDGE DETECTION USING SOBEL OPERATOR.pptx
EDGE DETECTION USING SOBEL OPERATOR.pptxEDGE DETECTION USING SOBEL OPERATOR.pptx
EDGE DETECTION USING SOBEL OPERATOR.pptxkolaruboys
 
Object detection with deep learning
Object detection with deep learningObject detection with deep learning
Object detection with deep learningSushant Shrivastava
 

What's hot (20)

Image Segmentation Using Deep Learning : A survey
Image Segmentation Using Deep Learning : A surveyImage Segmentation Using Deep Learning : A survey
Image Segmentation Using Deep Learning : A survey
 
Image processing9 segmentation(pointslinesedges)
Image processing9 segmentation(pointslinesedges)Image processing9 segmentation(pointslinesedges)
Image processing9 segmentation(pointslinesedges)
 
Unit 1 a notes
Unit 1 a notesUnit 1 a notes
Unit 1 a notes
 
U-Netpresentation.pptx
U-Netpresentation.pptxU-Netpresentation.pptx
U-Netpresentation.pptx
 
A Beginner's Guide to Monocular Depth Estimation
A Beginner's Guide to Monocular Depth EstimationA Beginner's Guide to Monocular Depth Estimation
A Beginner's Guide to Monocular Depth Estimation
 
Neural Radiance Fields & Neural Rendering.pdf
Neural Radiance Fields & Neural Rendering.pdfNeural Radiance Fields & Neural Rendering.pdf
Neural Radiance Fields & Neural Rendering.pdf
 
Visualizaing and understanding convolutional networks
Visualizaing and understanding convolutional networksVisualizaing and understanding convolutional networks
Visualizaing and understanding convolutional networks
 
Image Restoration
Image RestorationImage Restoration
Image Restoration
 
Image classification on Imagenet (D1L4 2017 UPC Deep Learning for Computer Vi...
Image classification on Imagenet (D1L4 2017 UPC Deep Learning for Computer Vi...Image classification on Imagenet (D1L4 2017 UPC Deep Learning for Computer Vi...
Image classification on Imagenet (D1L4 2017 UPC Deep Learning for Computer Vi...
 
Image segmentation techniques
Image segmentation techniquesImage segmentation techniques
Image segmentation techniques
 
Fuzzy image processing- fuzzy C-mean clustering
Fuzzy image processing- fuzzy C-mean clusteringFuzzy image processing- fuzzy C-mean clustering
Fuzzy image processing- fuzzy C-mean clustering
 
Do's and Don'ts of using t-SNE.pdf
Do's and Don'ts of using t-SNE.pdfDo's and Don'ts of using t-SNE.pdf
Do's and Don'ts of using t-SNE.pdf
 
Image restoration
Image restorationImage restoration
Image restoration
 
Deep Learning for Computer Vision: Object Detection (UPC 2016)
Deep Learning for Computer Vision: Object Detection (UPC 2016)Deep Learning for Computer Vision: Object Detection (UPC 2016)
Deep Learning for Computer Vision: Object Detection (UPC 2016)
 
Image segmentation with deep learning
Image segmentation with deep learningImage segmentation with deep learning
Image segmentation with deep learning
 
Mask-RCNN for Instance Segmentation
Mask-RCNN for Instance SegmentationMask-RCNN for Instance Segmentation
Mask-RCNN for Instance Segmentation
 
Lecture 4 Relationship between pixels
Lecture 4 Relationship between pixelsLecture 4 Relationship between pixels
Lecture 4 Relationship between pixels
 
EDGE DETECTION USING SOBEL OPERATOR.pptx
EDGE DETECTION USING SOBEL OPERATOR.pptxEDGE DETECTION USING SOBEL OPERATOR.pptx
EDGE DETECTION USING SOBEL OPERATOR.pptx
 
Image restoration and reconstruction
Image restoration and reconstructionImage restoration and reconstruction
Image restoration and reconstruction
 
Object detection with deep learning
Object detection with deep learningObject detection with deep learning
Object detection with deep learning
 

Similar to SE-U-Net++ Image Segmentation Model with Transfer Learning

USING IMAGE CLASSIFICATION TO INCENTIVIZE RECYCLING
USING IMAGE CLASSIFICATION TO INCENTIVIZE RECYCLINGUSING IMAGE CLASSIFICATION TO INCENTIVIZE RECYCLING
USING IMAGE CLASSIFICATION TO INCENTIVIZE RECYCLINGIRJET Journal
 
Helmet Detection Based on Convolutional Neural Networks
Helmet Detection Based on Convolutional Neural NetworksHelmet Detection Based on Convolutional Neural Networks
Helmet Detection Based on Convolutional Neural NetworksIRJET Journal
 
Human pose detection using machine learning by Grandel
Human pose detection using machine learning by GrandelHuman pose detection using machine learning by Grandel
Human pose detection using machine learning by GrandelGrandelDsouza
 
IRJET - Human Pose Detection using Deep Learning
IRJET - Human Pose Detection using Deep LearningIRJET - Human Pose Detection using Deep Learning
IRJET - Human Pose Detection using Deep LearningIRJET Journal
 
Real time ship detection using YOLOv5
Real time ship detection using YOLOv5Real time ship detection using YOLOv5
Real time ship detection using YOLOv5IRJET Journal
 
IRJET- 3D Object Recognition of Car Image Detection
IRJET-  	  3D Object Recognition of Car Image DetectionIRJET-  	  3D Object Recognition of Car Image Detection
IRJET- 3D Object Recognition of Car Image DetectionIRJET Journal
 
Semantic Segmentation on Satellite Imagery
Semantic Segmentation on Satellite ImagerySemantic Segmentation on Satellite Imagery
Semantic Segmentation on Satellite ImageryRAHUL BHOJWANI
 
IRJET- Displaying and Capturing Profile using Object Detection YOLO and Deepl...
IRJET- Displaying and Capturing Profile using Object Detection YOLO and Deepl...IRJET- Displaying and Capturing Profile using Object Detection YOLO and Deepl...
IRJET- Displaying and Capturing Profile using Object Detection YOLO and Deepl...IRJET Journal
 
IRJET- Glaucoma Detection using Convolutional Neural Network
IRJET- Glaucoma Detection using Convolutional Neural NetworkIRJET- Glaucoma Detection using Convolutional Neural Network
IRJET- Glaucoma Detection using Convolutional Neural NetworkIRJET Journal
 
Traffic Sign Recognition System
Traffic Sign Recognition SystemTraffic Sign Recognition System
Traffic Sign Recognition SystemIRJET Journal
 
IRJET- Rice QA using Deep Learning
IRJET- Rice QA using Deep LearningIRJET- Rice QA using Deep Learning
IRJET- Rice QA using Deep LearningIRJET Journal
 
DSNet Joint Semantic Learning for Object Detection in Inclement Weather Condi...
DSNet Joint Semantic Learning for Object Detection in Inclement Weather Condi...DSNet Joint Semantic Learning for Object Detection in Inclement Weather Condi...
DSNet Joint Semantic Learning for Object Detection in Inclement Weather Condi...IRJET Journal
 
IRJET - Computer Vision-based Image Processing System for Redundant Objec...
IRJET -  	  Computer Vision-based Image Processing System for Redundant Objec...IRJET -  	  Computer Vision-based Image Processing System for Redundant Objec...
IRJET - Computer Vision-based Image Processing System for Redundant Objec...IRJET Journal
 
Helmet Detection Using Yolo V3 Technique
Helmet Detection Using Yolo V3 TechniqueHelmet Detection Using Yolo V3 Technique
Helmet Detection Using Yolo V3 Techniqueijtsrd
 
IRJET - Face Recognition based Attendance System
IRJET -  	  Face Recognition based Attendance SystemIRJET -  	  Face Recognition based Attendance System
IRJET - Face Recognition based Attendance SystemIRJET Journal
 
IRJET- Object Detection and Recognition using Single Shot Multi-Box Detector
IRJET- Object Detection and Recognition using Single Shot Multi-Box DetectorIRJET- Object Detection and Recognition using Single Shot Multi-Box Detector
IRJET- Object Detection and Recognition using Single Shot Multi-Box DetectorIRJET Journal
 
IRJET- Deep Learning Framework Analysis
IRJET- Deep Learning Framework AnalysisIRJET- Deep Learning Framework Analysis
IRJET- Deep Learning Framework AnalysisIRJET Journal
 
Operation wise attention network for tampering localization fusion
Operation wise attention network for tampering localization fusionOperation wise attention network for tampering localization fusion
Operation wise attention network for tampering localization fusionWeverify
 
IRJET- Sketch-Verse: Sketch Image Inversion using DCNN
IRJET- Sketch-Verse: Sketch Image Inversion using DCNNIRJET- Sketch-Verse: Sketch Image Inversion using DCNN
IRJET- Sketch-Verse: Sketch Image Inversion using DCNNIRJET Journal
 
IRJET- Object Detection and Recognition for Blind Assistance
IRJET- Object Detection and Recognition for Blind AssistanceIRJET- Object Detection and Recognition for Blind Assistance
IRJET- Object Detection and Recognition for Blind AssistanceIRJET Journal
 

Similar to SE-U-Net++ Image Segmentation Model with Transfer Learning (20)

USING IMAGE CLASSIFICATION TO INCENTIVIZE RECYCLING
USING IMAGE CLASSIFICATION TO INCENTIVIZE RECYCLINGUSING IMAGE CLASSIFICATION TO INCENTIVIZE RECYCLING
USING IMAGE CLASSIFICATION TO INCENTIVIZE RECYCLING
 
Helmet Detection Based on Convolutional Neural Networks
Helmet Detection Based on Convolutional Neural NetworksHelmet Detection Based on Convolutional Neural Networks
Helmet Detection Based on Convolutional Neural Networks
 
Human pose detection using machine learning by Grandel
Human pose detection using machine learning by GrandelHuman pose detection using machine learning by Grandel
Human pose detection using machine learning by Grandel
 
IRJET - Human Pose Detection using Deep Learning
IRJET - Human Pose Detection using Deep LearningIRJET - Human Pose Detection using Deep Learning
IRJET - Human Pose Detection using Deep Learning
 
Real time ship detection using YOLOv5
Real time ship detection using YOLOv5Real time ship detection using YOLOv5
Real time ship detection using YOLOv5
 
IRJET- 3D Object Recognition of Car Image Detection
IRJET-  	  3D Object Recognition of Car Image DetectionIRJET-  	  3D Object Recognition of Car Image Detection
IRJET- 3D Object Recognition of Car Image Detection
 
Semantic Segmentation on Satellite Imagery
Semantic Segmentation on Satellite ImagerySemantic Segmentation on Satellite Imagery
Semantic Segmentation on Satellite Imagery
 
IRJET- Displaying and Capturing Profile using Object Detection YOLO and Deepl...
IRJET- Displaying and Capturing Profile using Object Detection YOLO and Deepl...IRJET- Displaying and Capturing Profile using Object Detection YOLO and Deepl...
IRJET- Displaying and Capturing Profile using Object Detection YOLO and Deepl...
 
IRJET- Glaucoma Detection using Convolutional Neural Network
IRJET- Glaucoma Detection using Convolutional Neural NetworkIRJET- Glaucoma Detection using Convolutional Neural Network
IRJET- Glaucoma Detection using Convolutional Neural Network
 
Traffic Sign Recognition System
Traffic Sign Recognition SystemTraffic Sign Recognition System
Traffic Sign Recognition System
 
IRJET- Rice QA using Deep Learning
IRJET- Rice QA using Deep LearningIRJET- Rice QA using Deep Learning
IRJET- Rice QA using Deep Learning
 
DSNet Joint Semantic Learning for Object Detection in Inclement Weather Condi...
DSNet Joint Semantic Learning for Object Detection in Inclement Weather Condi...DSNet Joint Semantic Learning for Object Detection in Inclement Weather Condi...
DSNet Joint Semantic Learning for Object Detection in Inclement Weather Condi...
 
IRJET - Computer Vision-based Image Processing System for Redundant Objec...
IRJET -  	  Computer Vision-based Image Processing System for Redundant Objec...IRJET -  	  Computer Vision-based Image Processing System for Redundant Objec...
IRJET - Computer Vision-based Image Processing System for Redundant Objec...
 
Helmet Detection Using Yolo V3 Technique
Helmet Detection Using Yolo V3 TechniqueHelmet Detection Using Yolo V3 Technique
Helmet Detection Using Yolo V3 Technique
 
IRJET - Face Recognition based Attendance System
IRJET -  	  Face Recognition based Attendance SystemIRJET -  	  Face Recognition based Attendance System
IRJET - Face Recognition based Attendance System
 
IRJET- Object Detection and Recognition using Single Shot Multi-Box Detector
IRJET- Object Detection and Recognition using Single Shot Multi-Box DetectorIRJET- Object Detection and Recognition using Single Shot Multi-Box Detector
IRJET- Object Detection and Recognition using Single Shot Multi-Box Detector
 
IRJET- Deep Learning Framework Analysis
IRJET- Deep Learning Framework AnalysisIRJET- Deep Learning Framework Analysis
IRJET- Deep Learning Framework Analysis
 
Operation wise attention network for tampering localization fusion
Operation wise attention network for tampering localization fusionOperation wise attention network for tampering localization fusion
Operation wise attention network for tampering localization fusion
 
IRJET- Sketch-Verse: Sketch Image Inversion using DCNN
IRJET- Sketch-Verse: Sketch Image Inversion using DCNNIRJET- Sketch-Verse: Sketch Image Inversion using DCNN
IRJET- Sketch-Verse: Sketch Image Inversion using DCNN
 
IRJET- Object Detection and Recognition for Blind Assistance
IRJET- Object Detection and Recognition for Blind AssistanceIRJET- Object Detection and Recognition for Blind Assistance
IRJET- Object Detection and Recognition for Blind Assistance
 

Recently uploaded

How To Troubleshoot Collaboration Apps for the Modern Connected Worker
How To Troubleshoot Collaboration Apps for the Modern Connected WorkerHow To Troubleshoot Collaboration Apps for the Modern Connected Worker
How To Troubleshoot Collaboration Apps for the Modern Connected WorkerThousandEyes
 
The Essentials of Digital Experience Monitoring_ A Comprehensive Guide.pdf
The Essentials of Digital Experience Monitoring_ A Comprehensive Guide.pdfThe Essentials of Digital Experience Monitoring_ A Comprehensive Guide.pdf
The Essentials of Digital Experience Monitoring_ A Comprehensive Guide.pdfkalichargn70th171
 
A Secure and Reliable Document Management System is Essential.docx
A Secure and Reliable Document Management System is Essential.docxA Secure and Reliable Document Management System is Essential.docx
A Secure and Reliable Document Management System is Essential.docxComplianceQuest1
 
Steps To Getting Up And Running Quickly With MyTimeClock Employee Scheduling ...
Steps To Getting Up And Running Quickly With MyTimeClock Employee Scheduling ...Steps To Getting Up And Running Quickly With MyTimeClock Employee Scheduling ...
Steps To Getting Up And Running Quickly With MyTimeClock Employee Scheduling ...MyIntelliSource, Inc.
 
Unlocking the Future of AI Agents with Large Language Models
Unlocking the Future of AI Agents with Large Language ModelsUnlocking the Future of AI Agents with Large Language Models
Unlocking the Future of AI Agents with Large Language Modelsaagamshah0812
 
why an Opensea Clone Script might be your perfect match.pdf
why an Opensea Clone Script might be your perfect match.pdfwhy an Opensea Clone Script might be your perfect match.pdf
why an Opensea Clone Script might be your perfect match.pdfjoe51371421
 
Unveiling the Tech Salsa of LAMs with Janus in Real-Time Applications
Unveiling the Tech Salsa of LAMs with Janus in Real-Time ApplicationsUnveiling the Tech Salsa of LAMs with Janus in Real-Time Applications
Unveiling the Tech Salsa of LAMs with Janus in Real-Time ApplicationsAlberto González Trastoy
 
Russian Call Girls in Karol Bagh Aasnvi ➡️ 8264348440 💋📞 Independent Escort S...
Russian Call Girls in Karol Bagh Aasnvi ➡️ 8264348440 💋📞 Independent Escort S...Russian Call Girls in Karol Bagh Aasnvi ➡️ 8264348440 💋📞 Independent Escort S...
Russian Call Girls in Karol Bagh Aasnvi ➡️ 8264348440 💋📞 Independent Escort S...soniya singh
 
CALL ON ➥8923113531 🔝Call Girls Kakori Lucknow best sexual service Online ☂️
CALL ON ➥8923113531 🔝Call Girls Kakori Lucknow best sexual service Online  ☂️CALL ON ➥8923113531 🔝Call Girls Kakori Lucknow best sexual service Online  ☂️
CALL ON ➥8923113531 🔝Call Girls Kakori Lucknow best sexual service Online ☂️anilsa9823
 
(Genuine) Escort Service Lucknow | Starting ₹,5K To @25k with A/C 🧑🏽‍❤️‍🧑🏻 89...
(Genuine) Escort Service Lucknow | Starting ₹,5K To @25k with A/C 🧑🏽‍❤️‍🧑🏻 89...(Genuine) Escort Service Lucknow | Starting ₹,5K To @25k with A/C 🧑🏽‍❤️‍🧑🏻 89...
(Genuine) Escort Service Lucknow | Starting ₹,5K To @25k with A/C 🧑🏽‍❤️‍🧑🏻 89...gurkirankumar98700
 
SyndBuddy AI 2k Review 2024: Revolutionizing Content Syndication with AI
SyndBuddy AI 2k Review 2024: Revolutionizing Content Syndication with AISyndBuddy AI 2k Review 2024: Revolutionizing Content Syndication with AI
SyndBuddy AI 2k Review 2024: Revolutionizing Content Syndication with AIABDERRAOUF MEHENNI
 
Diamond Application Development Crafting Solutions with Precision
Diamond Application Development Crafting Solutions with PrecisionDiamond Application Development Crafting Solutions with Precision
Diamond Application Development Crafting Solutions with PrecisionSolGuruz
 
Hand gesture recognition PROJECT PPT.pptx
Hand gesture recognition PROJECT PPT.pptxHand gesture recognition PROJECT PPT.pptx
Hand gesture recognition PROJECT PPT.pptxbodapatigopi8531
 
TECUNIQUE: Success Stories: IT Service provider
TECUNIQUE: Success Stories: IT Service providerTECUNIQUE: Success Stories: IT Service provider
TECUNIQUE: Success Stories: IT Service providermohitmore19
 
Optimizing AI for immediate response in Smart CCTV
Optimizing AI for immediate response in Smart CCTVOptimizing AI for immediate response in Smart CCTV
Optimizing AI for immediate response in Smart CCTVshikhaohhpro
 
Software Quality Assurance Interview Questions
Software Quality Assurance Interview QuestionsSoftware Quality Assurance Interview Questions
Software Quality Assurance Interview QuestionsArshad QA
 
Short Story: Unveiling the Reasoning Abilities of Large Language Models by Ke...
Short Story: Unveiling the Reasoning Abilities of Large Language Models by Ke...Short Story: Unveiling the Reasoning Abilities of Large Language Models by Ke...
Short Story: Unveiling the Reasoning Abilities of Large Language Models by Ke...kellynguyen01
 
Advancing Engineering with AI through the Next Generation of Strategic Projec...
Advancing Engineering with AI through the Next Generation of Strategic Projec...Advancing Engineering with AI through the Next Generation of Strategic Projec...
Advancing Engineering with AI through the Next Generation of Strategic Projec...OnePlan Solutions
 

Recently uploaded (20)

How To Troubleshoot Collaboration Apps for the Modern Connected Worker
How To Troubleshoot Collaboration Apps for the Modern Connected WorkerHow To Troubleshoot Collaboration Apps for the Modern Connected Worker
How To Troubleshoot Collaboration Apps for the Modern Connected Worker
 
The Essentials of Digital Experience Monitoring_ A Comprehensive Guide.pdf
The Essentials of Digital Experience Monitoring_ A Comprehensive Guide.pdfThe Essentials of Digital Experience Monitoring_ A Comprehensive Guide.pdf
The Essentials of Digital Experience Monitoring_ A Comprehensive Guide.pdf
 
A Secure and Reliable Document Management System is Essential.docx
A Secure and Reliable Document Management System is Essential.docxA Secure and Reliable Document Management System is Essential.docx
A Secure and Reliable Document Management System is Essential.docx
 
Steps To Getting Up And Running Quickly With MyTimeClock Employee Scheduling ...
Steps To Getting Up And Running Quickly With MyTimeClock Employee Scheduling ...Steps To Getting Up And Running Quickly With MyTimeClock Employee Scheduling ...
Steps To Getting Up And Running Quickly With MyTimeClock Employee Scheduling ...
 
Unlocking the Future of AI Agents with Large Language Models
Unlocking the Future of AI Agents with Large Language ModelsUnlocking the Future of AI Agents with Large Language Models
Unlocking the Future of AI Agents with Large Language Models
 
why an Opensea Clone Script might be your perfect match.pdf
why an Opensea Clone Script might be your perfect match.pdfwhy an Opensea Clone Script might be your perfect match.pdf
why an Opensea Clone Script might be your perfect match.pdf
 
Call Girls In Mukherjee Nagar 📱 9999965857 🤩 Delhi 🫦 HOT AND SEXY VVIP 🍎 SE...
Call Girls In Mukherjee Nagar 📱  9999965857  🤩 Delhi 🫦 HOT AND SEXY VVIP 🍎 SE...Call Girls In Mukherjee Nagar 📱  9999965857  🤩 Delhi 🫦 HOT AND SEXY VVIP 🍎 SE...
Call Girls In Mukherjee Nagar 📱 9999965857 🤩 Delhi 🫦 HOT AND SEXY VVIP 🍎 SE...
 
Vip Call Girls Noida ➡️ Delhi ➡️ 9999965857 No Advance 24HRS Live
Vip Call Girls Noida ➡️ Delhi ➡️ 9999965857 No Advance 24HRS LiveVip Call Girls Noida ➡️ Delhi ➡️ 9999965857 No Advance 24HRS Live
Vip Call Girls Noida ➡️ Delhi ➡️ 9999965857 No Advance 24HRS Live
 
Unveiling the Tech Salsa of LAMs with Janus in Real-Time Applications
Unveiling the Tech Salsa of LAMs with Janus in Real-Time ApplicationsUnveiling the Tech Salsa of LAMs with Janus in Real-Time Applications
Unveiling the Tech Salsa of LAMs with Janus in Real-Time Applications
 
Russian Call Girls in Karol Bagh Aasnvi ➡️ 8264348440 💋📞 Independent Escort S...
Russian Call Girls in Karol Bagh Aasnvi ➡️ 8264348440 💋📞 Independent Escort S...Russian Call Girls in Karol Bagh Aasnvi ➡️ 8264348440 💋📞 Independent Escort S...
Russian Call Girls in Karol Bagh Aasnvi ➡️ 8264348440 💋📞 Independent Escort S...
 
CALL ON ➥8923113531 🔝Call Girls Kakori Lucknow best sexual service Online ☂️
CALL ON ➥8923113531 🔝Call Girls Kakori Lucknow best sexual service Online  ☂️CALL ON ➥8923113531 🔝Call Girls Kakori Lucknow best sexual service Online  ☂️
CALL ON ➥8923113531 🔝Call Girls Kakori Lucknow best sexual service Online ☂️
 
(Genuine) Escort Service Lucknow | Starting ₹,5K To @25k with A/C 🧑🏽‍❤️‍🧑🏻 89...
(Genuine) Escort Service Lucknow | Starting ₹,5K To @25k with A/C 🧑🏽‍❤️‍🧑🏻 89...(Genuine) Escort Service Lucknow | Starting ₹,5K To @25k with A/C 🧑🏽‍❤️‍🧑🏻 89...
(Genuine) Escort Service Lucknow | Starting ₹,5K To @25k with A/C 🧑🏽‍❤️‍🧑🏻 89...
 
SyndBuddy AI 2k Review 2024: Revolutionizing Content Syndication with AI
SyndBuddy AI 2k Review 2024: Revolutionizing Content Syndication with AISyndBuddy AI 2k Review 2024: Revolutionizing Content Syndication with AI
SyndBuddy AI 2k Review 2024: Revolutionizing Content Syndication with AI
 
Diamond Application Development Crafting Solutions with Precision
Diamond Application Development Crafting Solutions with PrecisionDiamond Application Development Crafting Solutions with Precision
Diamond Application Development Crafting Solutions with Precision
 
Hand gesture recognition PROJECT PPT.pptx
Hand gesture recognition PROJECT PPT.pptxHand gesture recognition PROJECT PPT.pptx
Hand gesture recognition PROJECT PPT.pptx
 
TECUNIQUE: Success Stories: IT Service provider
TECUNIQUE: Success Stories: IT Service providerTECUNIQUE: Success Stories: IT Service provider
TECUNIQUE: Success Stories: IT Service provider
 
Optimizing AI for immediate response in Smart CCTV
Optimizing AI for immediate response in Smart CCTVOptimizing AI for immediate response in Smart CCTV
Optimizing AI for immediate response in Smart CCTV
 
Software Quality Assurance Interview Questions
Software Quality Assurance Interview QuestionsSoftware Quality Assurance Interview Questions
Software Quality Assurance Interview Questions
 
Short Story: Unveiling the Reasoning Abilities of Large Language Models by Ke...
Short Story: Unveiling the Reasoning Abilities of Large Language Models by Ke...Short Story: Unveiling the Reasoning Abilities of Large Language Models by Ke...
Short Story: Unveiling the Reasoning Abilities of Large Language Models by Ke...
 
Advancing Engineering with AI through the Next Generation of Strategic Projec...
Advancing Engineering with AI through the Next Generation of Strategic Projec...Advancing Engineering with AI through the Next Generation of Strategic Projec...
Advancing Engineering with AI through the Next Generation of Strategic Projec...
 

SE-U-Net++ Image Segmentation Model with Transfer Learning

  • 1. Transfer Learning Model for Image Segmentation by Integrating U-Net++ and SE Block GCCE2020 1 2nd Satoshi Yamane Institute of Science and Engineering, Kanazawa University 1st Yuta Suzuki Graduate School of Natural Science and Technology, Kanazawa University
  • 2. Contents 1. Introduction 2. Rerated Works 3. Proposed Method 4. Experiments and Results 5. Conclusion GCCE2020 2
  • 3. Contents 1. Introduction 2. Rerated Works 3. Proposed Method 4. Experiments and Results 5. Conclusion GCCE2020 3
  • 4. Segmentation Introduction The Development of Deep Learning Classification Object DetecHon GCCE2020 4 Apply to various image recogni8on tasks ・・・ Example
  • 5. Classifica0on Rabbit 98% GCCE2020 5 • Classification is the task of identifying an object in an image Predict
  • 6. Object Detection GCCE2020 6 • Object detection is a task to identify objects in an image and predict their rectangular positions Predict Rabbit 93%
  • 7. Segmentation GCCE2020 7 • Segmentation is the task of identifying objects in an image in pixels Predict
  • 8. ImageNet • Over 14 million images. • Names of objects in the image (class labels) are added • Over 20,000 different object names (class labels) GCCE2020 8 ImageNet is a very large dataset for image classifica8on ImageNet-trained models Transfer Learning Apply to new tasks
  • 9. Transfer Learning GCCE2020 9 Re-training with new data Transfer Learning is a method of applying a model learned in one task to another task. • Often effective at CNN • Pre-training task need to be large • Useful when you can't prepare a lot of data for training
  • 10. Fine-Tuning GCCE2020 10 • The lower layers of CNN are learning general features ➡ Freeze the training • SegmentaGon doesn't oHen work Re-training with new data Freeze the training Fine tuning is a transfer learning technique commonly used in CNNs for image classifica8on tasks
  • 11. Contents 1. Introduction 2. Rerated Works 3. Proposed Method 4. Experiments and Results 5. Conclusion GCCE2020 11
  • 12. U-Net GCCE2020 12 U-Net is a representative model for segmentation • Learn Local Features by Convolution • Learn location information by skip connections O. Ronneberger, P. Fischer and T. Brox, U-Net: Convolu@onal Networks for Biomedical Image Segmenta@on, arXiv:1505.04597, 2015. Encoder Decoder
  • 13. Transfer Learning in U-Net • Using Pre-trained models for the encoder part of U-Net GCCE2020 13 Vladimir Iglovikov, Alexey Shvets, TernausNet: U-Net with VGG11 Encoder Pre-Trained on ImageNet for Image Segmentation, arXiv:1801.05746, 2018. Using pre-trained models in ImageNet
  • 14. U-Net++ U-Net++ is an improved model of U-Net GCCE2020 14 Zongwei Zhou, Md Mahfuzur Rahman Siddiquee, Nima Tajbakhsh, Jianming Liang, UNet++: A Nested U-Net Architecture for Medical Image SegmentaGon, arXiv:1807.10165, 2018. • Decode from each scale's Encoder part and connect them to the Decoder by skip connection • Reduce feature map gaps between Encoder and Decoder
  • 15. Problems to be solved (1) Segmenta8on tasks are expensive to produce data for training GCCE2020 15 Transfer learning with a trained model in a ImageNet(classification task) There are differences in learning feature between classification and segmentation
  • 16. Problems to be solved (2) GCCE2020 16 Rabbit 98% Predict Predict classification segmentation local features local features + location information Learning features Learning features We need to learn to bridge this difference
  • 17. Contents 1. Introduction 2. Rerated Works 3. Proposed Method 4. Experiments and Results 5. Conclusion GCCE2020 17
  • 18. Proposed SE-U-Net++ GCCE2020 18 • SE-Block was attached to the encoder part of U-Net++ Efficient learning of local features and locaGon informaGon
  • 19. SE-Block GCCE2020 19 Jie Hu, Li Shen,Samuel Albanie, Gang Sun,Enhua Wu, Squeeze-and-Excitation Networks, arXiv:1709.01507v3, 2018. • Weighting channels in the CNN feature map Emphasize high-value feature maps and suppress low-value feature maps Emphasize location information Emphasize local features
  • 20. Proposed Transfer Learning Algorithm GCCE2020 20 Cosine similarity Visualize the learning features difference between ImageNet and segmentation Freeze training in areas with similar learning features Apply fine tuning to models with U-Net structure
  • 21. Contents 1. Introduction 2. Rerated Works 3. Proposed Method 4. Experiments and Results 5. Conclusion GCCE2020 21
  • 22. Experiments data GCCE2020 22 Kaggle’s 2018 Data Science Bowl • It is a task to detect the nucleus of a cell • It has 670 training data. Predict https://www.kaggle.com/c/data-science-bowl-2018/data
  • 23. Experiments model GCCE2020 23 The models used are U-Net, U-Net++, and SE-U-Net++ with a VGG16 encoder consisGng of 13 convoluGonal layers VGG16
  • 24. Result of SE-U-Net++ GCCE2020 24 unsupervised supervised U-Net 0.9246 0.9336 U-Net++ 0.9302 0.9443 SE-U-Net++ 0.9363 0.9445 RESULT OF 200 EPOCHs (Mean IoU) RESULT OF 1000 EPOCHs (Mean IoU) unsupervised supervised U-Net 0.9735 0.9756 U-Net++ 0.9754 0.9788 SE-U-Net++ 0.9769 0.9786 SE-U-Net++ is more efficient in learning
  • 25. The learning features difference between ImageNet and segmentation GCCE2020 25 In the first half of the encoder, the U-Net structural model is very different from ImageNet in terms of training features.
  • 26. Learning Features of SE-U-Net++ and Traditional Fine Tuning GCCE2020 26 Freezing a large difference area in learning features reduce performance. t Freeze this area
  • 27. Result of Proposed Transfer Learning Algorithm GCCE2020 27 supervised proposed U-Net 0.9336 0.9341 U-Net++ 0.9443 0.9453 SE-U-Net++ 0.9445 0.9454 RESULT OF 200 EPOCHs (Mean IoU) supervised proposed U-Net 0.9756 0.9757 U-Net++ 0.9788 0.9789 SE-U-Net++ 0.9786 0.9787 RESULT OF 1000 EPOCHs (Mean IoU) Fine tuning has been applied to the U-Net structural model
  • 28. Contents 1. Introduction 2. Rerated Works 3. Proposed Method 4. Experiments and Results 5. Conclusion GCCE2020 28
  • 29. Conclusion • we proposed SE-U-Net++, which efficiently learns both local features and location information by attaching SE blocks • we also proposed a transfer learning algorithm that bridges the difference between the tasks by comparing parameters in the convolutional layer • As a result, SE-U-Net++ showed better performance than U-Net++ • As a result, we were able to apply fine tuning to models with a U-Net structure GCCE2020 29