SlideShare a Scribd company logo
Applications of Deep Learning
in Computer Vision
Christoph Körner
Outline
1) Introduction to Neural Networks
2) Deep Learning
3) Applications in Computer Vision
4) Conclusion
Why Deep Learning?
●
Wins every computer vision challenge
(classification, segmentation, etc.)
●
Can be applied in various domains (speech
recognition, game prediction, computer vision,
etc.)
●
Beats human accuracy
●
Big communities and resources
●
Hardware for Deep Learning
Perceptron (1958)
●
Weighted sum of inputs
●
Threshold operator
Artificial Neural Network (1960)
●
Universal function approximator
●
Can solve the XOR problem
Backpropagation (1982)
●
Propagate the error through the network
●
Allows Optimization (SGD, etc.)
●
Enables training of multi-layer networks
Convolution and Pooling (1989)
●
Less parameters than hidden layers
●
More efficient training
Handwritten ZIP Codes (1989)
●
30 training passes
●
Achieved 92% accuracy
What happened until 2011?
●
Better Initialization
●
Better Non-linearities: ReLU
●
1000 times more training data
●
More computing power
●
Factor 1 million speedup in training time through
parallelization on GPUs
Deep Learning
●
Conv-, Pool- and Fully-Connected Layers
●
ReLU activations
●
Deep nested models with many parameters
●
New layer types and structures
●
New techniques to reduce overfitting
●
Loads of training data and compute power
●
10.000.000 images
●
Weeks of training on multi-GPU machines
AlexNet (2012)
●
62.378.344 parameters (250MB)
●
24 layers
VGGNet (2013)
●
102.908.520 parameters (412MB)
●
23 layers
GoogLeNet (2014)
●
6.998.552 parameters (28MB)
●
143 layers
Inception Module
●
Heavy use of 1x1 convolutions (applied along the
depth dimension)
●
Very efficient
ResNet (2015)
●
Residual learning
●
152 layers
Applications in Computer Vision
Classification
●
One class per image
●
Softmax layer at the end
Localization
●
Bounding box Regression
●
Sigmoid layer with 4 outputs at the end
●
Via Classification
Detection
●
Multiple Objects, multiple classes
●
Solved using multiple networks
Segmentation
More Applications
●
Compression
●
Auto-encoders, Self-organizing maps
●
Image Captioning
●
Solved with Recurrent Architecture
●
Image Stylization
●
Clustering
●
Many more...
Conclusion
●
Powerful, learn from data instead of hand-crafted
feature extraction
●
Better than humans
●
Deeper is always better
●
Overfitting
●
More data is always better
●
Data quality
●
Ground truth
Thank you!
Christoph Körner

More Related Content

PPTX
Image classification using CNN
PPTX
Introduction to Deep learning
PPTX
TEXT-SPEECH PPT.pptx
PDF
Recurrent Neural Networks, LSTM and GRU
PPTX
Transfer Learning and Fine-tuning Deep Neural Networks
PDF
Deep learning - A Visual Introduction
PPTX
Deep Learning Explained
PPTX
Face recognization using artificial nerual network
Image classification using CNN
Introduction to Deep learning
TEXT-SPEECH PPT.pptx
Recurrent Neural Networks, LSTM and GRU
Transfer Learning and Fine-tuning Deep Neural Networks
Deep learning - A Visual Introduction
Deep Learning Explained
Face recognization using artificial nerual network

What's hot (20)

PPTX
Introduction to CNN
PPTX
Intro to deep learning
PPTX
Artificial intelligence in software engineering ppt.
PDF
Introduction to Generative Adversarial Networks (GANs)
PPTX
BERT introduction
PPTX
Convolution Neural Network (CNN)
PDF
Introduction to LLMs
PDF
Machine learning
PDF
A brief history of machine learning
PPTX
Artificial Intelligence Course | AI Tutorial For Beginners | Artificial Intel...
PDF
Deep learning for NLP and Transformer
PDF
An introduction to the Transformers architecture and BERT
PDF
Introduction to Deep Learning
PPTX
Introduction to Deep Learning
PPTX
PDF
Machine Learning
PPT
Deep learning ppt
PDF
Deep learning
PPTX
Transfer learning-presentation
Introduction to CNN
Intro to deep learning
Artificial intelligence in software engineering ppt.
Introduction to Generative Adversarial Networks (GANs)
BERT introduction
Convolution Neural Network (CNN)
Introduction to LLMs
Machine learning
A brief history of machine learning
Artificial Intelligence Course | AI Tutorial For Beginners | Artificial Intel...
Deep learning for NLP and Transformer
An introduction to the Transformers architecture and BERT
Introduction to Deep Learning
Introduction to Deep Learning
Machine Learning
Deep learning ppt
Deep learning
Transfer learning-presentation
Ad

Similar to Intro to Deep Learning for Computer Vision (20)

PPTX
Deep learning
PDF
Deep convolutional neural networks and their many uses for computer vision
PDF
Deep_Learning_Applications_Detailed_Presentation.pdf
PDF
Industry Applications for Computer Vision and Deep Learning
PPTX
Learn to Build an App to Find Similar Images using Deep Learning- Piotr Teterwak
PPT
Introduction_to_DEEP_LEARNING.sfsdafsadfsadfsdafsdppt
PDF
Deep Learning Applications and Image Processing
PPT
Introduction_to_DEEP_LEARNING ppt 101ppt
PPT
Introduction_to_DEEP_LEARNING.ppt
PDF
Deep Learning AtoC with Image Perspective
PDF
Introduction to Deep Learning: Concepts, Architectures, and Applications
PDF
CNN Algorithm
PDF
Tutorial on Deep Learning
PPTX
Data Con LA 2019 - State of the Art of Innovation in Computer Vision by Chris...
PDF
Neural networks and deep learning
PPTX
Introduction to Deep learning
PDF
DLD meetup 2017, Efficient Deep Learning
PPTX
Computer vision - Applications and Trends
PDF
“Introduction to Computer Vision with CNNs,” a Presentation from Mohammad Hag...
PDF
Lecture 1: Deep Learning for Computer Vision
Deep learning
Deep convolutional neural networks and their many uses for computer vision
Deep_Learning_Applications_Detailed_Presentation.pdf
Industry Applications for Computer Vision and Deep Learning
Learn to Build an App to Find Similar Images using Deep Learning- Piotr Teterwak
Introduction_to_DEEP_LEARNING.sfsdafsadfsadfsdafsdppt
Deep Learning Applications and Image Processing
Introduction_to_DEEP_LEARNING ppt 101ppt
Introduction_to_DEEP_LEARNING.ppt
Deep Learning AtoC with Image Perspective
Introduction to Deep Learning: Concepts, Architectures, and Applications
CNN Algorithm
Tutorial on Deep Learning
Data Con LA 2019 - State of the Art of Innovation in Computer Vision by Chris...
Neural networks and deep learning
Introduction to Deep learning
DLD meetup 2017, Efficient Deep Learning
Computer vision - Applications and Trends
“Introduction to Computer Vision with CNNs,” a Presentation from Mohammad Hag...
Lecture 1: Deep Learning for Computer Vision
Ad

Recently uploaded (20)

PPTX
sap open course for s4hana steps from ECC to s4
PDF
Encapsulation theory and applications.pdf
PDF
Dropbox Q2 2025 Financial Results & Investor Presentation
PDF
Diabetes mellitus diagnosis method based random forest with bat algorithm
PDF
Per capita expenditure prediction using model stacking based on satellite ima...
PDF
Electronic commerce courselecture one. Pdf
PDF
Network Security Unit 5.pdf for BCA BBA.
DOCX
The AUB Centre for AI in Media Proposal.docx
PPTX
Detection-First SIEM: Rule Types, Dashboards, and Threat-Informed Strategy
PDF
Peak of Data & AI Encore- AI for Metadata and Smarter Workflows
PDF
Profit Center Accounting in SAP S/4HANA, S4F28 Col11
PDF
NewMind AI Weekly Chronicles - August'25 Week I
PDF
Optimiser vos workloads AI/ML sur Amazon EC2 et AWS Graviton
PDF
cuic standard and advanced reporting.pdf
PPTX
20250228 LYD VKU AI Blended-Learning.pptx
PPTX
Spectroscopy.pptx food analysis technology
PDF
The Rise and Fall of 3GPP – Time for a Sabbatical?
PPT
“AI and Expert System Decision Support & Business Intelligence Systems”
PDF
Approach and Philosophy of On baking technology
PDF
MIND Revenue Release Quarter 2 2025 Press Release
sap open course for s4hana steps from ECC to s4
Encapsulation theory and applications.pdf
Dropbox Q2 2025 Financial Results & Investor Presentation
Diabetes mellitus diagnosis method based random forest with bat algorithm
Per capita expenditure prediction using model stacking based on satellite ima...
Electronic commerce courselecture one. Pdf
Network Security Unit 5.pdf for BCA BBA.
The AUB Centre for AI in Media Proposal.docx
Detection-First SIEM: Rule Types, Dashboards, and Threat-Informed Strategy
Peak of Data & AI Encore- AI for Metadata and Smarter Workflows
Profit Center Accounting in SAP S/4HANA, S4F28 Col11
NewMind AI Weekly Chronicles - August'25 Week I
Optimiser vos workloads AI/ML sur Amazon EC2 et AWS Graviton
cuic standard and advanced reporting.pdf
20250228 LYD VKU AI Blended-Learning.pptx
Spectroscopy.pptx food analysis technology
The Rise and Fall of 3GPP – Time for a Sabbatical?
“AI and Expert System Decision Support & Business Intelligence Systems”
Approach and Philosophy of On baking technology
MIND Revenue Release Quarter 2 2025 Press Release

Intro to Deep Learning for Computer Vision