SlideShare uma empresa Scribd logo

Object Detection using Deep Neural Networks

•Transferir como PPTX, PDF•
•
U
Usman Qayyum

Recent Talk at PI school covering following contents Object Detection Recent Architecture of Deep NN for Object Detection Object Detection on Embedded Computers (or for edge computing) SqueezeNet for embedded computing TinySSD (object detection for edge computing)

Educação
1 de 31
1 Object Detection By Usman Qayyum 4, Dec, 2018
Talk Covers Three Papers (Object Detection -> Embedded Computing) 2 SqueezeNet-2016SSD-2016 TinySSD-2018 =+
Image Classification/Object Detection ● Autonomous vehicles, smart video surveillance, facial detection and various applications, fast and robust object detection is need of an hour ● Nonly recognizing and classifying every object in an image, but localizing each one by drawing the appropriate bounding box around it. 3
CNN Migration (Image Classification) 4
Object Detection as Classification CNN deer? cat? background?
Object Detection as Classification CNN deer? cat? background?
Object Detection as Classification CNN deer? cat? background?
Object Detection as Classification with Sliding Window CNN deer? cat? background?
Object Detection as Classification with Box Proposals
Box Proposal Method : Selective Search Segmentation As Selective Search for Object Recognition. van de Sande et al. ICCV 2011
Idea behind Object Detectors ● Box Proposals ● Classifier Algorithm 11
RCNN Rich feature hierarchies for accurate object detection and semantic segmentation. Girshick et al. CVPR 2014. https://people.eecs.berkeley.edu/~rbg/papers/r-cnn-cvpr.pdf
Fast-RCNN Fast R-CNN. Girshick. ICCV 2015. https://arxiv.org/abs/1504.08083 Idea: No need to recompute features for every box independently, Regress refined bounding box coordinates.
Faster-RCNN Ren et al. NIPS 2015. https://arxiv.org/abs/1506.01497 Idea: Integrate the Bounding Box Propos als as part of the CNN predictions
YOLO- You Only Look Once ● Single Shot Detector Redmon et al. CVPR 2016. https://arxiv.org/abs/1506.02640 Idea: No bounding box proposals. Predict a class and a box for every location in a grid.
SSD: Single Shot Detector Liu et al. ECCV 2016. Idea: Similar to YOLO, but denser grid map, multiscale grid maps. + Data augm entation + Hard negative mining + Other design choices in the network.
-The overall objective loss function is a weighted sum of the localization loss and the confidence loss(conf) N: the number of matched default boxes l: predicted boxes g: the ground truth box x=1 denotes some certain default box is matched to a ground truth box17 1 ( , , , ) ( ( , ) ( , , ))conf locL x c l g L x c L x l g N   SSD: Single Shot Detector
Performance 18
Accuracy Vs Computation 19
AI Workload Migration Embedded (Mobile/Edge) Server/Clou d Execution/Inference Training Execution/Inference Intelligence & Analytics Key Use Cases Vision | Audio | Security Benefits Low Latency | Privacy
AI in Embedded Devices 21
How ? (AI in Embedded Devices) Pruning Quantization22
SqueezeNet (Parameter Reduction) ● Strategy 1. Replace 3x3 filters with 1x1 filters ○ Parameters per filter: (3x3 filter) = 9 * (1x1 filter) ● Strategy 2. Decrease the number of input channels to 3x3 filters ○ Total # of parameters: (# of input channels) * (# of filters) * ( # of parameters per filter) ● Strategy 3. Downsample late in the network so that convolution layers have large activation maps ○ Size of activation maps: the size of input data, the choice of layers in which to downsample in the CNN architecture 23 Iandola, Forrest N., et al. "SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and< 0.5 MB model size."
Strategy#1 Conv1x1 or Kernel Reduction 24
Microarchitecture – Fire Module 25 Squeeze Layer Set s1x1 < (e1x1 + e3x3), limits the # of input channels to 3*3 filters Strategy 2. Decrease the number of input channels to 3x3 filters Total # of parameters: (# of input channels) * (# of filters) * ( # of parameters per filter) How much can we limit s1x1? Strategy 1. Replace 3*3 filters with 1*1 filters Parameters per filter: (3*3 filter) = 9 * (1*1 filter) How much can we replace 3*3 with 1*1? (e1x1 vs e3x3 )?
Expand ● In the "expand" modules, what are the tradeoffs when we turn the knob between mostly 1x1 and mostly 3x3 filters? ● Hypothesis: if having more weights leads to higher accuracy, then having all 3x3 filters should give the highest accuracy 27
28
Macroarchitecture 29 Strategy 3. Downsample late in the network so that convolution layers have large activation maps Size of activation maps: the size of input data, the choice of layers in which to downsample in the CNN architecture
Performance 30
TinySSD (SSD with Microarchitecture) 31
Thanks for your attention. 32

Recomendados

Object detection with deep learning
Object detection with deep learningObject detection with deep learning
Object detection with deep learningSushant Shrivastava
 
A Brief History of Object Detection / Tommi Kerola
A Brief History of Object Detection / Tommi KerolaA Brief History of Object Detection / Tommi Kerola
A Brief History of Object Detection / Tommi KerolaPreferred Networks
 
Deep learning for object detection
Deep learning for object detectionDeep learning for object detection
Deep learning for object detectionWenjing Chen
 
Introduction to object detection
Introduction to object detectionIntroduction to object detection
Introduction to object detectionBrodmann17
 
Deep learning based object detection basics
Deep learning based object detection basicsDeep learning based object detection basics
Deep learning based object detection basicsBrodmann17
 
You only look once (YOLO) : unified real time object detection
You only look once (YOLO) : unified real time object detectionYou only look once (YOLO) : unified real time object detection
You only look once (YOLO) : unified real time object detectionEntrepreneur / Startup
 
You only look once: Unified, real-time object detection (UPC Reading Group)
You only look once: Unified, real-time object detection (UPC Reading Group)You only look once: Unified, real-time object detection (UPC Reading Group)
You only look once: Unified, real-time object detection (UPC Reading Group)Universitat Politècnica de Catalunya
 
Object detection
Object detectionObject detection
Object detectionJksuryawanshi
 

Recomendados

Object detection with deep learning
Object detection with deep learningObject detection with deep learning
Object detection with deep learningSushant Shrivastava
 
A Brief History of Object Detection / Tommi Kerola
A Brief History of Object Detection / Tommi KerolaA Brief History of Object Detection / Tommi Kerola
A Brief History of Object Detection / Tommi KerolaPreferred Networks
 
Deep learning for object detection
Deep learning for object detectionDeep learning for object detection
Deep learning for object detectionWenjing Chen
 
Introduction to object detection
Introduction to object detectionIntroduction to object detection
Introduction to object detectionBrodmann17
 
Deep learning based object detection basics
Deep learning based object detection basicsDeep learning based object detection basics
Deep learning based object detection basicsBrodmann17
 
You only look once (YOLO) : unified real time object detection
You only look once (YOLO) : unified real time object detectionYou only look once (YOLO) : unified real time object detection
You only look once (YOLO) : unified real time object detectionEntrepreneur / Startup
 
You only look once: Unified, real-time object detection (UPC Reading Group)
You only look once: Unified, real-time object detection (UPC Reading Group)You only look once: Unified, real-time object detection (UPC Reading Group)
You only look once: Unified, real-time object detection (UPC Reading Group)Universitat Politècnica de Catalunya
 
Object detection
Object detectionObject detection
Object detectionJksuryawanshi
 
Machine Learning - Object Detection and Classification
Machine Learning - Object Detection and ClassificationMachine Learning - Object Detection and Classification
Machine Learning - Object Detection and ClassificationVikas Jain
 
Object detection
Object detectionObject detection
Object detectionROUSHAN RAJ KUMAR
 
[PR12] You Only Look Once (YOLO): Unified Real-Time Object Detection
[PR12] You Only Look Once (YOLO): Unified Real-Time Object Detection[PR12] You Only Look Once (YOLO): Unified Real-Time Object Detection
[PR12] You Only Look Once (YOLO): Unified Real-Time Object DetectionTaegyun Jeon
 
Real Time Object Tracking
Real Time Object TrackingReal Time Object Tracking
Real Time Object TrackingVanya Valindria
 
Deep learning based object detection
Deep learning based object detectionDeep learning based object detection
Deep learning based object detectionchettykulkarni
 
Multi Object Tracking | Presentation 1 | ID 103001
Multi Object Tracking | Presentation 1 | ID 103001Multi Object Tracking | Presentation 1 | ID 103001
Multi Object Tracking | Presentation 1 | ID 103001Md. Minhazul Haque
 
Object Detection Using R-CNN Deep Learning Framework
Object Detection Using R-CNN Deep Learning FrameworkObject Detection Using R-CNN Deep Learning Framework
Object Detection Using R-CNN Deep Learning FrameworkNader Karimi
 
You Only Look Once: Unified, Real-Time Object Detection
You Only Look Once: Unified, Real-Time Object DetectionYou Only Look Once: Unified, Real-Time Object Detection
You Only Look Once: Unified, Real-Time Object DetectionDADAJONJURAKUZIEV
 
Video object tracking with classification and recognition of objects
Video object tracking with classification and recognition of objectsVideo object tracking with classification and recognition of objects
Video object tracking with classification and recognition of objectsManish Khare
 
Object Detection & Tracking
Object Detection & TrackingObject Detection & Tracking
Object Detection & TrackingAkshay Gujarathi
 
What Is Deep Learning? | Introduction to Deep Learning | Deep Learning Tutori...
What Is Deep Learning? | Introduction to Deep Learning | Deep Learning Tutori...What Is Deep Learning? | Introduction to Deep Learning | Deep Learning Tutori...
What Is Deep Learning? | Introduction to Deep Learning | Deep Learning Tutori...Simplilearn
 
Moving object detection
Moving object detectionMoving object detection
Moving object detectionRaviraj singh shekhawat
 
Introduction to object detection
Introduction to object detectionIntroduction to object detection
Introduction to object detectionAmar Jindal
 
Object Detection and Recognition
Object Detection and Recognition Object Detection and Recognition
Object Detection and Recognition Intel Nervana
 
Object tracking
Object trackingObject tracking
Object trackingSri vidhya k
 
Mask R-CNN
Mask R-CNNMask R-CNN
Mask R-CNNChanuk Lim
 
Real-time object detection coz YOLO!
Real-time object detection coz YOLO!Real-time object detection coz YOLO!
Real-time object detection coz YOLO!J On The Beach
 
Object Detection Classification, tracking and Counting
Object Detection Classification, tracking and CountingObject Detection Classification, tracking and Counting
Object Detection Classification, tracking and CountingShounak Mitra
 
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
 
Deep sort and sort paper introduce presentation
Deep sort and sort paper introduce presentationDeep sort and sort paper introduce presentation
Deep sort and sort paper introduce presentation경훈 김
 
Convolutional Neural Network (CNN)of Deep Learning
Convolutional Neural Network (CNN)of Deep LearningConvolutional Neural Network (CNN)of Deep Learning
Convolutional Neural Network (CNN)of Deep Learningalihassaah1994
 
Large Scale Data Clustering: an overview
Large Scale Data Clustering: an overviewLarge Scale Data Clustering: an overview
Large Scale Data Clustering: an overviewVahid Mirjalili
 

Mais conteúdo relacionado

Mais procurados

Machine Learning - Object Detection and Classification
Machine Learning - Object Detection and ClassificationMachine Learning - Object Detection and Classification
Machine Learning - Object Detection and ClassificationVikas Jain
 
[PR12] You Only Look Once (YOLO): Unified Real-Time Object Detection
[PR12] You Only Look Once (YOLO): Unified Real-Time Object Detection[PR12] You Only Look Once (YOLO): Unified Real-Time Object Detection
[PR12] You Only Look Once (YOLO): Unified Real-Time Object DetectionTaegyun Jeon
 
Real Time Object Tracking
Real Time Object TrackingReal Time Object Tracking
Real Time Object TrackingVanya Valindria
 
Deep learning based object detection
Deep learning based object detectionDeep learning based object detection
Deep learning based object detectionchettykulkarni
 
Multi Object Tracking | Presentation 1 | ID 103001
Multi Object Tracking | Presentation 1 | ID 103001Multi Object Tracking | Presentation 1 | ID 103001
Multi Object Tracking | Presentation 1 | ID 103001Md. Minhazul Haque
 
Object Detection Using R-CNN Deep Learning Framework
Object Detection Using R-CNN Deep Learning FrameworkObject Detection Using R-CNN Deep Learning Framework
Object Detection Using R-CNN Deep Learning FrameworkNader Karimi
 
You Only Look Once: Unified, Real-Time Object Detection
You Only Look Once: Unified, Real-Time Object DetectionYou Only Look Once: Unified, Real-Time Object Detection
You Only Look Once: Unified, Real-Time Object DetectionDADAJONJURAKUZIEV
 
Video object tracking with classification and recognition of objects
Video object tracking with classification and recognition of objectsVideo object tracking with classification and recognition of objects
Video object tracking with classification and recognition of objectsManish Khare
 
Object Detection & Tracking
Object Detection & TrackingObject Detection & Tracking
Object Detection & TrackingAkshay Gujarathi
 
What Is Deep Learning? | Introduction to Deep Learning | Deep Learning Tutori...
What Is Deep Learning? | Introduction to Deep Learning | Deep Learning Tutori...What Is Deep Learning? | Introduction to Deep Learning | Deep Learning Tutori...
What Is Deep Learning? | Introduction to Deep Learning | Deep Learning Tutori...Simplilearn
 
Introduction to object detection
Introduction to object detectionIntroduction to object detection
Introduction to object detectionAmar Jindal
 
Object Detection and Recognition
Object Detection and Recognition Object Detection and Recognition
Object Detection and Recognition Intel Nervana
 
Real-time object detection coz YOLO!
Real-time object detection coz YOLO!Real-time object detection coz YOLO!
Real-time object detection coz YOLO!J On The Beach
 
Object Detection Classification, tracking and Counting
Object Detection Classification, tracking and CountingObject Detection Classification, tracking and Counting
Object Detection Classification, tracking and CountingShounak Mitra
 
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
 
Deep sort and sort paper introduce presentation
Deep sort and sort paper introduce presentationDeep sort and sort paper introduce presentation
Deep sort and sort paper introduce presentation경훈 김
 

Mais procurados (20)

Machine Learning - Object Detection and Classification
Machine Learning - Object Detection and ClassificationMachine Learning - Object Detection and Classification
Machine Learning - Object Detection and Classification
 
Object detection
Object detectionObject detection
Object detection
 
[PR12] You Only Look Once (YOLO): Unified Real-Time Object Detection
[PR12] You Only Look Once (YOLO): Unified Real-Time Object Detection[PR12] You Only Look Once (YOLO): Unified Real-Time Object Detection
[PR12] You Only Look Once (YOLO): Unified Real-Time Object Detection
 
Real Time Object Tracking
Real Time Object TrackingReal Time Object Tracking
Real Time Object Tracking
 
Deep learning based object detection
Deep learning based object detectionDeep learning based object detection
Deep learning based object detection
 
Multi Object Tracking | Presentation 1 | ID 103001
Multi Object Tracking | Presentation 1 | ID 103001Multi Object Tracking | Presentation 1 | ID 103001
Multi Object Tracking | Presentation 1 | ID 103001
 
Object Detection Using R-CNN Deep Learning Framework
Object Detection Using R-CNN Deep Learning FrameworkObject Detection Using R-CNN Deep Learning Framework
Object Detection Using R-CNN Deep Learning Framework
 
You Only Look Once: Unified, Real-Time Object Detection
You Only Look Once: Unified, Real-Time Object DetectionYou Only Look Once: Unified, Real-Time Object Detection
You Only Look Once: Unified, Real-Time Object Detection
 
Video object tracking with classification and recognition of objects
Video object tracking with classification and recognition of objectsVideo object tracking with classification and recognition of objects
Video object tracking with classification and recognition of objects
 
Object Detection & Tracking
Object Detection & TrackingObject Detection & Tracking
Object Detection & Tracking
 
What Is Deep Learning? | Introduction to Deep Learning | Deep Learning Tutori...
What Is Deep Learning? | Introduction to Deep Learning | Deep Learning Tutori...What Is Deep Learning? | Introduction to Deep Learning | Deep Learning Tutori...
What Is Deep Learning? | Introduction to Deep Learning | Deep Learning Tutori...
 
Moving object detection
Moving object detectionMoving object detection
Moving object detection
 
Introduction to object detection
Introduction to object detectionIntroduction to object detection
Introduction to object detection
 
Object Detection and Recognition
Object Detection and Recognition Object Detection and Recognition
Object Detection and Recognition
 
Object tracking
Object trackingObject tracking
Object tracking
 
Mask R-CNN
Mask R-CNNMask R-CNN
Mask R-CNN
 
Real-time object detection coz YOLO!
Real-time object detection coz YOLO!Real-time object detection coz YOLO!
Real-time object detection coz YOLO!
 
Object Detection Classification, tracking and Counting
Object Detection Classification, tracking and CountingObject Detection Classification, tracking and Counting
Object Detection Classification, tracking and Counting
 
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
 
Deep sort and sort paper introduce presentation
Deep sort and sort paper introduce presentationDeep sort and sort paper introduce presentation
Deep sort and sort paper introduce presentation
 

Semelhante a Object Detection using Deep Neural Networks

Convolutional Neural Network (CNN)of Deep Learning
Convolutional Neural Network (CNN)of Deep LearningConvolutional Neural Network (CNN)of Deep Learning
Convolutional Neural Network (CNN)of Deep Learningalihassaah1994
 
Large Scale Data Clustering: an overview
Large Scale Data Clustering: an overviewLarge Scale Data Clustering: an overview
Large Scale Data Clustering: an overviewVahid Mirjalili
 
Once-for-All: Train One Network and Specialize it for Efficient Deployment
Once-for-All: Train One Network and Specialize it for Efficient Deployment Once-for-All: Train One Network and Specialize it for Efficient Deployment
Once-for-All: Train One Network and Specialize it for Efficient Deploymenttaeseon ryu
 
00463517b1e90c1e63000000
00463517b1e90c1e6300000000463517b1e90c1e63000000
00463517b1e90c1e63000000Ivonne Liu
 
Convolutional Neural Networks
Convolutional Neural NetworksConvolutional Neural Networks
Convolutional Neural Networksmilad abbasi
 
Backbone search for object detection for applications in intrusion warning sy...
Backbone search for object detection for applications in intrusion warning sy...Backbone search for object detection for applications in intrusion warning sy...
Backbone search for object detection for applications in intrusion warning sy...IAESIJAI
 
DAOR - Bridging the Gap between Community and Node Representations: Graph Emb...
DAOR - Bridging the Gap between Community and Node Representations: Graph Emb...DAOR - Bridging the Gap between Community and Node Representations: Graph Emb...
DAOR - Bridging the Gap between Community and Node Representations: Graph Emb...Artem Lutov
 
Safety Verification of Deep Neural Networks_.pdf
Safety Verification of Deep Neural Networks_.pdfSafety Verification of Deep Neural Networks_.pdf
Safety Verification of Deep Neural Networks_.pdfPolytechnique Montréal
 
Meetup 18/10/2018 - Artificiële intelligentie en mobiliteit
Meetup 18/10/2018 - Artificiële intelligentie en mobiliteitMeetup 18/10/2018 - Artificiële intelligentie en mobiliteit
Meetup 18/10/2018 - Artificiële intelligentie en mobiliteitDigipolis Antwerpen
 
Coding the Continuum
Coding the ContinuumCoding the Continuum
Coding the ContinuumIan Foster
 
SPAR 2015 - Civil Maps Presentation by Sravan Puttagunta
SPAR 2015 - Civil Maps Presentation by Sravan PuttaguntaSPAR 2015 - Civil Maps Presentation by Sravan Puttagunta
SPAR 2015 - Civil Maps Presentation by Sravan PuttaguntaSravan Puttagunta
 
Deep Neural Networks (D1L2 Insight@DCU Machine Learning Workshop 2017)
Deep Neural Networks (D1L2 Insight@DCU Machine Learning Workshop 2017)Deep Neural Networks (D1L2 Insight@DCU Machine Learning Workshop 2017)
Deep Neural Networks (D1L2 Insight@DCU Machine Learning Workshop 2017)Universitat Politècnica de Catalunya
 
“Understanding DNN-Based Object Detectors,” a Presentation from Au-Zone Techn...
“Understanding DNN-Based Object Detectors,” a Presentation from Au-Zone Techn...“Understanding DNN-Based Object Detectors,” a Presentation from Au-Zone Techn...
“Understanding DNN-Based Object Detectors,” a Presentation from Au-Zone Techn...Edge AI and Vision Alliance
 
"An adaptive modular approach to the mining of sensor network ...
"An adaptive modular approach to the mining of sensor network ..."An adaptive modular approach to the mining of sensor network ...
"An adaptive modular approach to the mining of sensor network ...butest
 
Visual Search Engine with MXNet Gluon
Visual Search Engine with MXNet GluonVisual Search Engine with MXNet Gluon
Visual Search Engine with MXNet GluonApache MXNet
 
HYBRIDIZATION OF DCT BASED STEGANOGRAPHY AND RANDOM GRIDS
HYBRIDIZATION OF DCT BASED STEGANOGRAPHY AND RANDOM GRIDSHYBRIDIZATION OF DCT BASED STEGANOGRAPHY AND RANDOM GRIDS
HYBRIDIZATION OF DCT BASED STEGANOGRAPHY AND RANDOM GRIDSIJNSA Journal
 
HYBRIDIZATION OF DCT BASED STEGANOGRAPHY AND RANDOM GRIDS
HYBRIDIZATION OF DCT BASED STEGANOGRAPHY AND RANDOM GRIDSHYBRIDIZATION OF DCT BASED STEGANOGRAPHY AND RANDOM GRIDS
HYBRIDIZATION OF DCT BASED STEGANOGRAPHY AND RANDOM GRIDSIJNSA Journal
 
Volume 2-issue-6-2143-2147
Volume 2-issue-6-2143-2147Volume 2-issue-6-2143-2147
Volume 2-issue-6-2143-2147Editor IJARCET
 

Semelhante a Object Detection using Deep Neural Networks (20)

Convolutional Neural Network (CNN)of Deep Learning
Convolutional Neural Network (CNN)of Deep LearningConvolutional Neural Network (CNN)of Deep Learning
Convolutional Neural Network (CNN)of Deep Learning
 
Large Scale Data Clustering: an overview
Large Scale Data Clustering: an overviewLarge Scale Data Clustering: an overview
Large Scale Data Clustering: an overview
 
Once-for-All: Train One Network and Specialize it for Efficient Deployment
Once-for-All: Train One Network and Specialize it for Efficient Deployment Once-for-All: Train One Network and Specialize it for Efficient Deployment
Once-for-All: Train One Network and Specialize it for Efficient Deployment
 
dm_clustering2.ppt
dm_clustering2.pptdm_clustering2.ppt
dm_clustering2.ppt
 
00463517b1e90c1e63000000
00463517b1e90c1e6300000000463517b1e90c1e63000000
00463517b1e90c1e63000000
 
Cnn
CnnCnn
Cnn
 
Convolutional Neural Networks
Convolutional Neural NetworksConvolutional Neural Networks
Convolutional Neural Networks
 
Backbone search for object detection for applications in intrusion warning sy...
Backbone search for object detection for applications in intrusion warning sy...Backbone search for object detection for applications in intrusion warning sy...
Backbone search for object detection for applications in intrusion warning sy...
 
DAOR - Bridging the Gap between Community and Node Representations: Graph Emb...
DAOR - Bridging the Gap between Community and Node Representations: Graph Emb...DAOR - Bridging the Gap between Community and Node Representations: Graph Emb...
DAOR - Bridging the Gap between Community and Node Representations: Graph Emb...
 
Safety Verification of Deep Neural Networks_.pdf
Safety Verification of Deep Neural Networks_.pdfSafety Verification of Deep Neural Networks_.pdf
Safety Verification of Deep Neural Networks_.pdf
 
Meetup 18/10/2018 - Artificiële intelligentie en mobiliteit
Meetup 18/10/2018 - Artificiële intelligentie en mobiliteitMeetup 18/10/2018 - Artificiële intelligentie en mobiliteit
Meetup 18/10/2018 - Artificiële intelligentie en mobiliteit
 
Coding the Continuum
Coding the ContinuumCoding the Continuum
Coding the Continuum
 
SPAR 2015 - Civil Maps Presentation by Sravan Puttagunta
SPAR 2015 - Civil Maps Presentation by Sravan PuttaguntaSPAR 2015 - Civil Maps Presentation by Sravan Puttagunta
SPAR 2015 - Civil Maps Presentation by Sravan Puttagunta
 
Deep Neural Networks (D1L2 Insight@DCU Machine Learning Workshop 2017)
Deep Neural Networks (D1L2 Insight@DCU Machine Learning Workshop 2017)Deep Neural Networks (D1L2 Insight@DCU Machine Learning Workshop 2017)
Deep Neural Networks (D1L2 Insight@DCU Machine Learning Workshop 2017)
 
“Understanding DNN-Based Object Detectors,” a Presentation from Au-Zone Techn...
“Understanding DNN-Based Object Detectors,” a Presentation from Au-Zone Techn...“Understanding DNN-Based Object Detectors,” a Presentation from Au-Zone Techn...
“Understanding DNN-Based Object Detectors,” a Presentation from Au-Zone Techn...
 
"An adaptive modular approach to the mining of sensor network ...
"An adaptive modular approach to the mining of sensor network ..."An adaptive modular approach to the mining of sensor network ...
"An adaptive modular approach to the mining of sensor network ...
 
Visual Search Engine with MXNet Gluon
Visual Search Engine with MXNet GluonVisual Search Engine with MXNet Gluon
Visual Search Engine with MXNet Gluon
 
HYBRIDIZATION OF DCT BASED STEGANOGRAPHY AND RANDOM GRIDS
HYBRIDIZATION OF DCT BASED STEGANOGRAPHY AND RANDOM GRIDSHYBRIDIZATION OF DCT BASED STEGANOGRAPHY AND RANDOM GRIDS
HYBRIDIZATION OF DCT BASED STEGANOGRAPHY AND RANDOM GRIDS
 
HYBRIDIZATION OF DCT BASED STEGANOGRAPHY AND RANDOM GRIDS
HYBRIDIZATION OF DCT BASED STEGANOGRAPHY AND RANDOM GRIDSHYBRIDIZATION OF DCT BASED STEGANOGRAPHY AND RANDOM GRIDS
HYBRIDIZATION OF DCT BASED STEGANOGRAPHY AND RANDOM GRIDS
 
Volume 2-issue-6-2143-2147
Volume 2-issue-6-2143-2147Volume 2-issue-6-2143-2147
Volume 2-issue-6-2143-2147
 

Mais de Usman Qayyum

Artificial intelligence on the Edge
Artificial intelligence on the EdgeArtificial intelligence on the Edge
Artificial intelligence on the EdgeUsman Qayyum
 
Deep Reinforcement Learning
Deep Reinforcement LearningDeep Reinforcement Learning
Deep Reinforcement LearningUsman Qayyum
 
Deep Learning disruption
Deep Learning disruptionDeep Learning disruption
Deep Learning disruptionUsman Qayyum
 
Thermal colorization using Deep Neural Network
Thermal colorization using Deep Neural NetworkThermal colorization using Deep Neural Network
Thermal colorization using Deep Neural NetworkUsman Qayyum
 
Introduction to deep Learning
Introduction to deep LearningIntroduction to deep Learning
Introduction to deep LearningUsman Qayyum
 

Mais de Usman Qayyum (6)

Artificial intelligence on the Edge
Artificial intelligence on the EdgeArtificial intelligence on the Edge
Artificial intelligence on the Edge
 
Ai for kids
Ai for kidsAi for kids
Ai for kids
 
Deep Reinforcement Learning
Deep Reinforcement LearningDeep Reinforcement Learning
Deep Reinforcement Learning
 
Deep Learning disruption
Deep Learning disruptionDeep Learning disruption
Deep Learning disruption
 
Thermal colorization using Deep Neural Network
Thermal colorization using Deep Neural NetworkThermal colorization using Deep Neural Network
Thermal colorization using Deep Neural Network
 
Introduction to deep Learning
Introduction to deep LearningIntroduction to deep Learning
Introduction to deep Learning
 

Último

Daily Lesson Plan in Mathematics Quarter 4
Daily Lesson Plan in Mathematics Quarter 4Daily Lesson Plan in Mathematics Quarter 4
Daily Lesson Plan in Mathematics Quarter 4JOYLYNSAMANIEGO
 
ROLES IN A STAGE PRODUCTION in arts.pptx
ROLES IN A STAGE PRODUCTION in arts.pptxROLES IN A STAGE PRODUCTION in arts.pptx
ROLES IN A STAGE PRODUCTION in arts.pptxVanesaIglesias10
 
Global Lehigh Strategic Initiatives (without descriptions)
Global Lehigh Strategic Initiatives (without descriptions)Global Lehigh Strategic Initiatives (without descriptions)
Global Lehigh Strategic Initiatives (without descriptions)cama23
 
ISYU TUNGKOL SA SEKSWLADIDA (ISSUE ABOUT SEXUALITY
ISYU TUNGKOL SA SEKSWLADIDA (ISSUE ABOUT SEXUALITYISYU TUNGKOL SA SEKSWLADIDA (ISSUE ABOUT SEXUALITY
ISYU TUNGKOL SA SEKSWLADIDA (ISSUE ABOUT SEXUALITYKayeClaireEstoconing
 
Activity 2-unit 2-update 2024. English translation
Activity 2-unit 2-update 2024. English translationActivity 2-unit 2-update 2024. English translation
Activity 2-unit 2-update 2024. English translationRosabel UA
 
Active Learning Strategies (in short ALS).pdf
Active Learning Strategies (in short ALS).pdfActive Learning Strategies (in short ALS).pdf
Active Learning Strategies (in short ALS).pdfPatidar M
 
Choosing the Right CBSE School A Comprehensive Guide for Parents
Choosing the Right CBSE School A Comprehensive Guide for ParentsChoosing the Right CBSE School A Comprehensive Guide for Parents
Choosing the Right CBSE School A Comprehensive Guide for Parentsnavabharathschool99
 
4.16.24 Poverty and Precarity--Desmond.pptx
4.16.24 Poverty and Precarity--Desmond.pptx4.16.24 Poverty and Precarity--Desmond.pptx
4.16.24 Poverty and Precarity--Desmond.pptxmary850239
 
What is Model Inheritance in Odoo 17 ERP
What is Model Inheritance in Odoo 17 ERPWhat is Model Inheritance in Odoo 17 ERP
What is Model Inheritance in Odoo 17 ERPCeline George
 
How to Add Barcode on PDF Report in Odoo 17
How to Add Barcode on PDF Report in Odoo 17How to Add Barcode on PDF Report in Odoo 17
How to Add Barcode on PDF Report in Odoo 17Celine George
 
ENGLISH 7_Q4_LESSON 2_ Employing a Variety of Strategies for Effective Interp...
ENGLISH 7_Q4_LESSON 2_ Employing a Variety of Strategies for Effective Interp...ENGLISH 7_Q4_LESSON 2_ Employing a Variety of Strategies for Effective Interp...
ENGLISH 7_Q4_LESSON 2_ Employing a Variety of Strategies for Effective Interp...JhezDiaz1
 
Barangay Council for the Protection of Children (BCPC) Orientation.pptx
Barangay Council for the Protection of Children (BCPC) Orientation.pptxBarangay Council for the Protection of Children (BCPC) Orientation.pptx
Barangay Council for the Protection of Children (BCPC) Orientation.pptxCarlos105
 
HỌC TỐT TIẾNG ANH 11 THEO CHƯƠNG TRÌNH GLOBAL SUCCESS ĐÁP ÁN CHI TIẾT - CẢ NĂ...
HỌC TỐT TIẾNG ANH 11 THEO CHƯƠNG TRÌNH GLOBAL SUCCESS ĐÁP ÁN CHI TIẾT - CẢ NĂ...HỌC TỐT TIẾNG ANH 11 THEO CHƯƠNG TRÌNH GLOBAL SUCCESS ĐÁP ÁN CHI TIẾT - CẢ NĂ...
HỌC TỐT TIẾNG ANH 11 THEO CHƯƠNG TRÌNH GLOBAL SUCCESS ĐÁP ÁN CHI TIẾT - CẢ NĂ...Nguyen Thanh Tu Collection
 
Transaction Management in Database Management System
Transaction Management in Database Management SystemTransaction Management in Database Management System
Transaction Management in Database Management SystemChristalin Nelson
 
Influencing policy (training slides from Fast Track Impact)
Influencing policy (training slides from Fast Track Impact)Influencing policy (training slides from Fast Track Impact)
Influencing policy (training slides from Fast Track Impact)Mark Reed
 
Difference Between Search & Browse Methods in Odoo 17
Difference Between Search & Browse Methods in Odoo 17Difference Between Search & Browse Methods in Odoo 17
Difference Between Search & Browse Methods in Odoo 17Celine George
 
Q4-PPT-Music9_Lesson-1-Romantic-Opera.pptx
Q4-PPT-Music9_Lesson-1-Romantic-Opera.pptxQ4-PPT-Music9_Lesson-1-Romantic-Opera.pptx
Q4-PPT-Music9_Lesson-1-Romantic-Opera.pptxlancelewisportillo
 

Último (20)

Daily Lesson Plan in Mathematics Quarter 4
Daily Lesson Plan in Mathematics Quarter 4Daily Lesson Plan in Mathematics Quarter 4
Daily Lesson Plan in Mathematics Quarter 4
 
ROLES IN A STAGE PRODUCTION in arts.pptx
ROLES IN A STAGE PRODUCTION in arts.pptxROLES IN A STAGE PRODUCTION in arts.pptx
ROLES IN A STAGE PRODUCTION in arts.pptx
 
Global Lehigh Strategic Initiatives (without descriptions)
Global Lehigh Strategic Initiatives (without descriptions)Global Lehigh Strategic Initiatives (without descriptions)
Global Lehigh Strategic Initiatives (without descriptions)
 
ISYU TUNGKOL SA SEKSWLADIDA (ISSUE ABOUT SEXUALITY
ISYU TUNGKOL SA SEKSWLADIDA (ISSUE ABOUT SEXUALITYISYU TUNGKOL SA SEKSWLADIDA (ISSUE ABOUT SEXUALITY
ISYU TUNGKOL SA SEKSWLADIDA (ISSUE ABOUT SEXUALITY
 
YOUVE_GOT_EMAIL_PRELIMS_EL_DORADO_2024.pptx
YOUVE_GOT_EMAIL_PRELIMS_EL_DORADO_2024.pptxYOUVE_GOT_EMAIL_PRELIMS_EL_DORADO_2024.pptx
YOUVE_GOT_EMAIL_PRELIMS_EL_DORADO_2024.pptx
 
Activity 2-unit 2-update 2024. English translation
Activity 2-unit 2-update 2024. English translationActivity 2-unit 2-update 2024. English translation
Activity 2-unit 2-update 2024. English translation
 
Active Learning Strategies (in short ALS).pdf
Active Learning Strategies (in short ALS).pdfActive Learning Strategies (in short ALS).pdf
Active Learning Strategies (in short ALS).pdf
 
Choosing the Right CBSE School A Comprehensive Guide for Parents
Choosing the Right CBSE School A Comprehensive Guide for ParentsChoosing the Right CBSE School A Comprehensive Guide for Parents
Choosing the Right CBSE School A Comprehensive Guide for Parents
 
4.16.24 Poverty and Precarity--Desmond.pptx
4.16.24 Poverty and Precarity--Desmond.pptx4.16.24 Poverty and Precarity--Desmond.pptx
4.16.24 Poverty and Precarity--Desmond.pptx
 
What is Model Inheritance in Odoo 17 ERP
What is Model Inheritance in Odoo 17 ERPWhat is Model Inheritance in Odoo 17 ERP
What is Model Inheritance in Odoo 17 ERP
 
How to Add Barcode on PDF Report in Odoo 17
How to Add Barcode on PDF Report in Odoo 17How to Add Barcode on PDF Report in Odoo 17
How to Add Barcode on PDF Report in Odoo 17
 
ENGLISH 7_Q4_LESSON 2_ Employing a Variety of Strategies for Effective Interp...
ENGLISH 7_Q4_LESSON 2_ Employing a Variety of Strategies for Effective Interp...ENGLISH 7_Q4_LESSON 2_ Employing a Variety of Strategies for Effective Interp...
ENGLISH 7_Q4_LESSON 2_ Employing a Variety of Strategies for Effective Interp...
 
Barangay Council for the Protection of Children (BCPC) Orientation.pptx
Barangay Council for the Protection of Children (BCPC) Orientation.pptxBarangay Council for the Protection of Children (BCPC) Orientation.pptx
Barangay Council for the Protection of Children (BCPC) Orientation.pptx
 
HỌC TỐT TIẾNG ANH 11 THEO CHƯƠNG TRÌNH GLOBAL SUCCESS ĐÁP ÁN CHI TIẾT - CẢ NĂ...
HỌC TỐT TIẾNG ANH 11 THEO CHƯƠNG TRÌNH GLOBAL SUCCESS ĐÁP ÁN CHI TIẾT - CẢ NĂ...HỌC TỐT TIẾNG ANH 11 THEO CHƯƠNG TRÌNH GLOBAL SUCCESS ĐÁP ÁN CHI TIẾT - CẢ NĂ...
HỌC TỐT TIẾNG ANH 11 THEO CHƯƠNG TRÌNH GLOBAL SUCCESS ĐÁP ÁN CHI TIẾT - CẢ NĂ...
 
Transaction Management in Database Management System
Transaction Management in Database Management SystemTransaction Management in Database Management System
Transaction Management in Database Management System
 
YOUVE GOT EMAIL_FINALS_EL_DORADO_2024.pptx
YOUVE GOT EMAIL_FINALS_EL_DORADO_2024.pptxYOUVE GOT EMAIL_FINALS_EL_DORADO_2024.pptx
YOUVE GOT EMAIL_FINALS_EL_DORADO_2024.pptx
 
Influencing policy (training slides from Fast Track Impact)
Influencing policy (training slides from Fast Track Impact)Influencing policy (training slides from Fast Track Impact)
Influencing policy (training slides from Fast Track Impact)
 
Difference Between Search & Browse Methods in Odoo 17
Difference Between Search & Browse Methods in Odoo 17Difference Between Search & Browse Methods in Odoo 17
Difference Between Search & Browse Methods in Odoo 17
 
Q4-PPT-Music9_Lesson-1-Romantic-Opera.pptx
Q4-PPT-Music9_Lesson-1-Romantic-Opera.pptxQ4-PPT-Music9_Lesson-1-Romantic-Opera.pptx
Q4-PPT-Music9_Lesson-1-Romantic-Opera.pptx
 
LEFT_ON_C'N_ PRELIMS_EL_DORADO_2024.pptx
LEFT_ON_C'N_ PRELIMS_EL_DORADO_2024.pptxLEFT_ON_C'N_ PRELIMS_EL_DORADO_2024.pptx
LEFT_ON_C'N_ PRELIMS_EL_DORADO_2024.pptx
 

Object Detection using Deep Neural Networks

  • 1. 1 Object Detection By Usman Qayyum 4, Dec, 2018
  • 2. Talk Covers Three Papers (Object Detection -> Embedded Computing) 2 SqueezeNet-2016SSD-2016 TinySSD-2018 =+
  • 3. Image Classification/Object Detection ● Autonomous vehicles, smart video surveillance, facial detection and various applications, fast and robust object detection is need of an hour ● Nonly recognizing and classifying every object in an image, but localizing each one by drawing the appropriate bounding box around it. 3
  • 4. CNN Migration (Image Classification) 4
  • 5. Object Detection as Classification CNN deer? cat? background?
  • 6. Object Detection as Classification CNN deer? cat? background?
  • 7. Object Detection as Classification CNN deer? cat? background?
  • 8. Object Detection as Classification with Sliding Window CNN deer? cat? background?
  • 9. Object Detection as Classification with Box Proposals
  • 10. Box Proposal Method : Selective Search Segmentation As Selective Search for Object Recognition. van de Sande et al. ICCV 2011
  • 11. Idea behind Object Detectors ● Box Proposals ● Classifier Algorithm 11
  • 12. RCNN Rich feature hierarchies for accurate object detection and semantic segmentation. Girshick et al. CVPR 2014. https://people.eecs.berkeley.edu/~rbg/papers/r-cnn-cvpr.pdf
  • 13. Fast-RCNN Fast R-CNN. Girshick. ICCV 2015. https://arxiv.org/abs/1504.08083 Idea: No need to recompute features for every box independently, Regress refined bounding box coordinates.
  • 14. Faster-RCNN Ren et al. NIPS 2015. https://arxiv.org/abs/1506.01497 Idea: Integrate the Bounding Box Propos als as part of the CNN predictions
  • 15. YOLO- You Only Look Once ● Single Shot Detector Redmon et al. CVPR 2016. https://arxiv.org/abs/1506.02640 Idea: No bounding box proposals. Predict a class and a box for every location in a grid.
  • 16. SSD: Single Shot Detector Liu et al. ECCV 2016. Idea: Similar to YOLO, but denser grid map, multiscale grid maps. + Data augm entation + Hard negative mining + Other design choices in the network.
  • 17. -The overall objective loss function is a weighted sum of the localization loss and the confidence loss(conf) N: the number of matched default boxes l: predicted boxes g: the ground truth box x=1 denotes some certain default box is matched to a ground truth box17 1 ( , , , ) ( ( , ) ( , , ))conf locL x c l g L x c L x l g N   SSD: Single Shot Detector
  • 20. AI Workload Migration Embedded (Mobile/Edge) Server/Clou d Execution/Inference Training Execution/Inference Intelligence & Analytics Key Use Cases Vision | Audio | Security Benefits Low Latency | Privacy
  • 21. AI in Embedded Devices 21
  • 22. How ? (AI in Embedded Devices) Pruning Quantization22
  • 23. SqueezeNet (Parameter Reduction) ● Strategy 1. Replace 3x3 filters with 1x1 filters ○ Parameters per filter: (3x3 filter) = 9 * (1x1 filter) ● Strategy 2. Decrease the number of input channels to 3x3 filters ○ Total # of parameters: (# of input channels) * (# of filters) * ( # of parameters per filter) ● Strategy 3. Downsample late in the network so that convolution layers have large activation maps ○ Size of activation maps: the size of input data, the choice of layers in which to downsample in the CNN architecture 23 Iandola, Forrest N., et al. "SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and< 0.5 MB model size."
  • 24. Strategy#1 Conv1x1 or Kernel Reduction 24
  • 25. Microarchitecture – Fire Module 25 Squeeze Layer Set s1x1 < (e1x1 + e3x3), limits the # of input channels to 3*3 filters Strategy 2. Decrease the number of input channels to 3x3 filters Total # of parameters: (# of input channels) * (# of filters) * ( # of parameters per filter) How much can we limit s1x1? Strategy 1. Replace 3*3 filters with 1*1 filters Parameters per filter: (3*3 filter) = 9 * (1*1 filter) How much can we replace 3*3 with 1*1? (e1x1 vs e3x3 )?
  • 26. Expand ● In the "expand" modules, what are the tradeoffs when we turn the knob between mostly 1x1 and mostly 3x3 filters? ● Hypothesis: if having more weights leads to higher accuracy, then having all 3x3 filters should give the highest accuracy 27
  • 27. 28
  • 28. Macroarchitecture 29 Strategy 3. Downsample late in the network so that convolution layers have large activation maps Size of activation maps: the size of input data, the choice of layers in which to downsample in the CNN architecture
  • 30. TinySSD (SSD with Microarchitecture) 31
  • 31. Thanks for your attention. 32