SlideShare ist ein Scribd-Unternehmen logo
1 von 24
Downloaden Sie, um offline zu lesen
© 2021 Deep Netts
Modern Machine Vision from
Basics to Advanced Deep
Learning
Zoran Sevarac
University Of Belgrade /
Deep Netts
© 2021 Deep Netts
What are you going to learn
• Machine learning basic ideas
• Deep learning, and what’s so special about it
• How to use deep learning for image classification
• Advanced deep learning models for object detection
2
Machine Learning Basics
© 2021 Deep Netts
What is Machine Learning?
• Type of computer algorithm that is capable
to automatically configure its internal parameters (learn)
by looking at a set of examples given as a data set,
in order to perform specific task on similar data with usable accuracy.
• Examples of what it can do :
• Learn to assign items to category - classification
• Learn relationship between variables,
in order to estimate a numeric value - regression
4
© 2021 Deep Netts
Deep Learning
• Advanced machine learning technique
• Higher accuracy with more data
• Successful in solving vision-based
problems, and in general problems with
lots of inputs.
• Automates manual feature extraction
commonly used for image classification in
traditional machine learning
• Breakthrough in image recognition, and
natural language processing
5
Source:
https://machinelearningmastery.com/what-is-
deep-learning/
https://www.slideshare.net/NVIDIA/nvidia-ces-
2016-press-conference
© 2021 Deep Netts
Shallow vs Deep Learning
https://www.frontiersin.org/articles/10.3389/fninf.2019.00053/full
6
https://www.linkedin.com/pulse/introduction-shallow-machine-learning-ayman-mahmoud/
Deep Learning / Neural Networks
© 2021 Deep Netts
Feed Forward Neural Network
• Nodes are grouped into layers that
determine the order of
execution/computation.
• Each node performs computation
based on its inputs and set of
weight coefficients.
• Learning is based on error
minimization of total network
error for given data set.
• Can be use for both classification
and regression tasks
8
© 2021 Deep Netts
Supervised Training Procedure
9
Neural Network
Training Data
Components for training a
network:
• Network
• Training data
• Optimizer
• Testing data
© 2021 Deep Netts
From Image Classification to Object Detection
• Image Classification – assign an
image into one of many different
categories
• Object Localization – determine
the location of a single object
within image
• Object Detection – localizing and
classifying multiple objects within
image
10
Image Source: https://leonardoaraujosantos.gitbook.io
© 2021 Deep Netts
Convolutional Neural Networks and
Image Classification
• Extension of a feed forward network
specialized for image
classification/recognition
• Introduces convolutional layers with
adaptive image filters capable for
learning and detecting shape and color
features
• Reduces image preprocessing and
feature extraction – now it’s learned
during the training
11
© 2021 Deep Netts
Convolution - the Magic of Convolutional Layer
12
Image source: https://towardsdatascience.com/a-comprehensive-guide-to-convolutional-neural-networks-the-eli5-way-3bd2b1164a53
Convolution operation is sliding small matrix (filter) over input pixels
© 2021 Deep Netts
Types of Layers in CNN
• Convolutional Layer – performs feature detection
• Max Pooling Layer – scales down input images
• Fully Connected Layer – performs classification
• Softmax Layer – estimates probability for categories
• Linear Layer – performs regression, estimates object position
• Dropout Layer – reduces overfitting
13
© 2021 Deep Netts
Multiple Layers Combined :
Image Classification Using CNN
14
Image source: https://developer.nvidia.com/discover/convolutional-neural-network
© 2021 Deep Netts
Common CNN Architectures
• VGG Net: 16 or 19 layers, 3x3 conv
filters
• ResNet: skip connections enable
deeper networks
• InceptionNet: concatenates filters of
different sizes 3x3, 5x5, 1x1
• Mobile Net: depthwise separable
convolutions, and thinner more
efficient networks
15
Residual/skip connections
Filter concatenation
© 2021 Deep Netts
Quick Overview of the
Evolution of Object Detection
• Convolutional Network for Object Detection
• Region-based Convolutional Neural Network (RCNN)
• Fast RCNN
• Faster RCNN
• You Look Only Once - YOLO
• Single Shot Detector – SSD
• Convolutional network for image classification +
Regression for determining the position
16
© 2021 Deep Netts
Region-based Convolutional Neural Network
• Generate about 2000 region
proposals from input image using
the Selective Search
• Run a convolutional net to classify
each region proposal
• Intuitive but slow
17
© 2021 Deep Netts
Fast R-CNN
• In order to reduce computation
region proposals are generated from
the last convolutional layer, not from
the original image.
• The computationally expensive
convolutional layers are calculated
only once.
• Still using selective search for region
proposals
18
Image source: https://www.kdnuggets.com/2017/10/deep-learning-object-
detection-comprehensive-review.html
© 2021 Deep Netts
Faster RCNN
• Introduced region proposal network
instead of selective search: does the
region contain object?
19
Image source: https://www.kdnuggets.com/2017/10/deep-
learning-object-detection-comprehensive-review.html
© 2021 Deep Netts
YOLO – You Look Only Once
20
• Divides input image into SxS grid
• Each grid cell predicts a specific number of
bounding boxes (B) and confidence scores for
those boxes.
• If the center of an object falls into a grid cell, that
grid cell is responsible for detecting that object.
• Used pretrained convolutional features from
(typically ImageNet)
• Faster, and end-to-end training without region
proposals, compared to faster RCNN
• Has problems with detecting small grouped
objects
See more at: https://pjreddie.com/media/files/papers/yolo_1.pdf
© 2021 Deep Netts
Single Shot Detector - SSD
21
• Uses a fixed set of default bounding boxes
with small convolutional filters
• For each box, both the shape position and
the confidences for all categories are
predicted.
• Uses convolutional network (VGG-16,
ResNet, MobileNet) as feature extractor,
and additional conv layers for object
detection
• Improves speed vs accuracy tradeoff
• Compared to YOLO it is faster but less
accurate for some problems
© 2021 Deep Netts
Summary
• Deep learning is enabling modern computer vision
• The fundamental models to do this are convolutional neural networks
• Image classification is basic computer vision
• Image classification can be extended to object detection
• Tensorflow provides various implementations and pretrained convolutional networks
that can be used for computer vision problems
22
© 2021 Deep Netts
About Deep Netts
• Deep Learning Made Easy for Non-Experts
• Deep Learning IDE and Java Library
• Free For Development
https://www.deepnetts.com/download
• Easy to use, integrate and maintain (lower cost)
• Good accuracy with less data
• No requirements for specialized hardware (GPU)
• Highly portable
23
© 2021 Deep Netts
Resources to get started
24
Deep Learning and image recognition book
https://leonardoaraujosantos.gitbook.io/artificial-
inteligence/machine_learning/deep_learning/object_localization_and_detection
Deep Learning for Object Detection: A Comprehensive Review https://www.kdnuggets.com/2017/10/deep-
learning-object-detection-comprehensive-review.html
Image classification with Convolutional Neural Network in Tensorflow
https://www.tensorflow.org/tutorials/images/cnn
Tensorflow Object Detection API
https://github.com/tensorflow/models/tree/master/research/object_detection

Weitere ähnliche Inhalte

Was ist angesagt?

Introducing google’s mobile nets
Introducing google’s mobile netsIntroducing google’s mobile nets
Introducing google’s mobile netsLarry Guo
 
Computer Vision with Deep Learning
Computer Vision with Deep LearningComputer Vision with Deep Learning
Computer Vision with Deep LearningCapgemini
 
“Secure Hardware Architecture for Embedded Vision,” a Presentation from Neuro...
“Secure Hardware Architecture for Embedded Vision,” a Presentation from Neuro...“Secure Hardware Architecture for Embedded Vision,” a Presentation from Neuro...
“Secure Hardware Architecture for Embedded Vision,” a Presentation from Neuro...Edge AI and Vision Alliance
 
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 VisualizationFITMAN FI
 
Big data 2.0, deep learning and financial Usecases
Big data 2.0, deep learning and financial UsecasesBig data 2.0, deep learning and financial Usecases
Big data 2.0, deep learning and financial UsecasesArvind Rapaka
 
“Once-for-All DNNs: Simplifying Design of Efficient Models for Diverse Hardwa...
“Once-for-All DNNs: Simplifying Design of Efficient Models for Diverse Hardwa...“Once-for-All DNNs: Simplifying Design of Efficient Models for Diverse Hardwa...
“Once-for-All DNNs: Simplifying Design of Efficient Models for Diverse Hardwa...Edge AI and Vision Alliance
 
Single Image Super Resolution Overview
Single Image Super Resolution OverviewSingle Image Super Resolution Overview
Single Image Super Resolution OverviewLEE HOSEONG
 
"High-resolution 3D Reconstruction on a Mobile Processor," a Presentation fro...
"High-resolution 3D Reconstruction on a Mobile Processor," a Presentation fro..."High-resolution 3D Reconstruction on a Mobile Processor," a Presentation fro...
"High-resolution 3D Reconstruction on a Mobile Processor," a Presentation fro...Edge AI and Vision Alliance
 
"Deploying Deep Learning Models on Embedded Processors for Autonomous Systems...
"Deploying Deep Learning Models on Embedded Processors for Autonomous Systems..."Deploying Deep Learning Models on Embedded Processors for Autonomous Systems...
"Deploying Deep Learning Models on Embedded Processors for Autonomous Systems...Edge AI and Vision Alliance
 
Convolutional Neural Network (CNN)
Convolutional Neural Network (CNN)Convolutional Neural Network (CNN)
Convolutional Neural Network (CNN)Muhammad Haroon
 
"Designing Deep Neural Network Algorithms for Embedded Devices," a Presentati...
"Designing Deep Neural Network Algorithms for Embedded Devices," a Presentati..."Designing Deep Neural Network Algorithms for Embedded Devices," a Presentati...
"Designing Deep Neural Network Algorithms for Embedded Devices," a Presentati...Edge AI and Vision Alliance
 
"Optimizing SSD Object Detection for Low-power Devices," a Presentation from ...
"Optimizing SSD Object Detection for Low-power Devices," a Presentation from ..."Optimizing SSD Object Detection for Low-power Devices," a Presentation from ...
"Optimizing SSD Object Detection for Low-power Devices," a Presentation from ...Edge AI and Vision Alliance
 
Improving Hardware Efficiency for DNN Applications
Improving Hardware Efficiency for DNN ApplicationsImproving Hardware Efficiency for DNN Applications
Improving Hardware Efficiency for DNN ApplicationsChester Chen
 
“High-fidelity Conversion of Floating-point Networks for Low-precision Infere...
“High-fidelity Conversion of Floating-point Networks for Low-precision Infere...“High-fidelity Conversion of Floating-point Networks for Low-precision Infere...
“High-fidelity Conversion of Floating-point Networks for Low-precision Infere...Edge AI and Vision Alliance
 
Deep vo and slam iii
Deep vo and slam iiiDeep vo and slam iii
Deep vo and slam iiiYu Huang
 
GTC Taiwan 2017 深度學習於表面瑕疵檢測之應用
GTC Taiwan 2017 深度學習於表面瑕疵檢測之應用GTC Taiwan 2017 深度學習於表面瑕疵檢測之應用
GTC Taiwan 2017 深度學習於表面瑕疵檢測之應用NVIDIA Taiwan
 
“Introduction to the TVM Open Source Deep Learning Compiler Stack,” a Present...
“Introduction to the TVM Open Source Deep Learning Compiler Stack,” a Present...“Introduction to the TVM Open Source Deep Learning Compiler Stack,” a Present...
“Introduction to the TVM Open Source Deep Learning Compiler Stack,” a Present...Edge AI and Vision Alliance
 

Was ist angesagt? (20)

Cross-Year Multi-Modal Image Retrieval Using Siamese Networks by Margarita Kh...
Cross-Year Multi-Modal Image Retrieval Using Siamese Networks by Margarita Kh...Cross-Year Multi-Modal Image Retrieval Using Siamese Networks by Margarita Kh...
Cross-Year Multi-Modal Image Retrieval Using Siamese Networks by Margarita Kh...
 
Introducing google’s mobile nets
Introducing google’s mobile netsIntroducing google’s mobile nets
Introducing google’s mobile nets
 
Computer Vision with Deep Learning
Computer Vision with Deep LearningComputer Vision with Deep Learning
Computer Vision with Deep Learning
 
“Secure Hardware Architecture for Embedded Vision,” a Presentation from Neuro...
“Secure Hardware Architecture for Embedded Vision,” a Presentation from Neuro...“Secure Hardware Architecture for Embedded Vision,” a Presentation from Neuro...
“Secure Hardware Architecture for Embedded Vision,” a Presentation from Neuro...
 
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
 
Big data 2.0, deep learning and financial Usecases
Big data 2.0, deep learning and financial UsecasesBig data 2.0, deep learning and financial Usecases
Big data 2.0, deep learning and financial Usecases
 
“Once-for-All DNNs: Simplifying Design of Efficient Models for Diverse Hardwa...
“Once-for-All DNNs: Simplifying Design of Efficient Models for Diverse Hardwa...“Once-for-All DNNs: Simplifying Design of Efficient Models for Diverse Hardwa...
“Once-for-All DNNs: Simplifying Design of Efficient Models for Diverse Hardwa...
 
Single Image Super Resolution Overview
Single Image Super Resolution OverviewSingle Image Super Resolution Overview
Single Image Super Resolution Overview
 
"High-resolution 3D Reconstruction on a Mobile Processor," a Presentation fro...
"High-resolution 3D Reconstruction on a Mobile Processor," a Presentation fro..."High-resolution 3D Reconstruction on a Mobile Processor," a Presentation fro...
"High-resolution 3D Reconstruction on a Mobile Processor," a Presentation fro...
 
kanimozhi2019.pdf
kanimozhi2019.pdfkanimozhi2019.pdf
kanimozhi2019.pdf
 
CNN Quantization
CNN QuantizationCNN Quantization
CNN Quantization
 
"Deploying Deep Learning Models on Embedded Processors for Autonomous Systems...
"Deploying Deep Learning Models on Embedded Processors for Autonomous Systems..."Deploying Deep Learning Models on Embedded Processors for Autonomous Systems...
"Deploying Deep Learning Models on Embedded Processors for Autonomous Systems...
 
Convolutional Neural Network (CNN)
Convolutional Neural Network (CNN)Convolutional Neural Network (CNN)
Convolutional Neural Network (CNN)
 
"Designing Deep Neural Network Algorithms for Embedded Devices," a Presentati...
"Designing Deep Neural Network Algorithms for Embedded Devices," a Presentati..."Designing Deep Neural Network Algorithms for Embedded Devices," a Presentati...
"Designing Deep Neural Network Algorithms for Embedded Devices," a Presentati...
 
"Optimizing SSD Object Detection for Low-power Devices," a Presentation from ...
"Optimizing SSD Object Detection for Low-power Devices," a Presentation from ..."Optimizing SSD Object Detection for Low-power Devices," a Presentation from ...
"Optimizing SSD Object Detection for Low-power Devices," a Presentation from ...
 
Improving Hardware Efficiency for DNN Applications
Improving Hardware Efficiency for DNN ApplicationsImproving Hardware Efficiency for DNN Applications
Improving Hardware Efficiency for DNN Applications
 
“High-fidelity Conversion of Floating-point Networks for Low-precision Infere...
“High-fidelity Conversion of Floating-point Networks for Low-precision Infere...“High-fidelity Conversion of Floating-point Networks for Low-precision Infere...
“High-fidelity Conversion of Floating-point Networks for Low-precision Infere...
 
Deep vo and slam iii
Deep vo and slam iiiDeep vo and slam iii
Deep vo and slam iii
 
GTC Taiwan 2017 深度學習於表面瑕疵檢測之應用
GTC Taiwan 2017 深度學習於表面瑕疵檢測之應用GTC Taiwan 2017 深度學習於表面瑕疵檢測之應用
GTC Taiwan 2017 深度學習於表面瑕疵檢測之應用
 
“Introduction to the TVM Open Source Deep Learning Compiler Stack,” a Present...
“Introduction to the TVM Open Source Deep Learning Compiler Stack,” a Present...“Introduction to the TVM Open Source Deep Learning Compiler Stack,” a Present...
“Introduction to the TVM Open Source Deep Learning Compiler Stack,” a Present...
 

Ähnlich wie “Modern Machine Vision from Basics to Advanced Deep Learning,” a Presentation from Deep Netts

FINAL_Team_4.pptx
FINAL_Team_4.pptxFINAL_Team_4.pptx
FINAL_Team_4.pptxnitin571047
 
“Tools and Strategies for Quickly Building Effective Image Datasets,” a Prese...
“Tools and Strategies for Quickly Building Effective Image Datasets,” a Prese...“Tools and Strategies for Quickly Building Effective Image Datasets,” a Prese...
“Tools and Strategies for Quickly Building Effective Image Datasets,” a Prese...Edge AI and Vision Alliance
 
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
 
Transfer Learning and Fine-tuning Deep Neural Networks
 Transfer Learning and Fine-tuning Deep Neural Networks Transfer Learning and Fine-tuning Deep Neural Networks
Transfer Learning and Fine-tuning Deep Neural NetworksPyData
 
Makine Öğrenmesi ile Görüntü Tanıma | Image Recognition using Machine Learning
Makine Öğrenmesi ile Görüntü Tanıma | Image Recognition using Machine LearningMakine Öğrenmesi ile Görüntü Tanıma | Image Recognition using Machine Learning
Makine Öğrenmesi ile Görüntü Tanıma | Image Recognition using Machine LearningAli Alkan
 
Computer vision-nit-silchar-hackathon
Computer vision-nit-silchar-hackathonComputer vision-nit-silchar-hackathon
Computer vision-nit-silchar-hackathonAditya Bhattacharya
 
Object Detetcion using SSD-MobileNet
Object Detetcion using SSD-MobileNetObject Detetcion using SSD-MobileNet
Object Detetcion using SSD-MobileNetIRJET Journal
 
Convolutional neural networks 이론과 응용
Convolutional neural networks 이론과 응용Convolutional neural networks 이론과 응용
Convolutional neural networks 이론과 응용홍배 김
 
Deep Neural Networks Presentation
Deep Neural Networks PresentationDeep Neural Networks Presentation
Deep Neural Networks PresentationBohdan Klimenko
 
Computer vision-must-nit-silchar-ml-hackathon-2019
Computer vision-must-nit-silchar-ml-hackathon-2019Computer vision-must-nit-silchar-ml-hackathon-2019
Computer vision-must-nit-silchar-ml-hackathon-2019Aditya Bhattacharya
 
Introduction to computer vision with Convoluted Neural Networks
Introduction to computer vision with Convoluted Neural NetworksIntroduction to computer vision with Convoluted Neural Networks
Introduction to computer vision with Convoluted Neural NetworksMarcinJedyk
 
Introduction to computer vision
Introduction to computer visionIntroduction to computer vision
Introduction to computer visionMarcin Jedyk
 
Learn to Build an App to Find Similar Images using Deep Learning- Piotr Teterwak
Learn to Build an App to Find Similar Images using Deep Learning- Piotr TeterwakLearn to Build an App to Find Similar Images using Deep Learning- Piotr Teterwak
Learn to Build an App to Find Similar Images using Deep Learning- Piotr TeterwakPyData
 
AaSeminar_Template.pptx
AaSeminar_Template.pptxAaSeminar_Template.pptx
AaSeminar_Template.pptxManojGowdaKb
 
MDEC Data Matters Series: machine learning and Deep Learning, A Primer
MDEC Data Matters Series: machine learning and Deep Learning, A PrimerMDEC Data Matters Series: machine learning and Deep Learning, A Primer
MDEC Data Matters Series: machine learning and Deep Learning, A PrimerPoo Kuan Hoong
 
04 Deep CNN (Ch_01 to Ch_3).pptx
04 Deep CNN (Ch_01 to Ch_3).pptx04 Deep CNN (Ch_01 to Ch_3).pptx
04 Deep CNN (Ch_01 to Ch_3).pptxZainULABIDIN496386
 
"Enabling Ubiquitous Visual Intelligence Through Deep Learning," a Keynote Pr...
"Enabling Ubiquitous Visual Intelligence Through Deep Learning," a Keynote Pr..."Enabling Ubiquitous Visual Intelligence Through Deep Learning," a Keynote Pr...
"Enabling Ubiquitous Visual Intelligence Through Deep Learning," a Keynote Pr...Edge AI and Vision Alliance
 
Biometric Recognition using Deep Learning
Biometric Recognition using Deep LearningBiometric Recognition using Deep Learning
Biometric Recognition using Deep LearningSahithiKotha2
 

Ähnlich wie “Modern Machine Vision from Basics to Advanced Deep Learning,” a Presentation from Deep Netts (20)

FINAL_Team_4.pptx
FINAL_Team_4.pptxFINAL_Team_4.pptx
FINAL_Team_4.pptx
 
“Tools and Strategies for Quickly Building Effective Image Datasets,” a Prese...
“Tools and Strategies for Quickly Building Effective Image Datasets,” a Prese...“Tools and Strategies for Quickly Building Effective Image Datasets,” a Prese...
“Tools and Strategies for Quickly Building Effective Image Datasets,” a Prese...
 
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
 
Transfer Learning and Fine-tuning Deep Neural Networks
 Transfer Learning and Fine-tuning Deep Neural Networks Transfer Learning and Fine-tuning Deep Neural Networks
Transfer Learning and Fine-tuning Deep Neural Networks
 
Makine Öğrenmesi ile Görüntü Tanıma | Image Recognition using Machine Learning
Makine Öğrenmesi ile Görüntü Tanıma | Image Recognition using Machine LearningMakine Öğrenmesi ile Görüntü Tanıma | Image Recognition using Machine Learning
Makine Öğrenmesi ile Görüntü Tanıma | Image Recognition using Machine Learning
 
Computer vision-nit-silchar-hackathon
Computer vision-nit-silchar-hackathonComputer vision-nit-silchar-hackathon
Computer vision-nit-silchar-hackathon
 
Deep learning
Deep learning Deep learning
Deep learning
 
Object Detetcion using SSD-MobileNet
Object Detetcion using SSD-MobileNetObject Detetcion using SSD-MobileNet
Object Detetcion using SSD-MobileNet
 
Convolutional neural networks 이론과 응용
Convolutional neural networks 이론과 응용Convolutional neural networks 이론과 응용
Convolutional neural networks 이론과 응용
 
Deep Neural Networks Presentation
Deep Neural Networks PresentationDeep Neural Networks Presentation
Deep Neural Networks Presentation
 
lec6a.ppt
lec6a.pptlec6a.ppt
lec6a.ppt
 
Computer vision-must-nit-silchar-ml-hackathon-2019
Computer vision-must-nit-silchar-ml-hackathon-2019Computer vision-must-nit-silchar-ml-hackathon-2019
Computer vision-must-nit-silchar-ml-hackathon-2019
 
Introduction to computer vision with Convoluted Neural Networks
Introduction to computer vision with Convoluted Neural NetworksIntroduction to computer vision with Convoluted Neural Networks
Introduction to computer vision with Convoluted Neural Networks
 
Introduction to computer vision
Introduction to computer visionIntroduction to computer vision
Introduction to computer vision
 
Learn to Build an App to Find Similar Images using Deep Learning- Piotr Teterwak
Learn to Build an App to Find Similar Images using Deep Learning- Piotr TeterwakLearn to Build an App to Find Similar Images using Deep Learning- Piotr Teterwak
Learn to Build an App to Find Similar Images using Deep Learning- Piotr Teterwak
 
AaSeminar_Template.pptx
AaSeminar_Template.pptxAaSeminar_Template.pptx
AaSeminar_Template.pptx
 
MDEC Data Matters Series: machine learning and Deep Learning, A Primer
MDEC Data Matters Series: machine learning and Deep Learning, A PrimerMDEC Data Matters Series: machine learning and Deep Learning, A Primer
MDEC Data Matters Series: machine learning and Deep Learning, A Primer
 
04 Deep CNN (Ch_01 to Ch_3).pptx
04 Deep CNN (Ch_01 to Ch_3).pptx04 Deep CNN (Ch_01 to Ch_3).pptx
04 Deep CNN (Ch_01 to Ch_3).pptx
 
"Enabling Ubiquitous Visual Intelligence Through Deep Learning," a Keynote Pr...
"Enabling Ubiquitous Visual Intelligence Through Deep Learning," a Keynote Pr..."Enabling Ubiquitous Visual Intelligence Through Deep Learning," a Keynote Pr...
"Enabling Ubiquitous Visual Intelligence Through Deep Learning," a Keynote Pr...
 
Biometric Recognition using Deep Learning
Biometric Recognition using Deep LearningBiometric Recognition using Deep Learning
Biometric Recognition using Deep Learning
 

Mehr von Edge AI and Vision Alliance

“Learning Compact DNN Models for Embedded Vision,” a Presentation from the Un...
“Learning Compact DNN Models for Embedded Vision,” a Presentation from the Un...“Learning Compact DNN Models for Embedded Vision,” a Presentation from the Un...
“Learning Compact DNN Models for Embedded Vision,” a Presentation from the Un...Edge AI and Vision Alliance
 
“Introduction to Computer Vision with CNNs,” a Presentation from Mohammad Hag...
“Introduction to Computer Vision with CNNs,” a Presentation from Mohammad Hag...“Introduction to Computer Vision with CNNs,” a Presentation from Mohammad Hag...
“Introduction to Computer Vision with CNNs,” a Presentation from Mohammad Hag...Edge AI and Vision Alliance
 
“Selecting Tools for Developing, Monitoring and Maintaining ML Models,” a Pre...
“Selecting Tools for Developing, Monitoring and Maintaining ML Models,” a Pre...“Selecting Tools for Developing, Monitoring and Maintaining ML Models,” a Pre...
“Selecting Tools for Developing, Monitoring and Maintaining ML Models,” a Pre...Edge AI and Vision Alliance
 
“Building Accelerated GStreamer Applications for Video and Audio AI,” a Prese...
“Building Accelerated GStreamer Applications for Video and Audio AI,” a Prese...“Building Accelerated GStreamer Applications for Video and Audio AI,” a Prese...
“Building Accelerated GStreamer Applications for Video and Audio AI,” a Prese...Edge AI and Vision Alliance
 
“Understanding, Selecting and Optimizing Object Detectors for Edge Applicatio...
“Understanding, Selecting and Optimizing Object Detectors for Edge Applicatio...“Understanding, Selecting and Optimizing Object Detectors for Edge Applicatio...
“Understanding, Selecting and Optimizing Object Detectors for Edge Applicatio...Edge AI and Vision Alliance
 
“Introduction to Modern LiDAR for Machine Perception,” a Presentation from th...
“Introduction to Modern LiDAR for Machine Perception,” a Presentation from th...“Introduction to Modern LiDAR for Machine Perception,” a Presentation from th...
“Introduction to Modern LiDAR for Machine Perception,” a Presentation from th...Edge AI and Vision Alliance
 
“Vision-language Representations for Robotics,” a Presentation from the Unive...
“Vision-language Representations for Robotics,” a Presentation from the Unive...“Vision-language Representations for Robotics,” a Presentation from the Unive...
“Vision-language Representations for Robotics,” a Presentation from the Unive...Edge AI and Vision Alliance
 
“ADAS and AV Sensors: What’s Winning and Why?,” a Presentation from TechInsights
“ADAS and AV Sensors: What’s Winning and Why?,” a Presentation from TechInsights“ADAS and AV Sensors: What’s Winning and Why?,” a Presentation from TechInsights
“ADAS and AV Sensors: What’s Winning and Why?,” a Presentation from TechInsightsEdge AI and Vision Alliance
 
“Detecting Data Drift in Image Classification Neural Networks,” a Presentatio...
“Detecting Data Drift in Image Classification Neural Networks,” a Presentatio...“Detecting Data Drift in Image Classification Neural Networks,” a Presentatio...
“Detecting Data Drift in Image Classification Neural Networks,” a Presentatio...Edge AI and Vision Alliance
 
“Deep Neural Network Training: Diagnosing Problems and Implementing Solutions...
“Deep Neural Network Training: Diagnosing Problems and Implementing Solutions...“Deep Neural Network Training: Diagnosing Problems and Implementing Solutions...
“Deep Neural Network Training: Diagnosing Problems and Implementing Solutions...Edge AI and Vision Alliance
 
“AI Start-ups: The Perils of Fishing for Whales (War Stories from the Entrepr...
“AI Start-ups: The Perils of Fishing for Whales (War Stories from the Entrepr...“AI Start-ups: The Perils of Fishing for Whales (War Stories from the Entrepr...
“AI Start-ups: The Perils of Fishing for Whales (War Stories from the Entrepr...Edge AI and Vision Alliance
 
“A Computer Vision System for Autonomous Satellite Maneuvering,” a Presentati...
“A Computer Vision System for Autonomous Satellite Maneuvering,” a Presentati...“A Computer Vision System for Autonomous Satellite Maneuvering,” a Presentati...
“A Computer Vision System for Autonomous Satellite Maneuvering,” a Presentati...Edge AI and Vision Alliance
 
“Bias in Computer Vision—It’s Bigger Than Facial Recognition!,” a Presentatio...
“Bias in Computer Vision—It’s Bigger Than Facial Recognition!,” a Presentatio...“Bias in Computer Vision—It’s Bigger Than Facial Recognition!,” a Presentatio...
“Bias in Computer Vision—It’s Bigger Than Facial Recognition!,” a Presentatio...Edge AI and Vision Alliance
 
“Sensor Fusion Techniques for Accurate Perception of Objects in the Environme...
“Sensor Fusion Techniques for Accurate Perception of Objects in the Environme...“Sensor Fusion Techniques for Accurate Perception of Objects in the Environme...
“Sensor Fusion Techniques for Accurate Perception of Objects in the Environme...Edge AI and Vision Alliance
 
“Combating Bias in Production Computer Vision Systems,” a Presentation from R...
“Combating Bias in Production Computer Vision Systems,” a Presentation from R...“Combating Bias in Production Computer Vision Systems,” a Presentation from R...
“Combating Bias in Production Computer Vision Systems,” a Presentation from R...Edge AI and Vision Alliance
 
“Developing an Embedded Vision AI-powered Fitness System,” a Presentation fro...
“Developing an Embedded Vision AI-powered Fitness System,” a Presentation fro...“Developing an Embedded Vision AI-powered Fitness System,” a Presentation fro...
“Developing an Embedded Vision AI-powered Fitness System,” a Presentation fro...Edge AI and Vision Alliance
 
“Navigating the Evolving Venture Capital Landscape for Edge AI Start-ups,” a ...
“Navigating the Evolving Venture Capital Landscape for Edge AI Start-ups,” a ...“Navigating the Evolving Venture Capital Landscape for Edge AI Start-ups,” a ...
“Navigating the Evolving Venture Capital Landscape for Edge AI Start-ups,” a ...Edge AI and Vision Alliance
 
“Advanced Presence Sensing: What It Means for the Smart Home,” a Presentation...
“Advanced Presence Sensing: What It Means for the Smart Home,” a Presentation...“Advanced Presence Sensing: What It Means for the Smart Home,” a Presentation...
“Advanced Presence Sensing: What It Means for the Smart Home,” a Presentation...Edge AI and Vision Alliance
 
“Tracking and Fusing Diverse Risk Factors to Drive a SAFER Future,” a Present...
“Tracking and Fusing Diverse Risk Factors to Drive a SAFER Future,” a Present...“Tracking and Fusing Diverse Risk Factors to Drive a SAFER Future,” a Present...
“Tracking and Fusing Diverse Risk Factors to Drive a SAFER Future,” a Present...Edge AI and Vision Alliance
 
“MIPI CSI-2 Image Sensor Interface Standard Features Enable Efficient Embedde...
“MIPI CSI-2 Image Sensor Interface Standard Features Enable Efficient Embedde...“MIPI CSI-2 Image Sensor Interface Standard Features Enable Efficient Embedde...
“MIPI CSI-2 Image Sensor Interface Standard Features Enable Efficient Embedde...Edge AI and Vision Alliance
 

Mehr von Edge AI and Vision Alliance (20)

“Learning Compact DNN Models for Embedded Vision,” a Presentation from the Un...
“Learning Compact DNN Models for Embedded Vision,” a Presentation from the Un...“Learning Compact DNN Models for Embedded Vision,” a Presentation from the Un...
“Learning Compact DNN Models for Embedded Vision,” a Presentation from the Un...
 
“Introduction to Computer Vision with CNNs,” a Presentation from Mohammad Hag...
“Introduction to Computer Vision with CNNs,” a Presentation from Mohammad Hag...“Introduction to Computer Vision with CNNs,” a Presentation from Mohammad Hag...
“Introduction to Computer Vision with CNNs,” a Presentation from Mohammad Hag...
 
“Selecting Tools for Developing, Monitoring and Maintaining ML Models,” a Pre...
“Selecting Tools for Developing, Monitoring and Maintaining ML Models,” a Pre...“Selecting Tools for Developing, Monitoring and Maintaining ML Models,” a Pre...
“Selecting Tools for Developing, Monitoring and Maintaining ML Models,” a Pre...
 
“Building Accelerated GStreamer Applications for Video and Audio AI,” a Prese...
“Building Accelerated GStreamer Applications for Video and Audio AI,” a Prese...“Building Accelerated GStreamer Applications for Video and Audio AI,” a Prese...
“Building Accelerated GStreamer Applications for Video and Audio AI,” a Prese...
 
“Understanding, Selecting and Optimizing Object Detectors for Edge Applicatio...
“Understanding, Selecting and Optimizing Object Detectors for Edge Applicatio...“Understanding, Selecting and Optimizing Object Detectors for Edge Applicatio...
“Understanding, Selecting and Optimizing Object Detectors for Edge Applicatio...
 
“Introduction to Modern LiDAR for Machine Perception,” a Presentation from th...
“Introduction to Modern LiDAR for Machine Perception,” a Presentation from th...“Introduction to Modern LiDAR for Machine Perception,” a Presentation from th...
“Introduction to Modern LiDAR for Machine Perception,” a Presentation from th...
 
“Vision-language Representations for Robotics,” a Presentation from the Unive...
“Vision-language Representations for Robotics,” a Presentation from the Unive...“Vision-language Representations for Robotics,” a Presentation from the Unive...
“Vision-language Representations for Robotics,” a Presentation from the Unive...
 
“ADAS and AV Sensors: What’s Winning and Why?,” a Presentation from TechInsights
“ADAS and AV Sensors: What’s Winning and Why?,” a Presentation from TechInsights“ADAS and AV Sensors: What’s Winning and Why?,” a Presentation from TechInsights
“ADAS and AV Sensors: What’s Winning and Why?,” a Presentation from TechInsights
 
“Detecting Data Drift in Image Classification Neural Networks,” a Presentatio...
“Detecting Data Drift in Image Classification Neural Networks,” a Presentatio...“Detecting Data Drift in Image Classification Neural Networks,” a Presentatio...
“Detecting Data Drift in Image Classification Neural Networks,” a Presentatio...
 
“Deep Neural Network Training: Diagnosing Problems and Implementing Solutions...
“Deep Neural Network Training: Diagnosing Problems and Implementing Solutions...“Deep Neural Network Training: Diagnosing Problems and Implementing Solutions...
“Deep Neural Network Training: Diagnosing Problems and Implementing Solutions...
 
“AI Start-ups: The Perils of Fishing for Whales (War Stories from the Entrepr...
“AI Start-ups: The Perils of Fishing for Whales (War Stories from the Entrepr...“AI Start-ups: The Perils of Fishing for Whales (War Stories from the Entrepr...
“AI Start-ups: The Perils of Fishing for Whales (War Stories from the Entrepr...
 
“A Computer Vision System for Autonomous Satellite Maneuvering,” a Presentati...
“A Computer Vision System for Autonomous Satellite Maneuvering,” a Presentati...“A Computer Vision System for Autonomous Satellite Maneuvering,” a Presentati...
“A Computer Vision System for Autonomous Satellite Maneuvering,” a Presentati...
 
“Bias in Computer Vision—It’s Bigger Than Facial Recognition!,” a Presentatio...
“Bias in Computer Vision—It’s Bigger Than Facial Recognition!,” a Presentatio...“Bias in Computer Vision—It’s Bigger Than Facial Recognition!,” a Presentatio...
“Bias in Computer Vision—It’s Bigger Than Facial Recognition!,” a Presentatio...
 
“Sensor Fusion Techniques for Accurate Perception of Objects in the Environme...
“Sensor Fusion Techniques for Accurate Perception of Objects in the Environme...“Sensor Fusion Techniques for Accurate Perception of Objects in the Environme...
“Sensor Fusion Techniques for Accurate Perception of Objects in the Environme...
 
“Combating Bias in Production Computer Vision Systems,” a Presentation from R...
“Combating Bias in Production Computer Vision Systems,” a Presentation from R...“Combating Bias in Production Computer Vision Systems,” a Presentation from R...
“Combating Bias in Production Computer Vision Systems,” a Presentation from R...
 
“Developing an Embedded Vision AI-powered Fitness System,” a Presentation fro...
“Developing an Embedded Vision AI-powered Fitness System,” a Presentation fro...“Developing an Embedded Vision AI-powered Fitness System,” a Presentation fro...
“Developing an Embedded Vision AI-powered Fitness System,” a Presentation fro...
 
“Navigating the Evolving Venture Capital Landscape for Edge AI Start-ups,” a ...
“Navigating the Evolving Venture Capital Landscape for Edge AI Start-ups,” a ...“Navigating the Evolving Venture Capital Landscape for Edge AI Start-ups,” a ...
“Navigating the Evolving Venture Capital Landscape for Edge AI Start-ups,” a ...
 
“Advanced Presence Sensing: What It Means for the Smart Home,” a Presentation...
“Advanced Presence Sensing: What It Means for the Smart Home,” a Presentation...“Advanced Presence Sensing: What It Means for the Smart Home,” a Presentation...
“Advanced Presence Sensing: What It Means for the Smart Home,” a Presentation...
 
“Tracking and Fusing Diverse Risk Factors to Drive a SAFER Future,” a Present...
“Tracking and Fusing Diverse Risk Factors to Drive a SAFER Future,” a Present...“Tracking and Fusing Diverse Risk Factors to Drive a SAFER Future,” a Present...
“Tracking and Fusing Diverse Risk Factors to Drive a SAFER Future,” a Present...
 
“MIPI CSI-2 Image Sensor Interface Standard Features Enable Efficient Embedde...
“MIPI CSI-2 Image Sensor Interface Standard Features Enable Efficient Embedde...“MIPI CSI-2 Image Sensor Interface Standard Features Enable Efficient Embedde...
“MIPI CSI-2 Image Sensor Interface Standard Features Enable Efficient Embedde...
 

Kürzlich hochgeladen

KubeConEU24-Monitoring Kubernetes and Cloud Spend with OpenCost
KubeConEU24-Monitoring Kubernetes and Cloud Spend with OpenCostKubeConEU24-Monitoring Kubernetes and Cloud Spend with OpenCost
KubeConEU24-Monitoring Kubernetes and Cloud Spend with OpenCostMatt Ray
 
Cybersecurity Workshop #1.pptx
Cybersecurity Workshop #1.pptxCybersecurity Workshop #1.pptx
Cybersecurity Workshop #1.pptxGDSC PJATK
 
Introduction to Matsuo Laboratory (ENG).pptx
Introduction to Matsuo Laboratory (ENG).pptxIntroduction to Matsuo Laboratory (ENG).pptx
Introduction to Matsuo Laboratory (ENG).pptxMatsuo Lab
 
UiPath Studio Web workshop series - Day 6
UiPath Studio Web workshop series - Day 6UiPath Studio Web workshop series - Day 6
UiPath Studio Web workshop series - Day 6DianaGray10
 
UiPath Studio Web workshop series - Day 8
UiPath Studio Web workshop series - Day 8UiPath Studio Web workshop series - Day 8
UiPath Studio Web workshop series - Day 8DianaGray10
 
Nanopower In Semiconductor Industry.pdf
Nanopower  In Semiconductor Industry.pdfNanopower  In Semiconductor Industry.pdf
Nanopower In Semiconductor Industry.pdfPedro Manuel
 
Secure your environment with UiPath and CyberArk technologies - Session 1
Secure your environment with UiPath and CyberArk technologies - Session 1Secure your environment with UiPath and CyberArk technologies - Session 1
Secure your environment with UiPath and CyberArk technologies - Session 1DianaGray10
 
Igniting Next Level Productivity with AI-Infused Data Integration Workflows
Igniting Next Level Productivity with AI-Infused Data Integration WorkflowsIgniting Next Level Productivity with AI-Infused Data Integration Workflows
Igniting Next Level Productivity with AI-Infused Data Integration WorkflowsSafe Software
 
Building AI-Driven Apps Using Semantic Kernel.pptx
Building AI-Driven Apps Using Semantic Kernel.pptxBuilding AI-Driven Apps Using Semantic Kernel.pptx
Building AI-Driven Apps Using Semantic Kernel.pptxUdaiappa Ramachandran
 
Apres-Cyber - The Data Dilemma: Bridging Offensive Operations and Machine Lea...
Apres-Cyber - The Data Dilemma: Bridging Offensive Operations and Machine Lea...Apres-Cyber - The Data Dilemma: Bridging Offensive Operations and Machine Lea...
Apres-Cyber - The Data Dilemma: Bridging Offensive Operations and Machine Lea...Will Schroeder
 
ADOPTING WEB 3 FOR YOUR BUSINESS: A STEP-BY-STEP GUIDE
ADOPTING WEB 3 FOR YOUR BUSINESS: A STEP-BY-STEP GUIDEADOPTING WEB 3 FOR YOUR BUSINESS: A STEP-BY-STEP GUIDE
ADOPTING WEB 3 FOR YOUR BUSINESS: A STEP-BY-STEP GUIDELiveplex
 
Crea il tuo assistente AI con lo Stregatto (open source python framework)
Crea il tuo assistente AI con lo Stregatto (open source python framework)Crea il tuo assistente AI con lo Stregatto (open source python framework)
Crea il tuo assistente AI con lo Stregatto (open source python framework)Commit University
 
UiPath Platform: The Backend Engine Powering Your Automation - Session 1
UiPath Platform: The Backend Engine Powering Your Automation - Session 1UiPath Platform: The Backend Engine Powering Your Automation - Session 1
UiPath Platform: The Backend Engine Powering Your Automation - Session 1DianaGray10
 
Basic Building Blocks of Internet of Things.
Basic Building Blocks of Internet of Things.Basic Building Blocks of Internet of Things.
Basic Building Blocks of Internet of Things.YounusS2
 
Meet the new FSP 3000 M-Flex800™
Meet the new FSP 3000 M-Flex800™Meet the new FSP 3000 M-Flex800™
Meet the new FSP 3000 M-Flex800™Adtran
 
UiPath Solutions Management Preview - Northern CA Chapter - March 22.pdf
UiPath Solutions Management Preview - Northern CA Chapter - March 22.pdfUiPath Solutions Management Preview - Northern CA Chapter - March 22.pdf
UiPath Solutions Management Preview - Northern CA Chapter - March 22.pdfDianaGray10
 
NIST Cybersecurity Framework (CSF) 2.0 Workshop
NIST Cybersecurity Framework (CSF) 2.0 WorkshopNIST Cybersecurity Framework (CSF) 2.0 Workshop
NIST Cybersecurity Framework (CSF) 2.0 WorkshopBachir Benyammi
 
Machine Learning Model Validation (Aijun Zhang 2024).pdf
Machine Learning Model Validation (Aijun Zhang 2024).pdfMachine Learning Model Validation (Aijun Zhang 2024).pdf
Machine Learning Model Validation (Aijun Zhang 2024).pdfAijun Zhang
 
Artificial Intelligence & SEO Trends for 2024
Artificial Intelligence & SEO Trends for 2024Artificial Intelligence & SEO Trends for 2024
Artificial Intelligence & SEO Trends for 2024D Cloud Solutions
 
Videogame localization & technology_ how to enhance the power of translation.pdf
Videogame localization & technology_ how to enhance the power of translation.pdfVideogame localization & technology_ how to enhance the power of translation.pdf
Videogame localization & technology_ how to enhance the power of translation.pdfinfogdgmi
 

Kürzlich hochgeladen (20)

KubeConEU24-Monitoring Kubernetes and Cloud Spend with OpenCost
KubeConEU24-Monitoring Kubernetes and Cloud Spend with OpenCostKubeConEU24-Monitoring Kubernetes and Cloud Spend with OpenCost
KubeConEU24-Monitoring Kubernetes and Cloud Spend with OpenCost
 
Cybersecurity Workshop #1.pptx
Cybersecurity Workshop #1.pptxCybersecurity Workshop #1.pptx
Cybersecurity Workshop #1.pptx
 
Introduction to Matsuo Laboratory (ENG).pptx
Introduction to Matsuo Laboratory (ENG).pptxIntroduction to Matsuo Laboratory (ENG).pptx
Introduction to Matsuo Laboratory (ENG).pptx
 
UiPath Studio Web workshop series - Day 6
UiPath Studio Web workshop series - Day 6UiPath Studio Web workshop series - Day 6
UiPath Studio Web workshop series - Day 6
 
UiPath Studio Web workshop series - Day 8
UiPath Studio Web workshop series - Day 8UiPath Studio Web workshop series - Day 8
UiPath Studio Web workshop series - Day 8
 
Nanopower In Semiconductor Industry.pdf
Nanopower  In Semiconductor Industry.pdfNanopower  In Semiconductor Industry.pdf
Nanopower In Semiconductor Industry.pdf
 
Secure your environment with UiPath and CyberArk technologies - Session 1
Secure your environment with UiPath and CyberArk technologies - Session 1Secure your environment with UiPath and CyberArk technologies - Session 1
Secure your environment with UiPath and CyberArk technologies - Session 1
 
Igniting Next Level Productivity with AI-Infused Data Integration Workflows
Igniting Next Level Productivity with AI-Infused Data Integration WorkflowsIgniting Next Level Productivity with AI-Infused Data Integration Workflows
Igniting Next Level Productivity with AI-Infused Data Integration Workflows
 
Building AI-Driven Apps Using Semantic Kernel.pptx
Building AI-Driven Apps Using Semantic Kernel.pptxBuilding AI-Driven Apps Using Semantic Kernel.pptx
Building AI-Driven Apps Using Semantic Kernel.pptx
 
Apres-Cyber - The Data Dilemma: Bridging Offensive Operations and Machine Lea...
Apres-Cyber - The Data Dilemma: Bridging Offensive Operations and Machine Lea...Apres-Cyber - The Data Dilemma: Bridging Offensive Operations and Machine Lea...
Apres-Cyber - The Data Dilemma: Bridging Offensive Operations and Machine Lea...
 
ADOPTING WEB 3 FOR YOUR BUSINESS: A STEP-BY-STEP GUIDE
ADOPTING WEB 3 FOR YOUR BUSINESS: A STEP-BY-STEP GUIDEADOPTING WEB 3 FOR YOUR BUSINESS: A STEP-BY-STEP GUIDE
ADOPTING WEB 3 FOR YOUR BUSINESS: A STEP-BY-STEP GUIDE
 
Crea il tuo assistente AI con lo Stregatto (open source python framework)
Crea il tuo assistente AI con lo Stregatto (open source python framework)Crea il tuo assistente AI con lo Stregatto (open source python framework)
Crea il tuo assistente AI con lo Stregatto (open source python framework)
 
UiPath Platform: The Backend Engine Powering Your Automation - Session 1
UiPath Platform: The Backend Engine Powering Your Automation - Session 1UiPath Platform: The Backend Engine Powering Your Automation - Session 1
UiPath Platform: The Backend Engine Powering Your Automation - Session 1
 
Basic Building Blocks of Internet of Things.
Basic Building Blocks of Internet of Things.Basic Building Blocks of Internet of Things.
Basic Building Blocks of Internet of Things.
 
Meet the new FSP 3000 M-Flex800™
Meet the new FSP 3000 M-Flex800™Meet the new FSP 3000 M-Flex800™
Meet the new FSP 3000 M-Flex800™
 
UiPath Solutions Management Preview - Northern CA Chapter - March 22.pdf
UiPath Solutions Management Preview - Northern CA Chapter - March 22.pdfUiPath Solutions Management Preview - Northern CA Chapter - March 22.pdf
UiPath Solutions Management Preview - Northern CA Chapter - March 22.pdf
 
NIST Cybersecurity Framework (CSF) 2.0 Workshop
NIST Cybersecurity Framework (CSF) 2.0 WorkshopNIST Cybersecurity Framework (CSF) 2.0 Workshop
NIST Cybersecurity Framework (CSF) 2.0 Workshop
 
Machine Learning Model Validation (Aijun Zhang 2024).pdf
Machine Learning Model Validation (Aijun Zhang 2024).pdfMachine Learning Model Validation (Aijun Zhang 2024).pdf
Machine Learning Model Validation (Aijun Zhang 2024).pdf
 
Artificial Intelligence & SEO Trends for 2024
Artificial Intelligence & SEO Trends for 2024Artificial Intelligence & SEO Trends for 2024
Artificial Intelligence & SEO Trends for 2024
 
Videogame localization & technology_ how to enhance the power of translation.pdf
Videogame localization & technology_ how to enhance the power of translation.pdfVideogame localization & technology_ how to enhance the power of translation.pdf
Videogame localization & technology_ how to enhance the power of translation.pdf
 

“Modern Machine Vision from Basics to Advanced Deep Learning,” a Presentation from Deep Netts

  • 1. © 2021 Deep Netts Modern Machine Vision from Basics to Advanced Deep Learning Zoran Sevarac University Of Belgrade / Deep Netts
  • 2. © 2021 Deep Netts What are you going to learn • Machine learning basic ideas • Deep learning, and what’s so special about it • How to use deep learning for image classification • Advanced deep learning models for object detection 2
  • 4. © 2021 Deep Netts What is Machine Learning? • Type of computer algorithm that is capable to automatically configure its internal parameters (learn) by looking at a set of examples given as a data set, in order to perform specific task on similar data with usable accuracy. • Examples of what it can do : • Learn to assign items to category - classification • Learn relationship between variables, in order to estimate a numeric value - regression 4
  • 5. © 2021 Deep Netts Deep Learning • Advanced machine learning technique • Higher accuracy with more data • Successful in solving vision-based problems, and in general problems with lots of inputs. • Automates manual feature extraction commonly used for image classification in traditional machine learning • Breakthrough in image recognition, and natural language processing 5 Source: https://machinelearningmastery.com/what-is- deep-learning/ https://www.slideshare.net/NVIDIA/nvidia-ces- 2016-press-conference
  • 6. © 2021 Deep Netts Shallow vs Deep Learning https://www.frontiersin.org/articles/10.3389/fninf.2019.00053/full 6 https://www.linkedin.com/pulse/introduction-shallow-machine-learning-ayman-mahmoud/
  • 7. Deep Learning / Neural Networks
  • 8. © 2021 Deep Netts Feed Forward Neural Network • Nodes are grouped into layers that determine the order of execution/computation. • Each node performs computation based on its inputs and set of weight coefficients. • Learning is based on error minimization of total network error for given data set. • Can be use for both classification and regression tasks 8
  • 9. © 2021 Deep Netts Supervised Training Procedure 9 Neural Network Training Data Components for training a network: • Network • Training data • Optimizer • Testing data
  • 10. © 2021 Deep Netts From Image Classification to Object Detection • Image Classification – assign an image into one of many different categories • Object Localization – determine the location of a single object within image • Object Detection – localizing and classifying multiple objects within image 10 Image Source: https://leonardoaraujosantos.gitbook.io
  • 11. © 2021 Deep Netts Convolutional Neural Networks and Image Classification • Extension of a feed forward network specialized for image classification/recognition • Introduces convolutional layers with adaptive image filters capable for learning and detecting shape and color features • Reduces image preprocessing and feature extraction – now it’s learned during the training 11
  • 12. © 2021 Deep Netts Convolution - the Magic of Convolutional Layer 12 Image source: https://towardsdatascience.com/a-comprehensive-guide-to-convolutional-neural-networks-the-eli5-way-3bd2b1164a53 Convolution operation is sliding small matrix (filter) over input pixels
  • 13. © 2021 Deep Netts Types of Layers in CNN • Convolutional Layer – performs feature detection • Max Pooling Layer – scales down input images • Fully Connected Layer – performs classification • Softmax Layer – estimates probability for categories • Linear Layer – performs regression, estimates object position • Dropout Layer – reduces overfitting 13
  • 14. © 2021 Deep Netts Multiple Layers Combined : Image Classification Using CNN 14 Image source: https://developer.nvidia.com/discover/convolutional-neural-network
  • 15. © 2021 Deep Netts Common CNN Architectures • VGG Net: 16 or 19 layers, 3x3 conv filters • ResNet: skip connections enable deeper networks • InceptionNet: concatenates filters of different sizes 3x3, 5x5, 1x1 • Mobile Net: depthwise separable convolutions, and thinner more efficient networks 15 Residual/skip connections Filter concatenation
  • 16. © 2021 Deep Netts Quick Overview of the Evolution of Object Detection • Convolutional Network for Object Detection • Region-based Convolutional Neural Network (RCNN) • Fast RCNN • Faster RCNN • You Look Only Once - YOLO • Single Shot Detector – SSD • Convolutional network for image classification + Regression for determining the position 16
  • 17. © 2021 Deep Netts Region-based Convolutional Neural Network • Generate about 2000 region proposals from input image using the Selective Search • Run a convolutional net to classify each region proposal • Intuitive but slow 17
  • 18. © 2021 Deep Netts Fast R-CNN • In order to reduce computation region proposals are generated from the last convolutional layer, not from the original image. • The computationally expensive convolutional layers are calculated only once. • Still using selective search for region proposals 18 Image source: https://www.kdnuggets.com/2017/10/deep-learning-object- detection-comprehensive-review.html
  • 19. © 2021 Deep Netts Faster RCNN • Introduced region proposal network instead of selective search: does the region contain object? 19 Image source: https://www.kdnuggets.com/2017/10/deep- learning-object-detection-comprehensive-review.html
  • 20. © 2021 Deep Netts YOLO – You Look Only Once 20 • Divides input image into SxS grid • Each grid cell predicts a specific number of bounding boxes (B) and confidence scores for those boxes. • If the center of an object falls into a grid cell, that grid cell is responsible for detecting that object. • Used pretrained convolutional features from (typically ImageNet) • Faster, and end-to-end training without region proposals, compared to faster RCNN • Has problems with detecting small grouped objects See more at: https://pjreddie.com/media/files/papers/yolo_1.pdf
  • 21. © 2021 Deep Netts Single Shot Detector - SSD 21 • Uses a fixed set of default bounding boxes with small convolutional filters • For each box, both the shape position and the confidences for all categories are predicted. • Uses convolutional network (VGG-16, ResNet, MobileNet) as feature extractor, and additional conv layers for object detection • Improves speed vs accuracy tradeoff • Compared to YOLO it is faster but less accurate for some problems
  • 22. © 2021 Deep Netts Summary • Deep learning is enabling modern computer vision • The fundamental models to do this are convolutional neural networks • Image classification is basic computer vision • Image classification can be extended to object detection • Tensorflow provides various implementations and pretrained convolutional networks that can be used for computer vision problems 22
  • 23. © 2021 Deep Netts About Deep Netts • Deep Learning Made Easy for Non-Experts • Deep Learning IDE and Java Library • Free For Development https://www.deepnetts.com/download • Easy to use, integrate and maintain (lower cost) • Good accuracy with less data • No requirements for specialized hardware (GPU) • Highly portable 23
  • 24. © 2021 Deep Netts Resources to get started 24 Deep Learning and image recognition book https://leonardoaraujosantos.gitbook.io/artificial- inteligence/machine_learning/deep_learning/object_localization_and_detection Deep Learning for Object Detection: A Comprehensive Review https://www.kdnuggets.com/2017/10/deep- learning-object-detection-comprehensive-review.html Image classification with Convolutional Neural Network in Tensorflow https://www.tensorflow.org/tutorials/images/cnn Tensorflow Object Detection API https://github.com/tensorflow/models/tree/master/research/object_detection