SlideShare a Scribd company logo
Deep Residual Learning for
Image Recognition
By
Anup Joseph
August 2021
PAPER PRESENTAION
In theory for CNNs deeper == better
In practice however, after some depth the
performance decreases
This was one of the bottlenecks for VGG.
They started to lose generalization
capabilities as they went very deep.
Background
August 2021
PAPER PRESENTATION
PAPER PRESENTATIONS
Skip
Connections
August 2021
Skip connections are the central idea of the
Resnet paper.
The idea is to take the output of one layer and
then plug it to a layer much further in the network
Plain Nueral
Network
PAPER PRESENTATIONS
Skip connections
PAPER PRESENTATIONS
Configurations
August 2021
PAPER PRESENATIONS
A 224x224 random crop of the
image/horizontal flip is taken.
Normalization is done by subtracting the per-
pixel mean of the image from the original
image.
Dataset Augmentation
Learning Rate - 0.1 and then divided by a
factor of 10 on plateau
Iterations = 60 x 10^4, weight decay - 0.0001,
momentum - 0.9
Training Settings
Model Architecture
Resnet Models are made as a combination of "Conv" and "Identity" blocks.
Resnet was tested for 3 tasks and
managed to perform exceptionally
well in all of them
This the result on the ImageNet
classification tasks and are the
best achieved results at that point.
Results
August 2021
PAPER PRESENTATION
Object detection task on the MS-COCO
dataset.
Its better than the best in class models
for the tasks.
Object
Detection
August 2021
PAPER PRESENTATION
Using an ensemble of networks for
classification, ResNet achieve a top-5
localization error of 9.0% on the test
set.
This number significantly outperforms
the ILSVRC 14 results showing a 64%
relative reduction of error. This result
won the 1st place in the ImageNet
localization task in ILSVRC 2015.
Image Localization
August 2021
PAPER PRESENTATION
Quantiphi   resnets

More Related Content

What's hot

Enhanced Deep Residual Networks for Single Image Super-Resolution
Enhanced Deep Residual Networks for Single Image Super-ResolutionEnhanced Deep Residual Networks for Single Image Super-Resolution
Enhanced Deep Residual Networks for Single Image Super-Resolution
NAVER Engineering
 
Deep learning for image super resolution
Deep learning for image super resolutionDeep learning for image super resolution
Deep learning for image super resolution
Prudhvi Raj
 
Deep-Learning Based Stereo Super-Resolution
Deep-Learning Based Stereo Super-ResolutionDeep-Learning Based Stereo Super-Resolution
Deep-Learning Based Stereo Super-Resolution
NAVER Engineering
 
Rethinking Data Augmentation for Image Super-resolution: A Comprehensive Anal...
Rethinking Data Augmentation for Image Super-resolution: A Comprehensive Anal...Rethinking Data Augmentation for Image Super-resolution: A Comprehensive Anal...
Rethinking Data Augmentation for Image Super-resolution: A Comprehensive Anal...
JaeJun Yoo
 
[OSGeo-KR Tech Workshop] Deep Learning for Single Image Super-Resolution
[OSGeo-KR Tech Workshop] Deep Learning for Single Image Super-Resolution[OSGeo-KR Tech Workshop] Deep Learning for Single Image Super-Resolution
[OSGeo-KR Tech Workshop] Deep Learning for Single Image Super-Resolution
Taegyun Jeon
 
Image super resolution
Image super resolutionImage super resolution
Image super resolution
Akshay Hazare
 
Convolutional Neural Network (CNN)
Convolutional Neural Network (CNN)Convolutional Neural Network (CNN)
Convolutional Neural Network (CNN)
Muhammad Haroon
 
Single Image Super Resolution Overview
Single Image Super Resolution OverviewSingle Image Super Resolution Overview
Single Image Super Resolution Overview
LEE HOSEONG
 
Intelligent Image Enhancement and Restoration - From Prior Driven Model to Ad...
Intelligent Image Enhancement and Restoration - From Prior Driven Model to Ad...Intelligent Image Enhancement and Restoration - From Prior Driven Model to Ad...
Intelligent Image Enhancement and Restoration - From Prior Driven Model to Ad...
Wanjin Yu
 
Compressed sensing applications in image processing & communication (1)
Compressed sensing applications in image processing & communication (1)Compressed sensing applications in image processing & communication (1)
Compressed sensing applications in image processing & communication (1)
Mayur Sevak
 
2015 09-21 webinar - 3D SCAN 3D Scanning Storage and Visualization
2015 09-21 webinar - 3D SCAN 3D Scanning Storage and Visualization2015 09-21 webinar - 3D SCAN 3D Scanning Storage and Visualization
2015 09-21 webinar - 3D SCAN 3D Scanning Storage and Visualization
FITMAN FI
 
Locally_adaptive.ppt
Locally_adaptive.pptLocally_adaptive.ppt
Locally_adaptive.pptgrssieee
 
Scaling up Deep Learning Based Super Resolution Algorithms
Scaling up Deep Learning Based Super Resolution AlgorithmsScaling up Deep Learning Based Super Resolution Algorithms
Scaling up Deep Learning Based Super Resolution Algorithms
Xiaoyong Zhu
 
“Applying the Right Deep Learning Model with the Right Data for Your Applicat...
“Applying the Right Deep Learning Model with the Right Data for Your Applicat...“Applying the Right Deep Learning Model with the Right Data for Your Applicat...
“Applying the Right Deep Learning Model with the Right Data for Your Applicat...
Edge AI and Vision Alliance
 
Super resolution-review
Super resolution-reviewSuper resolution-review
Super resolution-review
Woojin Jeong
 
“Modern Machine Vision from Basics to Advanced Deep Learning,” a Presentation...
“Modern Machine Vision from Basics to Advanced Deep Learning,” a Presentation...“Modern Machine Vision from Basics to Advanced Deep Learning,” a Presentation...
“Modern Machine Vision from Basics to Advanced Deep Learning,” a Presentation...
Edge AI and Vision Alliance
 
Gdc19 junsik hwang_v20190314_upload
Gdc19 junsik hwang_v20190314_uploadGdc19 junsik hwang_v20190314_upload
Gdc19 junsik hwang_v20190314_upload
Junsik Whang
 
Intel ILS: Enhancing Photorealism Enhancement
Intel ILS: Enhancing Photorealism EnhancementIntel ILS: Enhancing Photorealism Enhancement
Intel ILS: Enhancing Photorealism Enhancement
Alejandro Franceschi
 
Google Research Siggraph Whitepaper | Total Relighting: Learning to Relight P...
Google Research Siggraph Whitepaper | Total Relighting: Learning to Relight P...Google Research Siggraph Whitepaper | Total Relighting: Learning to Relight P...
Google Research Siggraph Whitepaper | Total Relighting: Learning to Relight P...
Alejandro Franceschi
 

What's hot (20)

Enhanced Deep Residual Networks for Single Image Super-Resolution
Enhanced Deep Residual Networks for Single Image Super-ResolutionEnhanced Deep Residual Networks for Single Image Super-Resolution
Enhanced Deep Residual Networks for Single Image Super-Resolution
 
Deep learning for image super resolution
Deep learning for image super resolutionDeep learning for image super resolution
Deep learning for image super resolution
 
Deep-Learning Based Stereo Super-Resolution
Deep-Learning Based Stereo Super-ResolutionDeep-Learning Based Stereo Super-Resolution
Deep-Learning Based Stereo Super-Resolution
 
Rethinking Data Augmentation for Image Super-resolution: A Comprehensive Anal...
Rethinking Data Augmentation for Image Super-resolution: A Comprehensive Anal...Rethinking Data Augmentation for Image Super-resolution: A Comprehensive Anal...
Rethinking Data Augmentation for Image Super-resolution: A Comprehensive Anal...
 
Super resolution from a single image
Super resolution from a single imageSuper resolution from a single image
Super resolution from a single image
 
[OSGeo-KR Tech Workshop] Deep Learning for Single Image Super-Resolution
[OSGeo-KR Tech Workshop] Deep Learning for Single Image Super-Resolution[OSGeo-KR Tech Workshop] Deep Learning for Single Image Super-Resolution
[OSGeo-KR Tech Workshop] Deep Learning for Single Image Super-Resolution
 
Image super resolution
Image super resolutionImage super resolution
Image super resolution
 
Convolutional Neural Network (CNN)
Convolutional Neural Network (CNN)Convolutional Neural Network (CNN)
Convolutional Neural Network (CNN)
 
Single Image Super Resolution Overview
Single Image Super Resolution OverviewSingle Image Super Resolution Overview
Single Image Super Resolution Overview
 
Intelligent Image Enhancement and Restoration - From Prior Driven Model to Ad...
Intelligent Image Enhancement and Restoration - From Prior Driven Model to Ad...Intelligent Image Enhancement and Restoration - From Prior Driven Model to Ad...
Intelligent Image Enhancement and Restoration - From Prior Driven Model to Ad...
 
Compressed sensing applications in image processing & communication (1)
Compressed sensing applications in image processing & communication (1)Compressed sensing applications in image processing & communication (1)
Compressed sensing applications in image processing & communication (1)
 
2015 09-21 webinar - 3D SCAN 3D Scanning Storage and Visualization
2015 09-21 webinar - 3D SCAN 3D Scanning Storage and Visualization2015 09-21 webinar - 3D SCAN 3D Scanning Storage and Visualization
2015 09-21 webinar - 3D SCAN 3D Scanning Storage and Visualization
 
Locally_adaptive.ppt
Locally_adaptive.pptLocally_adaptive.ppt
Locally_adaptive.ppt
 
Scaling up Deep Learning Based Super Resolution Algorithms
Scaling up Deep Learning Based Super Resolution AlgorithmsScaling up Deep Learning Based Super Resolution Algorithms
Scaling up Deep Learning Based Super Resolution Algorithms
 
“Applying the Right Deep Learning Model with the Right Data for Your Applicat...
“Applying the Right Deep Learning Model with the Right Data for Your Applicat...“Applying the Right Deep Learning Model with the Right Data for Your Applicat...
“Applying the Right Deep Learning Model with the Right Data for Your Applicat...
 
Super resolution-review
Super resolution-reviewSuper resolution-review
Super resolution-review
 
“Modern Machine Vision from Basics to Advanced Deep Learning,” a Presentation...
“Modern Machine Vision from Basics to Advanced Deep Learning,” a Presentation...“Modern Machine Vision from Basics to Advanced Deep Learning,” a Presentation...
“Modern Machine Vision from Basics to Advanced Deep Learning,” a Presentation...
 
Gdc19 junsik hwang_v20190314_upload
Gdc19 junsik hwang_v20190314_uploadGdc19 junsik hwang_v20190314_upload
Gdc19 junsik hwang_v20190314_upload
 
Intel ILS: Enhancing Photorealism Enhancement
Intel ILS: Enhancing Photorealism EnhancementIntel ILS: Enhancing Photorealism Enhancement
Intel ILS: Enhancing Photorealism Enhancement
 
Google Research Siggraph Whitepaper | Total Relighting: Learning to Relight P...
Google Research Siggraph Whitepaper | Total Relighting: Learning to Relight P...Google Research Siggraph Whitepaper | Total Relighting: Learning to Relight P...
Google Research Siggraph Whitepaper | Total Relighting: Learning to Relight P...
 

Similar to Quantiphi resnets

Deep learning for image super resolution
Deep learning for image super resolutionDeep learning for image super resolution
Deep learning for image super resolution
Prudhvi Raj
 
ADVANCED SINGLE IMAGE RESOLUTION UPSURGING USING A GENERATIVE ADVERSARIAL NET...
ADVANCED SINGLE IMAGE RESOLUTION UPSURGING USING A GENERATIVE ADVERSARIAL NET...ADVANCED SINGLE IMAGE RESOLUTION UPSURGING USING A GENERATIVE ADVERSARIAL NET...
ADVANCED SINGLE IMAGE RESOLUTION UPSURGING USING A GENERATIVE ADVERSARIAL NET...
sipij
 
Deep Learning Approach in Characterizing Salt Body on Seismic Images - by Zhe...
Deep Learning Approach in Characterizing Salt Body on Seismic Images - by Zhe...Deep Learning Approach in Characterizing Salt Body on Seismic Images - by Zhe...
Deep Learning Approach in Characterizing Salt Body on Seismic Images - by Zhe...
Yan Xu
 
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
 
Deep learning for image video processing
Deep learning for image video processingDeep learning for image video processing
Deep learning for image video processing
Yu Huang
 
Saptashwa_Mitra_Sitakanta_Mishra_Final_Project_Report
Saptashwa_Mitra_Sitakanta_Mishra_Final_Project_ReportSaptashwa_Mitra_Sitakanta_Mishra_Final_Project_Report
Saptashwa_Mitra_Sitakanta_Mishra_Final_Project_ReportSitakanta Mishra
 
Mnist report
Mnist reportMnist report
Mnist report
RaghunandanJairam
 
Review-image-segmentation-by-deep-learning
Review-image-segmentation-by-deep-learningReview-image-segmentation-by-deep-learning
Review-image-segmentation-by-deep-learning
Trong-An Bui
 
An Approach for Image Deblurring: Based on Sparse Representation and Regulari...
An Approach for Image Deblurring: Based on Sparse Representation and Regulari...An Approach for Image Deblurring: Based on Sparse Representation and Regulari...
An Approach for Image Deblurring: Based on Sparse Representation and Regulari...
IRJET Journal
 
Unsupervised Object Detection
Unsupervised Object DetectionUnsupervised Object Detection
Unsupervised Object Detection
Mahan Fathi
 
Classification of Images Using CNN Model and its Variants
Classification of Images Using CNN Model and its VariantsClassification of Images Using CNN Model and its Variants
Classification of Images Using CNN Model and its Variants
IRJET Journal
 
Face Detection.pptx
Face Detection.pptxFace Detection.pptx
Face Detection.pptx
TorshaSett
 
[PR-325] Pixel-BERT: Aligning Image Pixels with Text by Deep Multi-Modal Tran...
[PR-325] Pixel-BERT: Aligning Image Pixels with Text by Deep Multi-Modal Tran...[PR-325] Pixel-BERT: Aligning Image Pixels with Text by Deep Multi-Modal Tran...
[PR-325] Pixel-BERT: Aligning Image Pixels with Text by Deep Multi-Modal Tran...
Sunghoon Joo
 
Inpainting related works (part 2)
Inpainting related works (part 2)Inpainting related works (part 2)
Inpainting related works (part 2)
Seowoo Han
 
Mnist report ppt
Mnist report pptMnist report ppt
Mnist report ppt
RaghunandanJairam
 
Efficient de cvpr_2020_paper
Efficient de cvpr_2020_paperEfficient de cvpr_2020_paper
Efficient de cvpr_2020_paper
shanullah3
 
2022-01-17-Rethinking_Bisenet.pptx
2022-01-17-Rethinking_Bisenet.pptx2022-01-17-Rethinking_Bisenet.pptx
2022-01-17-Rethinking_Bisenet.pptx
JAEMINJEONG5
 
CNN
CNNCNN
Convolutional Neural Networks - Xavier Giro - UPC TelecomBCN Barcelona 2020
Convolutional Neural Networks - Xavier Giro - UPC TelecomBCN Barcelona 2020Convolutional Neural Networks - Xavier Giro - UPC TelecomBCN Barcelona 2020
Convolutional Neural Networks - Xavier Giro - UPC TelecomBCN Barcelona 2020
Universitat Politècnica de Catalunya
 
A Review On Single Image Depth Prediction with Wavelet Decomposition
A Review On Single Image Depth Prediction with Wavelet DecompositionA Review On Single Image Depth Prediction with Wavelet Decomposition
A Review On Single Image Depth Prediction with Wavelet Decomposition
IRJET Journal
 

Similar to Quantiphi resnets (20)

Deep learning for image super resolution
Deep learning for image super resolutionDeep learning for image super resolution
Deep learning for image super resolution
 
ADVANCED SINGLE IMAGE RESOLUTION UPSURGING USING A GENERATIVE ADVERSARIAL NET...
ADVANCED SINGLE IMAGE RESOLUTION UPSURGING USING A GENERATIVE ADVERSARIAL NET...ADVANCED SINGLE IMAGE RESOLUTION UPSURGING USING A GENERATIVE ADVERSARIAL NET...
ADVANCED SINGLE IMAGE RESOLUTION UPSURGING USING A GENERATIVE ADVERSARIAL NET...
 
Deep Learning Approach in Characterizing Salt Body on Seismic Images - by Zhe...
Deep Learning Approach in Characterizing Salt Body on Seismic Images - by Zhe...Deep Learning Approach in Characterizing Salt Body on Seismic Images - by Zhe...
Deep Learning Approach in Characterizing Salt Body on Seismic Images - by Zhe...
 
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
 
Deep learning for image video processing
Deep learning for image video processingDeep learning for image video processing
Deep learning for image video processing
 
Saptashwa_Mitra_Sitakanta_Mishra_Final_Project_Report
Saptashwa_Mitra_Sitakanta_Mishra_Final_Project_ReportSaptashwa_Mitra_Sitakanta_Mishra_Final_Project_Report
Saptashwa_Mitra_Sitakanta_Mishra_Final_Project_Report
 
Mnist report
Mnist reportMnist report
Mnist report
 
Review-image-segmentation-by-deep-learning
Review-image-segmentation-by-deep-learningReview-image-segmentation-by-deep-learning
Review-image-segmentation-by-deep-learning
 
An Approach for Image Deblurring: Based on Sparse Representation and Regulari...
An Approach for Image Deblurring: Based on Sparse Representation and Regulari...An Approach for Image Deblurring: Based on Sparse Representation and Regulari...
An Approach for Image Deblurring: Based on Sparse Representation and Regulari...
 
Unsupervised Object Detection
Unsupervised Object DetectionUnsupervised Object Detection
Unsupervised Object Detection
 
Classification of Images Using CNN Model and its Variants
Classification of Images Using CNN Model and its VariantsClassification of Images Using CNN Model and its Variants
Classification of Images Using CNN Model and its Variants
 
Face Detection.pptx
Face Detection.pptxFace Detection.pptx
Face Detection.pptx
 
[PR-325] Pixel-BERT: Aligning Image Pixels with Text by Deep Multi-Modal Tran...
[PR-325] Pixel-BERT: Aligning Image Pixels with Text by Deep Multi-Modal Tran...[PR-325] Pixel-BERT: Aligning Image Pixels with Text by Deep Multi-Modal Tran...
[PR-325] Pixel-BERT: Aligning Image Pixels with Text by Deep Multi-Modal Tran...
 
Inpainting related works (part 2)
Inpainting related works (part 2)Inpainting related works (part 2)
Inpainting related works (part 2)
 
Mnist report ppt
Mnist report pptMnist report ppt
Mnist report ppt
 
Efficient de cvpr_2020_paper
Efficient de cvpr_2020_paperEfficient de cvpr_2020_paper
Efficient de cvpr_2020_paper
 
2022-01-17-Rethinking_Bisenet.pptx
2022-01-17-Rethinking_Bisenet.pptx2022-01-17-Rethinking_Bisenet.pptx
2022-01-17-Rethinking_Bisenet.pptx
 
CNN
CNNCNN
CNN
 
Convolutional Neural Networks - Xavier Giro - UPC TelecomBCN Barcelona 2020
Convolutional Neural Networks - Xavier Giro - UPC TelecomBCN Barcelona 2020Convolutional Neural Networks - Xavier Giro - UPC TelecomBCN Barcelona 2020
Convolutional Neural Networks - Xavier Giro - UPC TelecomBCN Barcelona 2020
 
A Review On Single Image Depth Prediction with Wavelet Decomposition
A Review On Single Image Depth Prediction with Wavelet DecompositionA Review On Single Image Depth Prediction with Wavelet Decomposition
A Review On Single Image Depth Prediction with Wavelet Decomposition
 

Recently uploaded

Design and Analysis of Algorithms-DP,Backtracking,Graphs,B&B
Design and Analysis of Algorithms-DP,Backtracking,Graphs,B&BDesign and Analysis of Algorithms-DP,Backtracking,Graphs,B&B
Design and Analysis of Algorithms-DP,Backtracking,Graphs,B&B
Sreedhar Chowdam
 
space technology lecture notes on satellite
space technology lecture notes on satellitespace technology lecture notes on satellite
space technology lecture notes on satellite
ongomchris
 
一比一原版(SFU毕业证)西蒙菲莎大学毕业证成绩单如何办理
一比一原版(SFU毕业证)西蒙菲莎大学毕业证成绩单如何办理一比一原版(SFU毕业证)西蒙菲莎大学毕业证成绩单如何办理
一比一原版(SFU毕业证)西蒙菲莎大学毕业证成绩单如何办理
bakpo1
 
DESIGN A COTTON SEED SEPARATION MACHINE.docx
DESIGN A COTTON SEED SEPARATION MACHINE.docxDESIGN A COTTON SEED SEPARATION MACHINE.docx
DESIGN A COTTON SEED SEPARATION MACHINE.docx
FluxPrime1
 
English lab ppt no titlespecENG PPTt.pdf
English lab ppt no titlespecENG PPTt.pdfEnglish lab ppt no titlespecENG PPTt.pdf
English lab ppt no titlespecENG PPTt.pdf
BrazilAccount1
 
ML for identifying fraud using open blockchain data.pptx
ML for identifying fraud using open blockchain data.pptxML for identifying fraud using open blockchain data.pptx
ML for identifying fraud using open blockchain data.pptx
Vijay Dialani, PhD
 
Cosmetic shop management system project report.pdf
Cosmetic shop management system project report.pdfCosmetic shop management system project report.pdf
Cosmetic shop management system project report.pdf
Kamal Acharya
 
Hybrid optimization of pumped hydro system and solar- Engr. Abdul-Azeez.pdf
Hybrid optimization of pumped hydro system and solar- Engr. Abdul-Azeez.pdfHybrid optimization of pumped hydro system and solar- Engr. Abdul-Azeez.pdf
Hybrid optimization of pumped hydro system and solar- Engr. Abdul-Azeez.pdf
fxintegritypublishin
 
Water Industry Process Automation and Control Monthly - May 2024.pdf
Water Industry Process Automation and Control Monthly - May 2024.pdfWater Industry Process Automation and Control Monthly - May 2024.pdf
Water Industry Process Automation and Control Monthly - May 2024.pdf
Water Industry Process Automation & Control
 
NUMERICAL SIMULATIONS OF HEAT AND MASS TRANSFER IN CONDENSING HEAT EXCHANGERS...
NUMERICAL SIMULATIONS OF HEAT AND MASS TRANSFER IN CONDENSING HEAT EXCHANGERS...NUMERICAL SIMULATIONS OF HEAT AND MASS TRANSFER IN CONDENSING HEAT EXCHANGERS...
NUMERICAL SIMULATIONS OF HEAT AND MASS TRANSFER IN CONDENSING HEAT EXCHANGERS...
ssuser7dcef0
 
Forklift Classes Overview by Intella Parts
Forklift Classes Overview by Intella PartsForklift Classes Overview by Intella Parts
Forklift Classes Overview by Intella Parts
Intella Parts
 
Standard Reomte Control Interface - Neometrix
Standard Reomte Control Interface - NeometrixStandard Reomte Control Interface - Neometrix
Standard Reomte Control Interface - Neometrix
Neometrix_Engineering_Pvt_Ltd
 
Recycled Concrete Aggregate in Construction Part III
Recycled Concrete Aggregate in Construction Part IIIRecycled Concrete Aggregate in Construction Part III
Recycled Concrete Aggregate in Construction Part III
Aditya Rajan Patra
 
Hierarchical Digital Twin of a Naval Power System
Hierarchical Digital Twin of a Naval Power SystemHierarchical Digital Twin of a Naval Power System
Hierarchical Digital Twin of a Naval Power System
Kerry Sado
 
block diagram and signal flow graph representation
block diagram and signal flow graph representationblock diagram and signal flow graph representation
block diagram and signal flow graph representation
Divya Somashekar
 
Top 10 Oil and Gas Projects in Saudi Arabia 2024.pdf
Top 10 Oil and Gas Projects in Saudi Arabia 2024.pdfTop 10 Oil and Gas Projects in Saudi Arabia 2024.pdf
Top 10 Oil and Gas Projects in Saudi Arabia 2024.pdf
Teleport Manpower Consultant
 
AKS UNIVERSITY Satna Final Year Project By OM Hardaha.pdf
AKS UNIVERSITY Satna Final Year Project By OM Hardaha.pdfAKS UNIVERSITY Satna Final Year Project By OM Hardaha.pdf
AKS UNIVERSITY Satna Final Year Project By OM Hardaha.pdf
SamSarthak3
 
Unbalanced Three Phase Systems and circuits.pptx
Unbalanced Three Phase Systems and circuits.pptxUnbalanced Three Phase Systems and circuits.pptx
Unbalanced Three Phase Systems and circuits.pptx
ChristineTorrepenida1
 
AP LAB PPT.pdf ap lab ppt no title specific
AP LAB PPT.pdf ap lab ppt no title specificAP LAB PPT.pdf ap lab ppt no title specific
AP LAB PPT.pdf ap lab ppt no title specific
BrazilAccount1
 
MCQ Soil mechanics questions (Soil shear strength).pdf
MCQ Soil mechanics questions (Soil shear strength).pdfMCQ Soil mechanics questions (Soil shear strength).pdf
MCQ Soil mechanics questions (Soil shear strength).pdf
Osamah Alsalih
 

Recently uploaded (20)

Design and Analysis of Algorithms-DP,Backtracking,Graphs,B&B
Design and Analysis of Algorithms-DP,Backtracking,Graphs,B&BDesign and Analysis of Algorithms-DP,Backtracking,Graphs,B&B
Design and Analysis of Algorithms-DP,Backtracking,Graphs,B&B
 
space technology lecture notes on satellite
space technology lecture notes on satellitespace technology lecture notes on satellite
space technology lecture notes on satellite
 
一比一原版(SFU毕业证)西蒙菲莎大学毕业证成绩单如何办理
一比一原版(SFU毕业证)西蒙菲莎大学毕业证成绩单如何办理一比一原版(SFU毕业证)西蒙菲莎大学毕业证成绩单如何办理
一比一原版(SFU毕业证)西蒙菲莎大学毕业证成绩单如何办理
 
DESIGN A COTTON SEED SEPARATION MACHINE.docx
DESIGN A COTTON SEED SEPARATION MACHINE.docxDESIGN A COTTON SEED SEPARATION MACHINE.docx
DESIGN A COTTON SEED SEPARATION MACHINE.docx
 
English lab ppt no titlespecENG PPTt.pdf
English lab ppt no titlespecENG PPTt.pdfEnglish lab ppt no titlespecENG PPTt.pdf
English lab ppt no titlespecENG PPTt.pdf
 
ML for identifying fraud using open blockchain data.pptx
ML for identifying fraud using open blockchain data.pptxML for identifying fraud using open blockchain data.pptx
ML for identifying fraud using open blockchain data.pptx
 
Cosmetic shop management system project report.pdf
Cosmetic shop management system project report.pdfCosmetic shop management system project report.pdf
Cosmetic shop management system project report.pdf
 
Hybrid optimization of pumped hydro system and solar- Engr. Abdul-Azeez.pdf
Hybrid optimization of pumped hydro system and solar- Engr. Abdul-Azeez.pdfHybrid optimization of pumped hydro system and solar- Engr. Abdul-Azeez.pdf
Hybrid optimization of pumped hydro system and solar- Engr. Abdul-Azeez.pdf
 
Water Industry Process Automation and Control Monthly - May 2024.pdf
Water Industry Process Automation and Control Monthly - May 2024.pdfWater Industry Process Automation and Control Monthly - May 2024.pdf
Water Industry Process Automation and Control Monthly - May 2024.pdf
 
NUMERICAL SIMULATIONS OF HEAT AND MASS TRANSFER IN CONDENSING HEAT EXCHANGERS...
NUMERICAL SIMULATIONS OF HEAT AND MASS TRANSFER IN CONDENSING HEAT EXCHANGERS...NUMERICAL SIMULATIONS OF HEAT AND MASS TRANSFER IN CONDENSING HEAT EXCHANGERS...
NUMERICAL SIMULATIONS OF HEAT AND MASS TRANSFER IN CONDENSING HEAT EXCHANGERS...
 
Forklift Classes Overview by Intella Parts
Forklift Classes Overview by Intella PartsForklift Classes Overview by Intella Parts
Forklift Classes Overview by Intella Parts
 
Standard Reomte Control Interface - Neometrix
Standard Reomte Control Interface - NeometrixStandard Reomte Control Interface - Neometrix
Standard Reomte Control Interface - Neometrix
 
Recycled Concrete Aggregate in Construction Part III
Recycled Concrete Aggregate in Construction Part IIIRecycled Concrete Aggregate in Construction Part III
Recycled Concrete Aggregate in Construction Part III
 
Hierarchical Digital Twin of a Naval Power System
Hierarchical Digital Twin of a Naval Power SystemHierarchical Digital Twin of a Naval Power System
Hierarchical Digital Twin of a Naval Power System
 
block diagram and signal flow graph representation
block diagram and signal flow graph representationblock diagram and signal flow graph representation
block diagram and signal flow graph representation
 
Top 10 Oil and Gas Projects in Saudi Arabia 2024.pdf
Top 10 Oil and Gas Projects in Saudi Arabia 2024.pdfTop 10 Oil and Gas Projects in Saudi Arabia 2024.pdf
Top 10 Oil and Gas Projects in Saudi Arabia 2024.pdf
 
AKS UNIVERSITY Satna Final Year Project By OM Hardaha.pdf
AKS UNIVERSITY Satna Final Year Project By OM Hardaha.pdfAKS UNIVERSITY Satna Final Year Project By OM Hardaha.pdf
AKS UNIVERSITY Satna Final Year Project By OM Hardaha.pdf
 
Unbalanced Three Phase Systems and circuits.pptx
Unbalanced Three Phase Systems and circuits.pptxUnbalanced Three Phase Systems and circuits.pptx
Unbalanced Three Phase Systems and circuits.pptx
 
AP LAB PPT.pdf ap lab ppt no title specific
AP LAB PPT.pdf ap lab ppt no title specificAP LAB PPT.pdf ap lab ppt no title specific
AP LAB PPT.pdf ap lab ppt no title specific
 
MCQ Soil mechanics questions (Soil shear strength).pdf
MCQ Soil mechanics questions (Soil shear strength).pdfMCQ Soil mechanics questions (Soil shear strength).pdf
MCQ Soil mechanics questions (Soil shear strength).pdf
 

Quantiphi resnets

  • 1. Deep Residual Learning for Image Recognition By Anup Joseph August 2021 PAPER PRESENTAION
  • 2. In theory for CNNs deeper == better In practice however, after some depth the performance decreases This was one of the bottlenecks for VGG. They started to lose generalization capabilities as they went very deep. Background August 2021 PAPER PRESENTATION
  • 3. PAPER PRESENTATIONS Skip Connections August 2021 Skip connections are the central idea of the Resnet paper. The idea is to take the output of one layer and then plug it to a layer much further in the network
  • 6. Configurations August 2021 PAPER PRESENATIONS A 224x224 random crop of the image/horizontal flip is taken. Normalization is done by subtracting the per- pixel mean of the image from the original image. Dataset Augmentation Learning Rate - 0.1 and then divided by a factor of 10 on plateau Iterations = 60 x 10^4, weight decay - 0.0001, momentum - 0.9 Training Settings
  • 7. Model Architecture Resnet Models are made as a combination of "Conv" and "Identity" blocks.
  • 8.
  • 9. Resnet was tested for 3 tasks and managed to perform exceptionally well in all of them This the result on the ImageNet classification tasks and are the best achieved results at that point. Results August 2021 PAPER PRESENTATION
  • 10. Object detection task on the MS-COCO dataset. Its better than the best in class models for the tasks. Object Detection August 2021 PAPER PRESENTATION
  • 11. Using an ensemble of networks for classification, ResNet achieve a top-5 localization error of 9.0% on the test set. This number significantly outperforms the ILSVRC 14 results showing a 64% relative reduction of error. This result won the 1st place in the ImageNet localization task in ILSVRC 2015. Image Localization August 2021 PAPER PRESENTATION