SlideShare a Scribd company logo
1 of 19
Download to read offline
Amirkabir University of Technology
Department of Computer Engineering
and Information Technology
Image Classification with
Deep Convolutional
Neural Networks
Sepehr Rasouli
Introduction > Methods > Results > Conclusion2
Outline
• Introduction to Image Classification
& Deep Networks
• Proposed Method
• Main Idea
• Data Set
• Architecture
• Techniques
• Comparison & Results
• Conclusion
Introduction > Methods > Results > Conclusion3
Image Classification
Introduction > Methods > Results > Conclusion4
Why Deep Learning?
•“Shallow” vs. “deep” architectures
Learn a feature hierarchy all the way from pixels to classifier
Hand	Designed	
Feature	
Extraction
Trainable	
Classifier
Layer	1 Layer	N
Simpler	
classifier
Introduction > Methods > Results > Conclusion5
Our Method
• Deep Convolutional Neural Network
• 5 convolutional and 3 fully connected layers
• 650,000 neurons, 60 million parameters
• Techniques used for boosting up performance
• ReLU nonlinearity
• Training on Multiple GPUs
• Overlapping max pooling
• Data Augmentation
• Dropout
Introduction > Methods > Results > Conclusion6
Overall Architecture
• Trained with stochastic gradient descent on two NVIDIA GPUs for about a
week (5~6 days)
• 650,000 neurons, 60 million parameters, 630 million connections
• The last layer contains 1,000 neurons which produces a distribution over the
1,000 class labels.
Introduction > Methods > Results > Conclusion7
Dataset
• ImageNet
§ Over 15 million high-quality labeled images
§ About 22,000 categories
§ Collected from the web, labeled by humans on Amazon's Mechanical
Turk
§ Variable-resolution images
• ILSVRC Competition
§ ImageNet Large-Scale Pascal Visual Object Challenge
§ Annual competition of image classification at large scale
§ Subset of ImageNet
§ 1,000 categories with about 1,000 images each
§ 1.2M images in 1K categories
§ Classification: make 5 guesses about the image label
Introduction > Methods > Results > Conclusion8
Rectified Linear Units
𝑥 = 𝑤$ 𝑓 𝑍$ + 𝑤( 𝑓 𝑍(
+𝑤) 𝑓 𝑍)
x	is	called	the	total	input	
to	the	neuron,	and	f(x)	
is	its	output
Very	bad	
(slow	to	train	)
Very	good	
(quick	to	train)
f(x)	=	max(0,x)f(x)	=	tanh(x)
Introduction > Methods > Results > Conclusion9
Rectified Linear Units
• Biological plausibility: One-sided, compared
to the antisymmetry of tanh.
• Sparse activation: For example, in a randomly
initialized network, only about 50% of hidden
units are activated (having a non-zero output).
• Efficient gradient propagation: No vanishing
gradient problem or exploding effect.
• Efficient computation: Only comparison,
addition and multiplication
Introduction > Methods > Results > Conclusion10
Training on Multiple GPUs
• Spread across two GPUs
• GTX 580 GPU with 3GB memory
• Particularly well-suited to cross-GPU
parallelization
• Very efficient implementation of CNN on
GPUs
Model Top-1 Top-5
Sparse	coding [3] 47.1% 28.2%
SIFT	+	FVs	[4] 45.7% 25.7%
CNN 37.5 17.0%
Introduction > Methods > Results > Conclusion11
Results & Comparison
•ILSVRC-2010	test	set
ILSVRC-2010	winner
Previous	best
published	result
Our	Method
Comparison	of	results	on	ILSRVCs	2010	
test	set.	In	italics	best	results	achieved	
by	others.
Introduction > Methods > Results > Conclusion12
Conclusion
• Large, deep convolutional neural networks for large
scale image classification was proposed
• 5 convolutional layers, 3 fully-connected layers
• 650,000 neurons, 60 million parameters
• Several techniques for boosting up performance
• The proposed method won the ILSVRC-2012
• Achieved a winning top-5 error rate of 15.3%,
compared to 26.2% achieved by the second-best entry
Introduction > Methods > Results > Conclusion13
Conclusion
Introduction > Methods > Results > Conclusion14
References
[1]	 http://cs.nyu.edu/~fergus/tutorials/
deep_learning_cvpr12/fergus_dl_tutorial_final.pptx
[2]	 reference	:	http://web.engr.illinois.edu/
~slazebni/spring14/lec24_cnn.pdf
[3]	 A.	Berg,	J.	Deng,	and	L.	Fei-Fei.	Large	scale	
visual	recognition	challenge	2010.	
www.imagenet.org/challenges.	2010.	[4]	
S.	Tara,	Brian	Kingsbury,	A.-r.	Mohamed	and
B.	Ramabhadran,	"Learning	Filter	Banks	within	a	Deep
[4]	 J.Sánchezand F.Perronnin.High-dimensional	
signature	compression	for	large-scale	image	classification.
In	Computer	Vision	and	Pattern	Recognition(CVPR),
2011IEEEConferenceon,pages1665–1672.IEEE,	2011.
Introduction > Methods > Results > Conclusion15
Thank you for your attention
Any Questions?
Introduction > Methods > Results > Conclusion16
Results 2012
• ILSVRC-2012	results
Proposed	method
Top-5	error	rate	:	16.422%
Runner-up
Top-5	error	rate	:	26.172%
Introduction > Methods > Results > Conclusion17
Convolutional NNs
Introduction > Methods > Results > Conclusion18
Pooling
• Spatial Pooling
• Non-overlapping / overlapping regions
• Sum or max
Max
Sum
Introduction > Methods > Results > Conclusion19
Dropout
• Independently	set	each	hidden	unit	activity	to			zero	with	0.5	
probability
• Used	in	the	two	globally-connected	hidden	layers	at	the	net's	
output

More Related Content

What's hot

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 DomainJoonhyung Lee
 
YOLOv4: optimal speed and accuracy of object detection review
YOLOv4: optimal speed and accuracy of object detection reviewYOLOv4: optimal speed and accuracy of object detection review
YOLOv4: optimal speed and accuracy of object detection reviewLEE HOSEONG
 
Matineh Shaker, Artificial Intelligence Scientist, Bonsai at MLconf SF 2017
Matineh Shaker, Artificial Intelligence Scientist, Bonsai at MLconf SF 2017Matineh Shaker, Artificial Intelligence Scientist, Bonsai at MLconf SF 2017
Matineh Shaker, Artificial Intelligence Scientist, Bonsai at MLconf SF 2017MLconf
 
Switch Transformers: Scaling to Trillion Parameter Models with Simple and Eff...
Switch Transformers: Scaling to Trillion Parameter Models with Simple and Eff...Switch Transformers: Scaling to Trillion Parameter Models with Simple and Eff...
Switch Transformers: Scaling to Trillion Parameter Models with Simple and Eff...taeseon ryu
 
Restricting the Flow: Information Bottlenecks for Attribution
Restricting the Flow: Information Bottlenecks for AttributionRestricting the Flow: Information Bottlenecks for Attribution
Restricting the Flow: Information Bottlenecks for Attributiontaeseon ryu
 
PR-343: Semi-Supervised Semantic Segmentation with Cross Pseudo Supervision
PR-343: Semi-Supervised Semantic Segmentation with Cross Pseudo SupervisionPR-343: Semi-Supervised Semantic Segmentation with Cross Pseudo Supervision
PR-343: Semi-Supervised Semantic Segmentation with Cross Pseudo SupervisionSungchul Kim
 
Human uncertainty makes classification more robust, ICCV 2019 Review
Human uncertainty makes classification more robust, ICCV 2019 ReviewHuman uncertainty makes classification more robust, ICCV 2019 Review
Human uncertainty makes classification more robust, ICCV 2019 ReviewLEE HOSEONG
 
201907 AutoML and Neural Architecture Search
201907 AutoML and Neural Architecture Search201907 AutoML and Neural Architecture Search
201907 AutoML and Neural Architecture SearchDaeJin Kim
 
Deep Learning in Computer Vision
Deep Learning in Computer VisionDeep Learning in Computer Vision
Deep Learning in Computer VisionSungjoon Choi
 
Poster_Reseau_Neurones_Journees_2013
Poster_Reseau_Neurones_Journees_2013Poster_Reseau_Neurones_Journees_2013
Poster_Reseau_Neurones_Journees_2013Pedro Lopes
 
Dueling Network Architectures for Deep Reinforcement Learning
Dueling Network Architectures for Deep Reinforcement LearningDueling Network Architectures for Deep Reinforcement Learning
Dueling Network Architectures for Deep Reinforcement LearningYoonho Lee
 
Bag of tricks for image classification with convolutional neural networks r...
Bag of tricks for image classification with convolutional neural networks   r...Bag of tricks for image classification with convolutional neural networks   r...
Bag of tricks for image classification with convolutional neural networks r...Dongmin Choi
 
2019 cvpr paper_overview
2019 cvpr paper_overview2019 cvpr paper_overview
2019 cvpr paper_overviewLEE HOSEONG
 
Kaggle review Planet: Understanding the Amazon from Space
Kaggle reviewPlanet: Understanding the Amazon from SpaceKaggle reviewPlanet: Understanding the Amazon from Space
Kaggle review Planet: Understanding the Amazon from SpaceEduard Tyantov
 
MetaPerturb: Transferable Regularizer for Heterogeneous Tasks and Architectures
MetaPerturb: Transferable Regularizer for Heterogeneous Tasks and ArchitecturesMetaPerturb: Transferable Regularizer for Heterogeneous Tasks and Architectures
MetaPerturb: Transferable Regularizer for Heterogeneous Tasks and ArchitecturesMLAI2
 
AlexNet and so on...
AlexNet and so on...AlexNet and so on...
AlexNet and so on...Dong Heon Cho
 
Anima Anadkumar, Principal Scientist, Amazon Web Services, Endowed Professor,...
Anima Anadkumar, Principal Scientist, Amazon Web Services, Endowed Professor,...Anima Anadkumar, Principal Scientist, Amazon Web Services, Endowed Professor,...
Anima Anadkumar, Principal Scientist, Amazon Web Services, Endowed Professor,...MLconf
 
Deep learning and image analytics using Python by Dr Sanparit
Deep learning and image analytics using Python by Dr SanparitDeep learning and image analytics using Python by Dr Sanparit
Deep learning and image analytics using Python by Dr SanparitBAINIDA
 

What's hot (20)

Network recasting
Network recastingNetwork recasting
Network recasting
 
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
 
YOLOv4: optimal speed and accuracy of object detection review
YOLOv4: optimal speed and accuracy of object detection reviewYOLOv4: optimal speed and accuracy of object detection review
YOLOv4: optimal speed and accuracy of object detection review
 
Matineh Shaker, Artificial Intelligence Scientist, Bonsai at MLconf SF 2017
Matineh Shaker, Artificial Intelligence Scientist, Bonsai at MLconf SF 2017Matineh Shaker, Artificial Intelligence Scientist, Bonsai at MLconf SF 2017
Matineh Shaker, Artificial Intelligence Scientist, Bonsai at MLconf SF 2017
 
Switch Transformers: Scaling to Trillion Parameter Models with Simple and Eff...
Switch Transformers: Scaling to Trillion Parameter Models with Simple and Eff...Switch Transformers: Scaling to Trillion Parameter Models with Simple and Eff...
Switch Transformers: Scaling to Trillion Parameter Models with Simple and Eff...
 
Restricting the Flow: Information Bottlenecks for Attribution
Restricting the Flow: Information Bottlenecks for AttributionRestricting the Flow: Information Bottlenecks for Attribution
Restricting the Flow: Information Bottlenecks for Attribution
 
PR-343: Semi-Supervised Semantic Segmentation with Cross Pseudo Supervision
PR-343: Semi-Supervised Semantic Segmentation with Cross Pseudo SupervisionPR-343: Semi-Supervised Semantic Segmentation with Cross Pseudo Supervision
PR-343: Semi-Supervised Semantic Segmentation with Cross Pseudo Supervision
 
Human uncertainty makes classification more robust, ICCV 2019 Review
Human uncertainty makes classification more robust, ICCV 2019 ReviewHuman uncertainty makes classification more robust, ICCV 2019 Review
Human uncertainty makes classification more robust, ICCV 2019 Review
 
201907 AutoML and Neural Architecture Search
201907 AutoML and Neural Architecture Search201907 AutoML and Neural Architecture Search
201907 AutoML and Neural Architecture Search
 
Deep Learning in Computer Vision
Deep Learning in Computer VisionDeep Learning in Computer Vision
Deep Learning in Computer Vision
 
Poster_Reseau_Neurones_Journees_2013
Poster_Reseau_Neurones_Journees_2013Poster_Reseau_Neurones_Journees_2013
Poster_Reseau_Neurones_Journees_2013
 
Dueling Network Architectures for Deep Reinforcement Learning
Dueling Network Architectures for Deep Reinforcement LearningDueling Network Architectures for Deep Reinforcement Learning
Dueling Network Architectures for Deep Reinforcement Learning
 
Bag of tricks for image classification with convolutional neural networks r...
Bag of tricks for image classification with convolutional neural networks   r...Bag of tricks for image classification with convolutional neural networks   r...
Bag of tricks for image classification with convolutional neural networks r...
 
InfoGAIL
InfoGAIL InfoGAIL
InfoGAIL
 
2019 cvpr paper_overview
2019 cvpr paper_overview2019 cvpr paper_overview
2019 cvpr paper_overview
 
Kaggle review Planet: Understanding the Amazon from Space
Kaggle reviewPlanet: Understanding the Amazon from SpaceKaggle reviewPlanet: Understanding the Amazon from Space
Kaggle review Planet: Understanding the Amazon from Space
 
MetaPerturb: Transferable Regularizer for Heterogeneous Tasks and Architectures
MetaPerturb: Transferable Regularizer for Heterogeneous Tasks and ArchitecturesMetaPerturb: Transferable Regularizer for Heterogeneous Tasks and Architectures
MetaPerturb: Transferable Regularizer for Heterogeneous Tasks and Architectures
 
AlexNet and so on...
AlexNet and so on...AlexNet and so on...
AlexNet and so on...
 
Anima Anadkumar, Principal Scientist, Amazon Web Services, Endowed Professor,...
Anima Anadkumar, Principal Scientist, Amazon Web Services, Endowed Professor,...Anima Anadkumar, Principal Scientist, Amazon Web Services, Endowed Professor,...
Anima Anadkumar, Principal Scientist, Amazon Web Services, Endowed Professor,...
 
Deep learning and image analytics using Python by Dr Sanparit
Deep learning and image analytics using Python by Dr SanparitDeep learning and image analytics using Python by Dr Sanparit
Deep learning and image analytics using Python by Dr Sanparit
 

Similar to Image classification with neural networks

Cvpr 2018 papers review (efficient computing)
Cvpr 2018 papers review (efficient computing)Cvpr 2018 papers review (efficient computing)
Cvpr 2018 papers review (efficient computing)DonghyunKang12
 
08 neural networks
08 neural networks08 neural networks
08 neural networksankit_ppt
 
Deep Learning Interview Questions And Answers | AI & Deep Learning Interview ...
Deep Learning Interview Questions And Answers | AI & Deep Learning Interview ...Deep Learning Interview Questions And Answers | AI & Deep Learning Interview ...
Deep Learning Interview Questions And Answers | AI & Deep Learning Interview ...Simplilearn
 
Artificial neural network model & hidden layers in multilayer artificial neur...
Artificial neural network model & hidden layers in multilayer artificial neur...Artificial neural network model & hidden layers in multilayer artificial neur...
Artificial neural network model & hidden layers in multilayer artificial neur...Muhammad Ishaq
 
Machine Learning, Deep Learning and Data Analysis Introduction
Machine Learning, Deep Learning and Data Analysis IntroductionMachine Learning, Deep Learning and Data Analysis Introduction
Machine Learning, Deep Learning and Data Analysis IntroductionTe-Yen Liu
 
DeepLearningLecture.pptx
DeepLearningLecture.pptxDeepLearningLecture.pptx
DeepLearningLecture.pptxssuserf07225
 
Facial Emotion Detection on Children's Emotional Face
Facial Emotion Detection on Children's Emotional FaceFacial Emotion Detection on Children's Emotional Face
Facial Emotion Detection on Children's Emotional FaceTakrim Ul Islam Laskar
 
Computer Vision for Beginners
Computer Vision for BeginnersComputer Vision for Beginners
Computer Vision for BeginnersSanghamitra Deb
 
Finding the best solution for Image Processing
Finding the best solution for Image ProcessingFinding the best solution for Image Processing
Finding the best solution for Image ProcessingTech Triveni
 
An Introduction to Deep Learning
An Introduction to Deep LearningAn Introduction to Deep Learning
An Introduction to Deep Learningmilad abbasi
 
Introduction to Deep Learning
Introduction to Deep LearningIntroduction to Deep Learning
Introduction to Deep LearningMehrnaz Faraz
 
NVIDIA 深度學習教育機構 (DLI): Image segmentation with tensorflow
NVIDIA 深度學習教育機構 (DLI): Image segmentation with tensorflowNVIDIA 深度學習教育機構 (DLI): Image segmentation with tensorflow
NVIDIA 深度學習教育機構 (DLI): Image segmentation with tensorflowNVIDIA Taiwan
 
Deep learning with TensorFlow
Deep learning with TensorFlowDeep learning with TensorFlow
Deep learning with TensorFlowBarbara Fusinska
 
Deep Learning for Computer Vision - PyconDE 2017
Deep Learning for Computer Vision - PyconDE 2017Deep Learning for Computer Vision - PyconDE 2017
Deep Learning for Computer Vision - PyconDE 2017Alex Conway
 
Activation functions and Training Algorithms for Deep Neural network
Activation functions and Training Algorithms for Deep Neural networkActivation functions and Training Algorithms for Deep Neural network
Activation functions and Training Algorithms for Deep Neural networkGayatri Khanvilkar
 

Similar to Image classification with neural networks (20)

Cvpr 2018 papers review (efficient computing)
Cvpr 2018 papers review (efficient computing)Cvpr 2018 papers review (efficient computing)
Cvpr 2018 papers review (efficient computing)
 
Development of Deep Learning Architecture
Development of Deep Learning ArchitectureDevelopment of Deep Learning Architecture
Development of Deep Learning Architecture
 
08 neural networks
08 neural networks08 neural networks
08 neural networks
 
Introduction to deep learning
Introduction to deep learningIntroduction to deep learning
Introduction to deep learning
 
Deep Learning Interview Questions And Answers | AI & Deep Learning Interview ...
Deep Learning Interview Questions And Answers | AI & Deep Learning Interview ...Deep Learning Interview Questions And Answers | AI & Deep Learning Interview ...
Deep Learning Interview Questions And Answers | AI & Deep Learning Interview ...
 
Artificial neural network model & hidden layers in multilayer artificial neur...
Artificial neural network model & hidden layers in multilayer artificial neur...Artificial neural network model & hidden layers in multilayer artificial neur...
Artificial neural network model & hidden layers in multilayer artificial neur...
 
Deep Learning Initiative @ NECSTLab
Deep Learning Initiative @ NECSTLabDeep Learning Initiative @ NECSTLab
Deep Learning Initiative @ NECSTLab
 
Machine Learning, Deep Learning and Data Analysis Introduction
Machine Learning, Deep Learning and Data Analysis IntroductionMachine Learning, Deep Learning and Data Analysis Introduction
Machine Learning, Deep Learning and Data Analysis Introduction
 
DeepLearningLecture.pptx
DeepLearningLecture.pptxDeepLearningLecture.pptx
DeepLearningLecture.pptx
 
Facial Emotion Detection on Children's Emotional Face
Facial Emotion Detection on Children's Emotional FaceFacial Emotion Detection on Children's Emotional Face
Facial Emotion Detection on Children's Emotional Face
 
Computer Vision for Beginners
Computer Vision for BeginnersComputer Vision for Beginners
Computer Vision for Beginners
 
Deep learning
Deep learningDeep learning
Deep learning
 
Finding the best solution for Image Processing
Finding the best solution for Image ProcessingFinding the best solution for Image Processing
Finding the best solution for Image Processing
 
An Introduction to Deep Learning
An Introduction to Deep LearningAn Introduction to Deep Learning
An Introduction to Deep Learning
 
Introduction to Deep Learning
Introduction to Deep LearningIntroduction to Deep Learning
Introduction to Deep Learning
 
NVIDIA 深度學習教育機構 (DLI): Image segmentation with tensorflow
NVIDIA 深度學習教育機構 (DLI): Image segmentation with tensorflowNVIDIA 深度學習教育機構 (DLI): Image segmentation with tensorflow
NVIDIA 深度學習教育機構 (DLI): Image segmentation with tensorflow
 
Deep learning with TensorFlow
Deep learning with TensorFlowDeep learning with TensorFlow
Deep learning with TensorFlow
 
Computer Design Concepts for Machine Learning
Computer Design Concepts for Machine LearningComputer Design Concepts for Machine Learning
Computer Design Concepts for Machine Learning
 
Deep Learning for Computer Vision - PyconDE 2017
Deep Learning for Computer Vision - PyconDE 2017Deep Learning for Computer Vision - PyconDE 2017
Deep Learning for Computer Vision - PyconDE 2017
 
Activation functions and Training Algorithms for Deep Neural network
Activation functions and Training Algorithms for Deep Neural networkActivation functions and Training Algorithms for Deep Neural network
Activation functions and Training Algorithms for Deep Neural network
 

Recently uploaded

1029-Danh muc Sach Giao Khoa khoi 6.pdf
1029-Danh muc Sach Giao Khoa khoi  6.pdf1029-Danh muc Sach Giao Khoa khoi  6.pdf
1029-Danh muc Sach Giao Khoa khoi 6.pdfQucHHunhnh
 
Separation of Lanthanides/ Lanthanides and Actinides
Separation of Lanthanides/ Lanthanides and ActinidesSeparation of Lanthanides/ Lanthanides and Actinides
Separation of Lanthanides/ Lanthanides and ActinidesFatimaKhan178732
 
Kisan Call Centre - To harness potential of ICT in Agriculture by answer farm...
Kisan Call Centre - To harness potential of ICT in Agriculture by answer farm...Kisan Call Centre - To harness potential of ICT in Agriculture by answer farm...
Kisan Call Centre - To harness potential of ICT in Agriculture by answer farm...Krashi Coaching
 
Call Girls in Dwarka Mor Delhi Contact Us 9654467111
Call Girls in Dwarka Mor Delhi Contact Us 9654467111Call Girls in Dwarka Mor Delhi Contact Us 9654467111
Call Girls in Dwarka Mor Delhi Contact Us 9654467111Sapana Sha
 
Student login on Anyboli platform.helpin
Student login on Anyboli platform.helpinStudent login on Anyboli platform.helpin
Student login on Anyboli platform.helpinRaunakKeshri1
 
Software Engineering Methodologies (overview)
Software Engineering Methodologies (overview)Software Engineering Methodologies (overview)
Software Engineering Methodologies (overview)eniolaolutunde
 
Privatization and Disinvestment - Meaning, Objectives, Advantages and Disadva...
Privatization and Disinvestment - Meaning, Objectives, Advantages and Disadva...Privatization and Disinvestment - Meaning, Objectives, Advantages and Disadva...
Privatization and Disinvestment - Meaning, Objectives, Advantages and Disadva...RKavithamani
 
SOCIAL AND HISTORICAL CONTEXT - LFTVD.pptx
SOCIAL AND HISTORICAL CONTEXT - LFTVD.pptxSOCIAL AND HISTORICAL CONTEXT - LFTVD.pptx
SOCIAL AND HISTORICAL CONTEXT - LFTVD.pptxiammrhaywood
 
The Most Excellent Way | 1 Corinthians 13
The Most Excellent Way | 1 Corinthians 13The Most Excellent Way | 1 Corinthians 13
The Most Excellent Way | 1 Corinthians 13Steve Thomason
 
Contemporary philippine arts from the regions_PPT_Module_12 [Autosaved] (1).pptx
Contemporary philippine arts from the regions_PPT_Module_12 [Autosaved] (1).pptxContemporary philippine arts from the regions_PPT_Module_12 [Autosaved] (1).pptx
Contemporary philippine arts from the regions_PPT_Module_12 [Autosaved] (1).pptxRoyAbrique
 
CARE OF CHILD IN INCUBATOR..........pptx
CARE OF CHILD IN INCUBATOR..........pptxCARE OF CHILD IN INCUBATOR..........pptx
CARE OF CHILD IN INCUBATOR..........pptxGaneshChakor2
 
POINT- BIOCHEMISTRY SEM 2 ENZYMES UNIT 5.pptx
POINT- BIOCHEMISTRY SEM 2 ENZYMES UNIT 5.pptxPOINT- BIOCHEMISTRY SEM 2 ENZYMES UNIT 5.pptx
POINT- BIOCHEMISTRY SEM 2 ENZYMES UNIT 5.pptxSayali Powar
 
The basics of sentences session 2pptx copy.pptx
The basics of sentences session 2pptx copy.pptxThe basics of sentences session 2pptx copy.pptx
The basics of sentences session 2pptx copy.pptxheathfieldcps1
 
Advanced Views - Calendar View in Odoo 17
Advanced Views - Calendar View in Odoo 17Advanced Views - Calendar View in Odoo 17
Advanced Views - Calendar View in Odoo 17Celine George
 
microwave assisted reaction. General introduction
microwave assisted reaction. General introductionmicrowave assisted reaction. General introduction
microwave assisted reaction. General introductionMaksud Ahmed
 
Hybridoma Technology ( Production , Purification , and Application )
Hybridoma Technology  ( Production , Purification , and Application  ) Hybridoma Technology  ( Production , Purification , and Application  )
Hybridoma Technology ( Production , Purification , and Application ) Sakshi Ghasle
 

Recently uploaded (20)

1029-Danh muc Sach Giao Khoa khoi 6.pdf
1029-Danh muc Sach Giao Khoa khoi  6.pdf1029-Danh muc Sach Giao Khoa khoi  6.pdf
1029-Danh muc Sach Giao Khoa khoi 6.pdf
 
Mattingly "AI & Prompt Design: Structured Data, Assistants, & RAG"
Mattingly "AI & Prompt Design: Structured Data, Assistants, & RAG"Mattingly "AI & Prompt Design: Structured Data, Assistants, & RAG"
Mattingly "AI & Prompt Design: Structured Data, Assistants, & RAG"
 
Separation of Lanthanides/ Lanthanides and Actinides
Separation of Lanthanides/ Lanthanides and ActinidesSeparation of Lanthanides/ Lanthanides and Actinides
Separation of Lanthanides/ Lanthanides and Actinides
 
Kisan Call Centre - To harness potential of ICT in Agriculture by answer farm...
Kisan Call Centre - To harness potential of ICT in Agriculture by answer farm...Kisan Call Centre - To harness potential of ICT in Agriculture by answer farm...
Kisan Call Centre - To harness potential of ICT in Agriculture by answer farm...
 
Call Girls in Dwarka Mor Delhi Contact Us 9654467111
Call Girls in Dwarka Mor Delhi Contact Us 9654467111Call Girls in Dwarka Mor Delhi Contact Us 9654467111
Call Girls in Dwarka Mor Delhi Contact Us 9654467111
 
Student login on Anyboli platform.helpin
Student login on Anyboli platform.helpinStudent login on Anyboli platform.helpin
Student login on Anyboli platform.helpin
 
Software Engineering Methodologies (overview)
Software Engineering Methodologies (overview)Software Engineering Methodologies (overview)
Software Engineering Methodologies (overview)
 
Privatization and Disinvestment - Meaning, Objectives, Advantages and Disadva...
Privatization and Disinvestment - Meaning, Objectives, Advantages and Disadva...Privatization and Disinvestment - Meaning, Objectives, Advantages and Disadva...
Privatization and Disinvestment - Meaning, Objectives, Advantages and Disadva...
 
SOCIAL AND HISTORICAL CONTEXT - LFTVD.pptx
SOCIAL AND HISTORICAL CONTEXT - LFTVD.pptxSOCIAL AND HISTORICAL CONTEXT - LFTVD.pptx
SOCIAL AND HISTORICAL CONTEXT - LFTVD.pptx
 
The Most Excellent Way | 1 Corinthians 13
The Most Excellent Way | 1 Corinthians 13The Most Excellent Way | 1 Corinthians 13
The Most Excellent Way | 1 Corinthians 13
 
Mattingly "AI & Prompt Design: The Basics of Prompt Design"
Mattingly "AI & Prompt Design: The Basics of Prompt Design"Mattingly "AI & Prompt Design: The Basics of Prompt Design"
Mattingly "AI & Prompt Design: The Basics of Prompt Design"
 
Contemporary philippine arts from the regions_PPT_Module_12 [Autosaved] (1).pptx
Contemporary philippine arts from the regions_PPT_Module_12 [Autosaved] (1).pptxContemporary philippine arts from the regions_PPT_Module_12 [Autosaved] (1).pptx
Contemporary philippine arts from the regions_PPT_Module_12 [Autosaved] (1).pptx
 
CARE OF CHILD IN INCUBATOR..........pptx
CARE OF CHILD IN INCUBATOR..........pptxCARE OF CHILD IN INCUBATOR..........pptx
CARE OF CHILD IN INCUBATOR..........pptx
 
Staff of Color (SOC) Retention Efforts DDSD
Staff of Color (SOC) Retention Efforts DDSDStaff of Color (SOC) Retention Efforts DDSD
Staff of Color (SOC) Retention Efforts DDSD
 
POINT- BIOCHEMISTRY SEM 2 ENZYMES UNIT 5.pptx
POINT- BIOCHEMISTRY SEM 2 ENZYMES UNIT 5.pptxPOINT- BIOCHEMISTRY SEM 2 ENZYMES UNIT 5.pptx
POINT- BIOCHEMISTRY SEM 2 ENZYMES UNIT 5.pptx
 
The basics of sentences session 2pptx copy.pptx
The basics of sentences session 2pptx copy.pptxThe basics of sentences session 2pptx copy.pptx
The basics of sentences session 2pptx copy.pptx
 
Advanced Views - Calendar View in Odoo 17
Advanced Views - Calendar View in Odoo 17Advanced Views - Calendar View in Odoo 17
Advanced Views - Calendar View in Odoo 17
 
INDIA QUIZ 2024 RLAC DELHI UNIVERSITY.pptx
INDIA QUIZ 2024 RLAC DELHI UNIVERSITY.pptxINDIA QUIZ 2024 RLAC DELHI UNIVERSITY.pptx
INDIA QUIZ 2024 RLAC DELHI UNIVERSITY.pptx
 
microwave assisted reaction. General introduction
microwave assisted reaction. General introductionmicrowave assisted reaction. General introduction
microwave assisted reaction. General introduction
 
Hybridoma Technology ( Production , Purification , and Application )
Hybridoma Technology  ( Production , Purification , and Application  ) Hybridoma Technology  ( Production , Purification , and Application  )
Hybridoma Technology ( Production , Purification , and Application )
 

Image classification with neural networks

  • 1. Amirkabir University of Technology Department of Computer Engineering and Information Technology Image Classification with Deep Convolutional Neural Networks Sepehr Rasouli
  • 2. Introduction > Methods > Results > Conclusion2 Outline • Introduction to Image Classification & Deep Networks • Proposed Method • Main Idea • Data Set • Architecture • Techniques • Comparison & Results • Conclusion
  • 3. Introduction > Methods > Results > Conclusion3 Image Classification
  • 4. Introduction > Methods > Results > Conclusion4 Why Deep Learning? •“Shallow” vs. “deep” architectures Learn a feature hierarchy all the way from pixels to classifier Hand Designed Feature Extraction Trainable Classifier Layer 1 Layer N Simpler classifier
  • 5. Introduction > Methods > Results > Conclusion5 Our Method • Deep Convolutional Neural Network • 5 convolutional and 3 fully connected layers • 650,000 neurons, 60 million parameters • Techniques used for boosting up performance • ReLU nonlinearity • Training on Multiple GPUs • Overlapping max pooling • Data Augmentation • Dropout
  • 6. Introduction > Methods > Results > Conclusion6 Overall Architecture • Trained with stochastic gradient descent on two NVIDIA GPUs for about a week (5~6 days) • 650,000 neurons, 60 million parameters, 630 million connections • The last layer contains 1,000 neurons which produces a distribution over the 1,000 class labels.
  • 7. Introduction > Methods > Results > Conclusion7 Dataset • ImageNet § Over 15 million high-quality labeled images § About 22,000 categories § Collected from the web, labeled by humans on Amazon's Mechanical Turk § Variable-resolution images • ILSVRC Competition § ImageNet Large-Scale Pascal Visual Object Challenge § Annual competition of image classification at large scale § Subset of ImageNet § 1,000 categories with about 1,000 images each § 1.2M images in 1K categories § Classification: make 5 guesses about the image label
  • 8. Introduction > Methods > Results > Conclusion8 Rectified Linear Units 𝑥 = 𝑤$ 𝑓 𝑍$ + 𝑤( 𝑓 𝑍( +𝑤) 𝑓 𝑍) x is called the total input to the neuron, and f(x) is its output Very bad (slow to train ) Very good (quick to train) f(x) = max(0,x)f(x) = tanh(x)
  • 9. Introduction > Methods > Results > Conclusion9 Rectified Linear Units • Biological plausibility: One-sided, compared to the antisymmetry of tanh. • Sparse activation: For example, in a randomly initialized network, only about 50% of hidden units are activated (having a non-zero output). • Efficient gradient propagation: No vanishing gradient problem or exploding effect. • Efficient computation: Only comparison, addition and multiplication
  • 10. Introduction > Methods > Results > Conclusion10 Training on Multiple GPUs • Spread across two GPUs • GTX 580 GPU with 3GB memory • Particularly well-suited to cross-GPU parallelization • Very efficient implementation of CNN on GPUs
  • 11. Model Top-1 Top-5 Sparse coding [3] 47.1% 28.2% SIFT + FVs [4] 45.7% 25.7% CNN 37.5 17.0% Introduction > Methods > Results > Conclusion11 Results & Comparison •ILSVRC-2010 test set ILSVRC-2010 winner Previous best published result Our Method Comparison of results on ILSRVCs 2010 test set. In italics best results achieved by others.
  • 12. Introduction > Methods > Results > Conclusion12 Conclusion • Large, deep convolutional neural networks for large scale image classification was proposed • 5 convolutional layers, 3 fully-connected layers • 650,000 neurons, 60 million parameters • Several techniques for boosting up performance • The proposed method won the ILSVRC-2012 • Achieved a winning top-5 error rate of 15.3%, compared to 26.2% achieved by the second-best entry
  • 13. Introduction > Methods > Results > Conclusion13 Conclusion
  • 14. Introduction > Methods > Results > Conclusion14 References [1] http://cs.nyu.edu/~fergus/tutorials/ deep_learning_cvpr12/fergus_dl_tutorial_final.pptx [2] reference : http://web.engr.illinois.edu/ ~slazebni/spring14/lec24_cnn.pdf [3] A. Berg, J. Deng, and L. Fei-Fei. Large scale visual recognition challenge 2010. www.imagenet.org/challenges. 2010. [4] S. Tara, Brian Kingsbury, A.-r. Mohamed and B. Ramabhadran, "Learning Filter Banks within a Deep [4] J.Sánchezand F.Perronnin.High-dimensional signature compression for large-scale image classification. In Computer Vision and Pattern Recognition(CVPR), 2011IEEEConferenceon,pages1665–1672.IEEE, 2011.
  • 15. Introduction > Methods > Results > Conclusion15 Thank you for your attention Any Questions?
  • 16. Introduction > Methods > Results > Conclusion16 Results 2012 • ILSVRC-2012 results Proposed method Top-5 error rate : 16.422% Runner-up Top-5 error rate : 26.172%
  • 17. Introduction > Methods > Results > Conclusion17 Convolutional NNs
  • 18. Introduction > Methods > Results > Conclusion18 Pooling • Spatial Pooling • Non-overlapping / overlapping regions • Sum or max Max Sum
  • 19. Introduction > Methods > Results > Conclusion19 Dropout • Independently set each hidden unit activity to zero with 0.5 probability • Used in the two globally-connected hidden layers at the net's output