SlideShare uma empresa Scribd logo
1 de 71
Baixar para ler offline
Alexander Zarichkovyi
Ring Ukraine
Faster than real-time
face detection
About me
2
● Junior Researcher
@ Ring Ukraine
● Student of “Kyiv Polytechnic
Institute” (B.SE. Software
Engineering)
● Love algorithms and programming
competitions
3
1. Object detection problem
a. Why is detection problem important?
b. Face detection problem
c. Datasets
d. How to evaluate different Object Detection approaches?
2. History of object detection architectures
a. Viola–Jones object detection
b. Classi ication based
c. Regression based
d. Cascade classi ication based
Agenda
Object detection
problem
5http://cs231n.github.io/classi ication/
Image classification
6http://tutorial.caffe.berkeleyvision.org/caffe-cvpr15-detection.pdf
Classi ication problem Detection problem
Classification vs Detection
7
Object detection results are
mostly used as an input for other
tasks:
● face recognition
● person recognition
● self driving cars
● . . .
Why is object detection
so important?
Face detection
problem
9
What is the Face Detection problem?
10
How many faces do you see on
the picture?
11
● Occlusions
● Light conditions
● Pose
● Diversity
● ...
Why is it difficult?
Datasets
13
20 classes:
• Person: person
• Animal: bird, cat, cow, dog, horse, sheep
• Vehicle: aeroplane, bicycle, boat, bus, car, motorbike, train
• Indoor: bottle, chair, dining table, potted plant, sofa, tv/monitor
Train/val size:
VOC 2007 has 9,963 images containing 24,640 annotated objects.
The PASCAL Visual Object Classes Challenge: A Retrospective
Pascal VOC 2007
14
● Consists of 32 203 images with
393 703 labeled faces
● The faces vary largely in
appearance, pose and scale
● Multiple attributes annotated:
occlusion, pose and event
categories, which allows depth
analysis of existing algorithms
WIDER FACE: A Face Detection Benchmark
WIDER FACE: A Face
Detection Benchmark
15WIDER FACE: A Face Detection Benchmark
WIDER FACE. Annotations
How good is your
Detection algorithm?
17https://www.pyimagesearch.com/2016/11/07/intersection-over-union-iou-for-object-detection/
Intersection Over Union
(Jaccard index)
18
https://classeval.wordpress.com/introduction/introduction-to-the-precision-recall-plot
Recall/Precision curve
Evaluation Plot
19
Evolution of detectors
Viola–Jones object
detection architecture
Viola-Jones
detector
CVPR, 2001
21
Main principles:
● Integral image
● Scanning window
● HAAR-like Features
● Boosted feature selection
● Cascaded classi ier
Rapid object detection using a boosted cascade of simple feature
Viola-Jones detector (1)
22
Integral image
Rapid object detection using a boosted cascade of simple feature
Viola-Jones detector (2)
23
Scanning window
Rapid object detection using a boosted cascade of simple feature
Viola-Jones detector (3)
24
HAAR-like Features
Rapid object detection using a boosted cascade of simple feature
Viola-Jones detector (4)
25
Boosted feature selection
α
α
α
α
…
…
α α α … α
Feature importance
(hi
∈ ℜ)
Feature
(αi
∈ ℜ)
Rapid object detection using a boosted cascade of simple feature
Viola-Jones detector (5)
26
Cascaded classi ier
Rapid object detection using a boosted cascade of simple feature
Viola-Jones detector (5)
27
Pros:
● Really fast (can run at real-time
on embedded devices)
● Low false-positive rate
● Easy to tune
Cons:
● Hand-made features
● Hard to train
● Low detection rate on non
frontal faces
● Detects only simple objects
Rapid object detection using a boosted cascade of simple feature
Viola-Jones detector (5)
Classification based
architectures
Selective Search
Viola-Jones
detector
CVPR, 2001
Selective
Search
IJCV, 2013
30Selective Search for Object Recognition
Selective Search (1)
31
Selective search + SIFT + bag-of-words + SVMs = 35.1% mAP on
PASCAL 2007
Selective Search for Object Recognition
Selective Search (2)
Region-based CNN
(R-CNN)
Viola-Jones
detector
CVPR, 2001
Selective
Search
mAP: 35.1%
IJCV, 2013
R-CNN
Nov, 2013
33Rich feature hierarchies for accurate object detection and semantic segmen ation
● Regions: ~2000 Selective
Search proposals
● Feature Extractor:
AlexNet pre-trained on
ImageNet, ine-tuned on
PASCAL 2007
● Bounding box regression
to re ine box locations
● Performance: mAP of
53.7% on PASCAL 2007
R-CNN (1)
34
Pros:
● Accurate
● Any architecture can be used as a feature
extractor
Cons:
● Hard to train (lots of training objectives:
softmax classi ier, linear SVMs, bound-box
regressions, lot of them train separately)
● Slow training (84h on GPU)
● Inference (detection) is slow (47s / image with
VGG-16 feature extractor)
Rich feature hierarchies for accurate object detection and semantic segmentation
R-CNN (2)
Why so slow?
Multiple usage of CNN
inference!
How to use CNN only once on the whole image?
Spatial Pyramid Pooling
Network (SPP-Net)
Viola-Jones
detector
CVPR, 2001
Selective
Search
mAP: 35.1%
IJCV, 2013
R-CNN
mAP: 53.7%
FPS: 0.05
Nov, 2013
SPP-Net
Jun, 2014
38
● In each region proposal, used a
4-level spatial pyramid, with
grids:
■ 1×1
■ 2×2
■ 3×3
■ 6×6
● To each grid's cells we apply
some global pooling operation.
● Totally we get 50 bins to pool
the features from each feature
map.
Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
SPP-Net (1): Spatial Pyramid
Pooling Layer
39
ROIs from
proposal
method
● Fully-connected layers
● Forward whole image
through Convolutional
Network
● Get feature map of image
● Apply Spatial Pyramid
Pooling layer to feature
map
● Input image
● Classify regions and
apply bounding box
regressors
Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
SPP-Net (2)
40
What’s good about SPP-net?
Pascal VOC 2007 results
It's really faster…
Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
SPP-Net (3)
41
What’s wrong about SPP-net?
● Inherits the rest of
R CNN’s problems
● Introduces a new
problem: cannot update
parameters below SPP
layer during training
Trainable
(3 layers)
Frozen
(13 layers)
Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
SPP-Net (4)
Fast R-CNN
Viola-Jones
detector
CVPR, 2001
Selective
Search
mAP: 35.1%
IJCV, 2013
R-CNN
mAP: 53.7%
FPS: 0.05
Nov, 2013
SPP-Net
mAP: 59.2%
Jun, 2014
Fast R-CNN
Apr, 2015
43
● Fast test time, like
SPP-net
● One network,
trained in one stage
● Higher mean
average precision
than R CNN and
SPP-net
Fast R CNN
Fast R-CNN (1)
44Fast R CNN
R-CNN Fast R-CNN
Training Time 84 hours 9.5 hours
(Speedup) 1x 8.8x
Test time per image
(network only)
47 seconds 0.32 seconds
(Speedup) 1x 146x
mAP (VOC 2007) 53.7% 66.9%
Comparison of R CNN and Fast R CNN (both use
VGG-16 feature extractor)
Fast R-CNN (2)
But, work time do not
include time for Selective
Search...
46
R-CNN Fast R-CNN
Test time per image
(network only)
47 seconds 0.32 seconds
(Speedup) 1x 146x
Test time per image (with
Selective Search)
50 seconds 2 seconds
(Speedup) 1x 25x
Comparison of R CNN and Fast R CNN (both use
VGG-16 feature extractor)
Fast R-CNN (3)
How to speedup
Selective Search?
Rewrite with GPU usage?
Use other segmentation
algorithms?
Use Neural Network!
Faster R-CNN
Viola-Jones
detector
CVPR, 2001
Selective
Search
mAP: 35.1%
IJCV, 2013
R-CNN
mAP: 53.7%
FPS: 0.05
Nov, 2013
SPP-Net
mAP: 59.2%
FPS: 0.47
Jun, 2014
Fast R-CNN
mAP: 66.9%
FPS: 0.5
Apr, 2015
Faster
R-CNN
Jun, 2015
52
~ 100 FPS
Faster R CNN: Towards Real-Time Object Detection with Region Proposal Networks
Faster R-CNN (1):
Region proposal network
53Faster R CNN: Towards Real-Time Object Detection with Region Proposal Networks
Faster R-CNN (2)
54Faster R CNN: Towards Real-Time Object Detection with Region Proposal Networks
R-CNN Fast R-CNN Faster R-CNN
Test time per image
(with proposals)
50 seconds 2 seconds 0.2 seconds
(Speedup) 1x 25x 250x
mAP (VOC 2007) 53.7% 66.9% 69.9%
Comparison of R CNN/Fast R CNN/Faster R CNN (all use
VGG-16 feature extractor)
Faster R-CNN (3)
Regression based
architectures
You Only Look Once
(YOLO)
Viola-Jones
detector
CVPR, 2001
Selective
Search
mAP: 35.1%
IJCV, 2013
R-CNN
mAP: 53.7%
FPS: 0.05
Nov, 2013
SPP-Net
mAP: 59.2%
FPS: 0.47
Jun, 2014
YOLO
Jun, 2015
Fast R-CNN
mAP: 66.9%
FPS: 0.5
Apr, 2015
Faster
R-CNN
mAP: 69.9%
FPS: 5
Jun, 2015
57You Only Look Once: Uni ied, Real-Time Object Detection
YOLO’s pipeline
YOLO (1)
58You Only Look Once: Uni ied, Real-Time Object Detection
Bottom layers from
GoogLeNet
Custom layers
YOLO architecture
YOLO (2)
59
Pros:
● uite fast (~40 FPS on Nvidia Titan Black)
● End-to-end training
● Low Error Rate for
Foreground/Background misclassi ication
● Learn very general representation of objects
Cons:
● Less accurate than Fast R CNN (63.9% mAP
comparte to 66.9%)
● Loss function is an approximation
● Can not detect small objects
● Low detection rate of objects that located
close to each other
You Only Look Once: Unified, Real-Time Object Detection
Errors types comparison
Fast R CNN vs YOLO
YOLO (3)
Single Shot MultiBox
Detector (SSD)
Viola-Jones
detector
CVPR, 2001
Selective
Search
mAP: 35.1%
IJCV, 2013
R-CNN
mAP: 53.7%
FPS: 0.05
Nov, 2013
SPP-Net
mAP: 59.2%
FPS: 0.47
Jun, 2014
YOLO
mAP: 63.9%
FPS: 40
Jun, 2015
Faster
R-CNN
mAP: 69.9%
FPS: 5
Jun, 2015
Fast R-CNN
mAP: 66.9%
FPS: 0.5
Apr, 2015
SSD
Dec, 2015
61SSD: Single Shot MultiBox Detector
SSD architecture
SSD (1)
62
Apply regressors to default
box and get result
Regressors
Confidences for 21 classes
(20 VOC Pascal 2007 classes + background)
3 default boxes for
each cell
SSD: Single Shot MultiBox Detector
SSD detector example
SSD (2)
63
Model mAP FPS
Faster R-CNN (VGG-16) 73.2% 7
Faster R-CNN (ZF) 62.1% 17
YOLO 63.4% 45
Tiny YOLO 52.7% 155
SSD300 (VGG-16) 72.1% 58
SSD500 (VGG-16) 75.1% 23
Pros:
● The best speed/accuracy trade-offs
● State of the art results on all object
detection datasets
● Pretty well works with light feature
extractors (InceprtionV2,
S ueeze Net, MobileNet, Shu leNet,
etc.)
Cons:
● Default boxes as hyper parameter
● Poorly works with heavy feature
extractors (ResNet-101, InceptionV4,
VGG-16, etc.)
SSD: Single Shot MultiBox Detector
Comparison of SSD with other
detectors
SSD (3)
Cascade classification
based architectures
Multi-task cascade NN
(MTCNN)
Viola-Jones
detector
CVPR, 2001
Selective
Search
mAP: 35.1%
IJCV, 2013
R-CNN
mAP: 53.7%
FPS: 0.05
Nov, 2013
SPP-Net
mAP: 59.2%
FPS: 0.47
Jun, 2014
YOLO
mAP: 63.9%
FPS: 40
Jun, 2015
Faster
R-CNN
mAP: 69.9%
FPS: 5
Jun, 2015
Fast R-CNN
mAP: 66.9%
FPS: 0.5
Apr, 2015
SSD
mAP: 72.1%
FPS: 58
Dec, 2015
MTCNN
Apr, 2016
66
Network Input size FPS* Validation
Accuracy
P-Net 12x12 8000 94.6%
R-Net 24x24 650 95.4%
O-Net 48x48 220 95.4%
Networks speed and accuracy on crops
* - for original network input and batch size 1
Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks
MTCNN (1)
67
MTCNN s Networks Architectures
Landmarks example
Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks
MTCNN (2)
68
Recall/Precision curve
Test set o Wider Face date set
Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks
MTCNN (3)
69
Pros:
● Really fast (100 FPS on GPU)
● Lot of speed/accuracy trade-offs
● State of the art results on big part of
Face Detection Datasets (CelebA,
FDDB, etc.)
Cons:
● Hard to train
● Lot of hyper-parameters
● Low detection rate of small faces
● Poorly works without landmarks
Model mAP FPS
MTCNN 85.1% 100
Faster R-CNN
(VGG-16)
93.2% 5
SSH
(VGG-16)
91.9% 10
Different face detector models comparison
Wider Face test set
Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks
MTCNN (4)
70
Questions?
71
Thanks for your attention!
Contact information:
alexander.zarichkovyi@ring.com

Mais conteúdo relacionado

Mais procurados

Introduction to Deep learning
Introduction to Deep learningIntroduction to Deep learning
Introduction to Deep learningleopauly
 
Conception d’antennes imprimées pour Identification Radio Fréquence (RFID) d...
Conception d’antennes imprimées pour Identification  Radio Fréquence (RFID) d...Conception d’antennes imprimées pour Identification  Radio Fréquence (RFID) d...
Conception d’antennes imprimées pour Identification Radio Fréquence (RFID) d...Chergui Athman
 
DSP_FOEHU - MATLAB 04 - The Discrete Fourier Transform (DFT)
DSP_FOEHU - MATLAB 04 - The Discrete Fourier Transform (DFT)DSP_FOEHU - MATLAB 04 - The Discrete Fourier Transform (DFT)
DSP_FOEHU - MATLAB 04 - The Discrete Fourier Transform (DFT)Amr E. Mohamed
 
Nural network ER. Abhishek k. upadhyay Learning rules
Nural network ER. Abhishek  k. upadhyay Learning rulesNural network ER. Abhishek  k. upadhyay Learning rules
Nural network ER. Abhishek k. upadhyay Learning rulesabhishek upadhyay
 
Speech Processing with deep learning
Speech Processing  with deep learningSpeech Processing  with deep learning
Speech Processing with deep learningMohamed Essam
 
Recent Trends in Signal and Image Processing - Applications
Recent Trends in Signal and Image Processing - ApplicationsRecent Trends in Signal and Image Processing - Applications
Recent Trends in Signal and Image Processing - ApplicationsAnand Muglikar
 
Overview of quantum computing and it's application in artificial intelligence
Overview of quantum computing and it's application in artificial intelligenceOverview of quantum computing and it's application in artificial intelligence
Overview of quantum computing and it's application in artificial intelligenceBincySam2
 
Predictive Analysis of Breast Cancer Detection using Classification Algorithm
Predictive Analysis of Breast Cancer Detection using Classification AlgorithmPredictive Analysis of Breast Cancer Detection using Classification Algorithm
Predictive Analysis of Breast Cancer Detection using Classification AlgorithmSushanti Acharya
 
IIR filter realization using direct form I & II
IIR filter realization using direct form I & IIIIR filter realization using direct form I & II
IIR filter realization using direct form I & IISarang Joshi
 
Fuzzy logic in approximate Reasoning
Fuzzy logic in approximate ReasoningFuzzy logic in approximate Reasoning
Fuzzy logic in approximate ReasoningHoàng Đức
 
Introduction to object detection
Introduction to object detectionIntroduction to object detection
Introduction to object detectionBrodmann17
 
Visual Object Tracking: review
Visual Object Tracking: reviewVisual Object Tracking: review
Visual Object Tracking: reviewDmytro Mishkin
 
Deep Learning - CNN and RNN
Deep Learning - CNN and RNNDeep Learning - CNN and RNN
Deep Learning - CNN and RNNAshray Bhandare
 

Mais procurados (20)

Medical Image Processing
Medical Image ProcessingMedical Image Processing
Medical Image Processing
 
Adaptive filters
Adaptive filtersAdaptive filters
Adaptive filters
 
Introduction to Deep learning
Introduction to Deep learningIntroduction to Deep learning
Introduction to Deep learning
 
Conception d’antennes imprimées pour Identification Radio Fréquence (RFID) d...
Conception d’antennes imprimées pour Identification  Radio Fréquence (RFID) d...Conception d’antennes imprimées pour Identification  Radio Fréquence (RFID) d...
Conception d’antennes imprimées pour Identification Radio Fréquence (RFID) d...
 
YOLO
YOLOYOLO
YOLO
 
Cellular neural
Cellular  neuralCellular  neural
Cellular neural
 
Wavelet Transform and DSP Applications
Wavelet Transform and DSP ApplicationsWavelet Transform and DSP Applications
Wavelet Transform and DSP Applications
 
DSP_FOEHU - MATLAB 04 - The Discrete Fourier Transform (DFT)
DSP_FOEHU - MATLAB 04 - The Discrete Fourier Transform (DFT)DSP_FOEHU - MATLAB 04 - The Discrete Fourier Transform (DFT)
DSP_FOEHU - MATLAB 04 - The Discrete Fourier Transform (DFT)
 
Nural network ER. Abhishek k. upadhyay Learning rules
Nural network ER. Abhishek  k. upadhyay Learning rulesNural network ER. Abhishek  k. upadhyay Learning rules
Nural network ER. Abhishek k. upadhyay Learning rules
 
Introduction to OpenCV
Introduction to OpenCVIntroduction to OpenCV
Introduction to OpenCV
 
Speech Processing with deep learning
Speech Processing  with deep learningSpeech Processing  with deep learning
Speech Processing with deep learning
 
Recent Trends in Signal and Image Processing - Applications
Recent Trends in Signal and Image Processing - ApplicationsRecent Trends in Signal and Image Processing - Applications
Recent Trends in Signal and Image Processing - Applications
 
Rq
RqRq
Rq
 
Overview of quantum computing and it's application in artificial intelligence
Overview of quantum computing and it's application in artificial intelligenceOverview of quantum computing and it's application in artificial intelligence
Overview of quantum computing and it's application in artificial intelligence
 
Predictive Analysis of Breast Cancer Detection using Classification Algorithm
Predictive Analysis of Breast Cancer Detection using Classification AlgorithmPredictive Analysis of Breast Cancer Detection using Classification Algorithm
Predictive Analysis of Breast Cancer Detection using Classification Algorithm
 
IIR filter realization using direct form I & II
IIR filter realization using direct form I & IIIIR filter realization using direct form I & II
IIR filter realization using direct form I & II
 
Fuzzy logic in approximate Reasoning
Fuzzy logic in approximate ReasoningFuzzy logic in approximate Reasoning
Fuzzy logic in approximate Reasoning
 
Introduction to object detection
Introduction to object detectionIntroduction to object detection
Introduction to object detection
 
Visual Object Tracking: review
Visual Object Tracking: reviewVisual Object Tracking: review
Visual Object Tracking: review
 
Deep Learning - CNN and RNN
Deep Learning - CNN and RNNDeep Learning - CNN and RNN
Deep Learning - CNN and RNN
 

Semelhante a Александр Заричковый "Faster than real-time face detection"

物件偵測與辨識技術
物件偵測與辨識技術物件偵測與辨識技術
物件偵測與辨識技術CHENHuiMei
 
stitching presentation
stitching presentationstitching presentation
stitching presentationNicholas Eu
 
Computer vision for transportation
Computer vision for transportationComputer vision for transportation
Computer vision for transportationWanjin Yu
 
Deep learning based object detection
Deep learning based object detectionDeep learning based object detection
Deep learning based object detectionMonicaDommaraju
 
Video Classification: Human Action Recognition on HMDB-51 dataset
Video Classification: Human Action Recognition on HMDB-51 datasetVideo Classification: Human Action Recognition on HMDB-51 dataset
Video Classification: Human Action Recognition on HMDB-51 datasetGiorgio Carbone
 
Detecting and Avoiding Frontal Obstacles from a Monocular Camera for Micro Un...
Detecting and Avoiding Frontal Obstacles from a Monocular Camera for Micro Un...Detecting and Avoiding Frontal Obstacles from a Monocular Camera for Micro Un...
Detecting and Avoiding Frontal Obstacles from a Monocular Camera for Micro Un...Mohamed Elawady
 
Object Detection Beyond Mask R-CNN and RetinaNet I
Object Detection Beyond Mask R-CNN and RetinaNet IObject Detection Beyond Mask R-CNN and RetinaNet I
Object Detection Beyond Mask R-CNN and RetinaNet IWanjin Yu
 
Development of wearable object detection system & blind stick for visuall...
Development of wearable object detection system & blind stick for visuall...Development of wearable object detection system & blind stick for visuall...
Development of wearable object detection system & blind stick for visuall...Arkadev Kundu
 
Advanced deep learning based object detection methods
Advanced deep learning based object detection methodsAdvanced deep learning based object detection methods
Advanced deep learning based object detection methodsBrodmann17
 
Intelligente visie maakt drones autonoom
Intelligente visie maakt drones autonoomIntelligente visie maakt drones autonoom
Intelligente visie maakt drones autonoomEUKA
 
Deep Transfer Learning: A new deep learning glitch classification method for ...
Deep Transfer Learning: A new deep learning glitch classification method for ...Deep Transfer Learning: A new deep learning glitch classification method for ...
Deep Transfer Learning: A new deep learning glitch classification method for ...Daniel George
 
Qualcomm research-imagenet2015
Qualcomm research-imagenet2015Qualcomm research-imagenet2015
Qualcomm research-imagenet2015Bilkent University
 
Real Time Object Dectection using machine learning
Real Time Object Dectection using machine learningReal Time Object Dectection using machine learning
Real Time Object Dectection using machine learningpratik pratyay
 
Deep Learning in Computer Vision
Deep Learning in Computer VisionDeep Learning in Computer Vision
Deep Learning in Computer VisionSungjoon Choi
 
150807 Fast R-CNN
150807 Fast R-CNN150807 Fast R-CNN
150807 Fast R-CNNJunho Cho
 
Talk 2010-monash-seminar-panic-driven-event-detection
Talk 2010-monash-seminar-panic-driven-event-detectionTalk 2010-monash-seminar-panic-driven-event-detection
Talk 2010-monash-seminar-panic-driven-event-detectionMahfuzul Haque
 
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
 

Semelhante a Александр Заричковый "Faster than real-time face detection" (20)

物件偵測與辨識技術
物件偵測與辨識技術物件偵測與辨識技術
物件偵測與辨識技術
 
stitching presentation
stitching presentationstitching presentation
stitching presentation
 
Computer vision for transportation
Computer vision for transportationComputer vision for transportation
Computer vision for transportation
 
Deep learning based object detection
Deep learning based object detectionDeep learning based object detection
Deep learning based object detection
 
object-detection.pptx
object-detection.pptxobject-detection.pptx
object-detection.pptx
 
Video Classification: Human Action Recognition on HMDB-51 dataset
Video Classification: Human Action Recognition on HMDB-51 datasetVideo Classification: Human Action Recognition on HMDB-51 dataset
Video Classification: Human Action Recognition on HMDB-51 dataset
 
Detecting and Avoiding Frontal Obstacles from a Monocular Camera for Micro Un...
Detecting and Avoiding Frontal Obstacles from a Monocular Camera for Micro Un...Detecting and Avoiding Frontal Obstacles from a Monocular Camera for Micro Un...
Detecting and Avoiding Frontal Obstacles from a Monocular Camera for Micro Un...
 
Object Detection - Míriam Bellver - UPC Barcelona 2018
Object Detection - Míriam Bellver - UPC Barcelona 2018Object Detection - Míriam Bellver - UPC Barcelona 2018
Object Detection - Míriam Bellver - UPC Barcelona 2018
 
Object Detection Beyond Mask R-CNN and RetinaNet I
Object Detection Beyond Mask R-CNN and RetinaNet IObject Detection Beyond Mask R-CNN and RetinaNet I
Object Detection Beyond Mask R-CNN and RetinaNet I
 
Development of wearable object detection system & blind stick for visuall...
Development of wearable object detection system & blind stick for visuall...Development of wearable object detection system & blind stick for visuall...
Development of wearable object detection system & blind stick for visuall...
 
Advanced deep learning based object detection methods
Advanced deep learning based object detection methodsAdvanced deep learning based object detection methods
Advanced deep learning based object detection methods
 
Intelligente visie maakt drones autonoom
Intelligente visie maakt drones autonoomIntelligente visie maakt drones autonoom
Intelligente visie maakt drones autonoom
 
Deep Transfer Learning: A new deep learning glitch classification method for ...
Deep Transfer Learning: A new deep learning glitch classification method for ...Deep Transfer Learning: A new deep learning glitch classification method for ...
Deep Transfer Learning: A new deep learning glitch classification method for ...
 
Qualcomm research-imagenet2015
Qualcomm research-imagenet2015Qualcomm research-imagenet2015
Qualcomm research-imagenet2015
 
slide-171212080528.pptx
slide-171212080528.pptxslide-171212080528.pptx
slide-171212080528.pptx
 
Real Time Object Dectection using machine learning
Real Time Object Dectection using machine learningReal Time Object Dectection using machine learning
Real Time Object Dectection using machine learning
 
Deep Learning in Computer Vision
Deep Learning in Computer VisionDeep Learning in Computer Vision
Deep Learning in Computer Vision
 
150807 Fast R-CNN
150807 Fast R-CNN150807 Fast R-CNN
150807 Fast R-CNN
 
Talk 2010-monash-seminar-panic-driven-event-detection
Talk 2010-monash-seminar-panic-driven-event-detectionTalk 2010-monash-seminar-panic-driven-event-detection
Talk 2010-monash-seminar-panic-driven-event-detection
 
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
 

Mais de Fwdays

"How Preply reduced ML model development time from 1 month to 1 day",Yevhen Y...
"How Preply reduced ML model development time from 1 month to 1 day",Yevhen Y..."How Preply reduced ML model development time from 1 month to 1 day",Yevhen Y...
"How Preply reduced ML model development time from 1 month to 1 day",Yevhen Y...Fwdays
 
"GenAI Apps: Our Journey from Ideas to Production Excellence",Danil Topchii
"GenAI Apps: Our Journey from Ideas to Production Excellence",Danil Topchii"GenAI Apps: Our Journey from Ideas to Production Excellence",Danil Topchii
"GenAI Apps: Our Journey from Ideas to Production Excellence",Danil TopchiiFwdays
 
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks..."LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...Fwdays
 
"Federated learning: out of reach no matter how close",Oleksandr Lapshyn
"Federated learning: out of reach no matter how close",Oleksandr Lapshyn"Federated learning: out of reach no matter how close",Oleksandr Lapshyn
"Federated learning: out of reach no matter how close",Oleksandr LapshynFwdays
 
"What is a RAG system and how to build it",Dmytro Spodarets
"What is a RAG system and how to build it",Dmytro Spodarets"What is a RAG system and how to build it",Dmytro Spodarets
"What is a RAG system and how to build it",Dmytro SpodaretsFwdays
 
"Debugging python applications inside k8s environment", Andrii Soldatenko
"Debugging python applications inside k8s environment", Andrii Soldatenko"Debugging python applications inside k8s environment", Andrii Soldatenko
"Debugging python applications inside k8s environment", Andrii SoldatenkoFwdays
 
"ML in Production",Oleksandr Bagan
"ML in Production",Oleksandr Bagan"ML in Production",Oleksandr Bagan
"ML in Production",Oleksandr BaganFwdays
 
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek SchlawackFwdays
 
"Distributed graphs and microservices in Prom.ua", Maksym Kindritskyi
"Distributed graphs and microservices in Prom.ua",  Maksym Kindritskyi"Distributed graphs and microservices in Prom.ua",  Maksym Kindritskyi
"Distributed graphs and microservices in Prom.ua", Maksym KindritskyiFwdays
 
"Rethinking the existing data loading and processing process as an ETL exampl...
"Rethinking the existing data loading and processing process as an ETL exampl..."Rethinking the existing data loading and processing process as an ETL exampl...
"Rethinking the existing data loading and processing process as an ETL exampl...Fwdays
 
"How Ukrainian IT specialist can go on vacation abroad without crossing the T...
"How Ukrainian IT specialist can go on vacation abroad without crossing the T..."How Ukrainian IT specialist can go on vacation abroad without crossing the T...
"How Ukrainian IT specialist can go on vacation abroad without crossing the T...Fwdays
 
"The Strength of Being Vulnerable: the experience from CIA, Tesla and Uber", ...
"The Strength of Being Vulnerable: the experience from CIA, Tesla and Uber", ..."The Strength of Being Vulnerable: the experience from CIA, Tesla and Uber", ...
"The Strength of Being Vulnerable: the experience from CIA, Tesla and Uber", ...Fwdays
 
"[QUICK TALK] Radical candor: how to achieve results faster thanks to a cultu...
"[QUICK TALK] Radical candor: how to achieve results faster thanks to a cultu..."[QUICK TALK] Radical candor: how to achieve results faster thanks to a cultu...
"[QUICK TALK] Radical candor: how to achieve results faster thanks to a cultu...Fwdays
 
"[QUICK TALK] PDP Plan, the only one door to raise your salary and boost care...
"[QUICK TALK] PDP Plan, the only one door to raise your salary and boost care..."[QUICK TALK] PDP Plan, the only one door to raise your salary and boost care...
"[QUICK TALK] PDP Plan, the only one door to raise your salary and boost care...Fwdays
 
"4 horsemen of the apocalypse of working relationships (+ antidotes to them)"...
"4 horsemen of the apocalypse of working relationships (+ antidotes to them)"..."4 horsemen of the apocalypse of working relationships (+ antidotes to them)"...
"4 horsemen of the apocalypse of working relationships (+ antidotes to them)"...Fwdays
 
"Reconnecting with Purpose: Rediscovering Job Interest after Burnout", Anast...
"Reconnecting with Purpose: Rediscovering Job Interest after Burnout",  Anast..."Reconnecting with Purpose: Rediscovering Job Interest after Burnout",  Anast...
"Reconnecting with Purpose: Rediscovering Job Interest after Burnout", Anast...Fwdays
 
"Mentoring 101: How to effectively invest experience in the success of others...
"Mentoring 101: How to effectively invest experience in the success of others..."Mentoring 101: How to effectively invest experience in the success of others...
"Mentoring 101: How to effectively invest experience in the success of others...Fwdays
 
"Mission (im) possible: How to get an offer in 2024?", Oleksandra Myronova
"Mission (im) possible: How to get an offer in 2024?",  Oleksandra Myronova"Mission (im) possible: How to get an offer in 2024?",  Oleksandra Myronova
"Mission (im) possible: How to get an offer in 2024?", Oleksandra MyronovaFwdays
 
"Why have we learned how to package products, but not how to 'package ourselv...
"Why have we learned how to package products, but not how to 'package ourselv..."Why have we learned how to package products, but not how to 'package ourselv...
"Why have we learned how to package products, but not how to 'package ourselv...Fwdays
 
"How to tame the dragon, or leadership with imposter syndrome", Oleksandr Zin...
"How to tame the dragon, or leadership with imposter syndrome", Oleksandr Zin..."How to tame the dragon, or leadership with imposter syndrome", Oleksandr Zin...
"How to tame the dragon, or leadership with imposter syndrome", Oleksandr Zin...Fwdays
 

Mais de Fwdays (20)

"How Preply reduced ML model development time from 1 month to 1 day",Yevhen Y...
"How Preply reduced ML model development time from 1 month to 1 day",Yevhen Y..."How Preply reduced ML model development time from 1 month to 1 day",Yevhen Y...
"How Preply reduced ML model development time from 1 month to 1 day",Yevhen Y...
 
"GenAI Apps: Our Journey from Ideas to Production Excellence",Danil Topchii
"GenAI Apps: Our Journey from Ideas to Production Excellence",Danil Topchii"GenAI Apps: Our Journey from Ideas to Production Excellence",Danil Topchii
"GenAI Apps: Our Journey from Ideas to Production Excellence",Danil Topchii
 
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks..."LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
 
"Federated learning: out of reach no matter how close",Oleksandr Lapshyn
"Federated learning: out of reach no matter how close",Oleksandr Lapshyn"Federated learning: out of reach no matter how close",Oleksandr Lapshyn
"Federated learning: out of reach no matter how close",Oleksandr Lapshyn
 
"What is a RAG system and how to build it",Dmytro Spodarets
"What is a RAG system and how to build it",Dmytro Spodarets"What is a RAG system and how to build it",Dmytro Spodarets
"What is a RAG system and how to build it",Dmytro Spodarets
 
"Debugging python applications inside k8s environment", Andrii Soldatenko
"Debugging python applications inside k8s environment", Andrii Soldatenko"Debugging python applications inside k8s environment", Andrii Soldatenko
"Debugging python applications inside k8s environment", Andrii Soldatenko
 
"ML in Production",Oleksandr Bagan
"ML in Production",Oleksandr Bagan"ML in Production",Oleksandr Bagan
"ML in Production",Oleksandr Bagan
 
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack
 
"Distributed graphs and microservices in Prom.ua", Maksym Kindritskyi
"Distributed graphs and microservices in Prom.ua",  Maksym Kindritskyi"Distributed graphs and microservices in Prom.ua",  Maksym Kindritskyi
"Distributed graphs and microservices in Prom.ua", Maksym Kindritskyi
 
"Rethinking the existing data loading and processing process as an ETL exampl...
"Rethinking the existing data loading and processing process as an ETL exampl..."Rethinking the existing data loading and processing process as an ETL exampl...
"Rethinking the existing data loading and processing process as an ETL exampl...
 
"How Ukrainian IT specialist can go on vacation abroad without crossing the T...
"How Ukrainian IT specialist can go on vacation abroad without crossing the T..."How Ukrainian IT specialist can go on vacation abroad without crossing the T...
"How Ukrainian IT specialist can go on vacation abroad without crossing the T...
 
"The Strength of Being Vulnerable: the experience from CIA, Tesla and Uber", ...
"The Strength of Being Vulnerable: the experience from CIA, Tesla and Uber", ..."The Strength of Being Vulnerable: the experience from CIA, Tesla and Uber", ...
"The Strength of Being Vulnerable: the experience from CIA, Tesla and Uber", ...
 
"[QUICK TALK] Radical candor: how to achieve results faster thanks to a cultu...
"[QUICK TALK] Radical candor: how to achieve results faster thanks to a cultu..."[QUICK TALK] Radical candor: how to achieve results faster thanks to a cultu...
"[QUICK TALK] Radical candor: how to achieve results faster thanks to a cultu...
 
"[QUICK TALK] PDP Plan, the only one door to raise your salary and boost care...
"[QUICK TALK] PDP Plan, the only one door to raise your salary and boost care..."[QUICK TALK] PDP Plan, the only one door to raise your salary and boost care...
"[QUICK TALK] PDP Plan, the only one door to raise your salary and boost care...
 
"4 horsemen of the apocalypse of working relationships (+ antidotes to them)"...
"4 horsemen of the apocalypse of working relationships (+ antidotes to them)"..."4 horsemen of the apocalypse of working relationships (+ antidotes to them)"...
"4 horsemen of the apocalypse of working relationships (+ antidotes to them)"...
 
"Reconnecting with Purpose: Rediscovering Job Interest after Burnout", Anast...
"Reconnecting with Purpose: Rediscovering Job Interest after Burnout",  Anast..."Reconnecting with Purpose: Rediscovering Job Interest after Burnout",  Anast...
"Reconnecting with Purpose: Rediscovering Job Interest after Burnout", Anast...
 
"Mentoring 101: How to effectively invest experience in the success of others...
"Mentoring 101: How to effectively invest experience in the success of others..."Mentoring 101: How to effectively invest experience in the success of others...
"Mentoring 101: How to effectively invest experience in the success of others...
 
"Mission (im) possible: How to get an offer in 2024?", Oleksandra Myronova
"Mission (im) possible: How to get an offer in 2024?",  Oleksandra Myronova"Mission (im) possible: How to get an offer in 2024?",  Oleksandra Myronova
"Mission (im) possible: How to get an offer in 2024?", Oleksandra Myronova
 
"Why have we learned how to package products, but not how to 'package ourselv...
"Why have we learned how to package products, but not how to 'package ourselv..."Why have we learned how to package products, but not how to 'package ourselv...
"Why have we learned how to package products, but not how to 'package ourselv...
 
"How to tame the dragon, or leadership with imposter syndrome", Oleksandr Zin...
"How to tame the dragon, or leadership with imposter syndrome", Oleksandr Zin..."How to tame the dragon, or leadership with imposter syndrome", Oleksandr Zin...
"How to tame the dragon, or leadership with imposter syndrome", Oleksandr Zin...
 

Último

AWS Community Day CPH - Three problems of Terraform
AWS Community Day CPH - Three problems of TerraformAWS Community Day CPH - Three problems of Terraform
AWS Community Day CPH - Three problems of TerraformAndrey Devyatkin
 
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...Miguel Araújo
 
Partners Life - Insurer Innovation Award 2024
Partners Life - Insurer Innovation Award 2024Partners Life - Insurer Innovation Award 2024
Partners Life - Insurer Innovation Award 2024The Digital Insurer
 
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...apidays
 
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, AdobeApidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobeapidays
 
Histor y of HAM Radio presentation slide
Histor y of HAM Radio presentation slideHistor y of HAM Radio presentation slide
Histor y of HAM Radio presentation slidevu2urc
 
Handwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed textsHandwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed textsMaria Levchenko
 
How to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerHow to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerThousandEyes
 
GenAI Risks & Security Meetup 01052024.pdf
GenAI Risks & Security Meetup 01052024.pdfGenAI Risks & Security Meetup 01052024.pdf
GenAI Risks & Security Meetup 01052024.pdflior mazor
 
HTML Injection Attacks: Impact and Mitigation Strategies
HTML Injection Attacks: Impact and Mitigation StrategiesHTML Injection Attacks: Impact and Mitigation Strategies
HTML Injection Attacks: Impact and Mitigation StrategiesBoston Institute of Analytics
 
From Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time AutomationFrom Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time AutomationSafe Software
 
What Are The Drone Anti-jamming Systems Technology?
What Are The Drone Anti-jamming Systems Technology?What Are The Drone Anti-jamming Systems Technology?
What Are The Drone Anti-jamming Systems Technology?Antenna Manufacturer Coco
 
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024The Digital Insurer
 
Artificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and MythsArtificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and MythsJoaquim Jorge
 
presentation ICT roal in 21st century education
presentation ICT roal in 21st century educationpresentation ICT roal in 21st century education
presentation ICT roal in 21st century educationjfdjdjcjdnsjd
 
Driving Behavioral Change for Information Management through Data-Driven Gree...
Driving Behavioral Change for Information Management through Data-Driven Gree...Driving Behavioral Change for Information Management through Data-Driven Gree...
Driving Behavioral Change for Information Management through Data-Driven Gree...Enterprise Knowledge
 
A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)Gabriella Davis
 
A Year of the Servo Reboot: Where Are We Now?
A Year of the Servo Reboot: Where Are We Now?A Year of the Servo Reboot: Where Are We Now?
A Year of the Servo Reboot: Where Are We Now?Igalia
 
Scaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organizationScaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organizationRadu Cotescu
 
Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024The Digital Insurer
 

Último (20)

AWS Community Day CPH - Three problems of Terraform
AWS Community Day CPH - Three problems of TerraformAWS Community Day CPH - Three problems of Terraform
AWS Community Day CPH - Three problems of Terraform
 
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
 
Partners Life - Insurer Innovation Award 2024
Partners Life - Insurer Innovation Award 2024Partners Life - Insurer Innovation Award 2024
Partners Life - Insurer Innovation Award 2024
 
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
 
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, AdobeApidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
 
Histor y of HAM Radio presentation slide
Histor y of HAM Radio presentation slideHistor y of HAM Radio presentation slide
Histor y of HAM Radio presentation slide
 
Handwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed textsHandwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed texts
 
How to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerHow to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected Worker
 
GenAI Risks & Security Meetup 01052024.pdf
GenAI Risks & Security Meetup 01052024.pdfGenAI Risks & Security Meetup 01052024.pdf
GenAI Risks & Security Meetup 01052024.pdf
 
HTML Injection Attacks: Impact and Mitigation Strategies
HTML Injection Attacks: Impact and Mitigation StrategiesHTML Injection Attacks: Impact and Mitigation Strategies
HTML Injection Attacks: Impact and Mitigation Strategies
 
From Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time AutomationFrom Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time Automation
 
What Are The Drone Anti-jamming Systems Technology?
What Are The Drone Anti-jamming Systems Technology?What Are The Drone Anti-jamming Systems Technology?
What Are The Drone Anti-jamming Systems Technology?
 
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
 
Artificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and MythsArtificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and Myths
 
presentation ICT roal in 21st century education
presentation ICT roal in 21st century educationpresentation ICT roal in 21st century education
presentation ICT roal in 21st century education
 
Driving Behavioral Change for Information Management through Data-Driven Gree...
Driving Behavioral Change for Information Management through Data-Driven Gree...Driving Behavioral Change for Information Management through Data-Driven Gree...
Driving Behavioral Change for Information Management through Data-Driven Gree...
 
A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)
 
A Year of the Servo Reboot: Where Are We Now?
A Year of the Servo Reboot: Where Are We Now?A Year of the Servo Reboot: Where Are We Now?
A Year of the Servo Reboot: Where Are We Now?
 
Scaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organizationScaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organization
 
Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024
 

Александр Заричковый "Faster than real-time face detection"

  • 1. Alexander Zarichkovyi Ring Ukraine Faster than real-time face detection
  • 2. About me 2 ● Junior Researcher @ Ring Ukraine ● Student of “Kyiv Polytechnic Institute” (B.SE. Software Engineering) ● Love algorithms and programming competitions
  • 3. 3 1. Object detection problem a. Why is detection problem important? b. Face detection problem c. Datasets d. How to evaluate different Object Detection approaches? 2. History of object detection architectures a. Viola–Jones object detection b. Classi ication based c. Regression based d. Cascade classi ication based Agenda
  • 7. 7 Object detection results are mostly used as an input for other tasks: ● face recognition ● person recognition ● self driving cars ● . . . Why is object detection so important?
  • 9. 9 What is the Face Detection problem?
  • 10. 10 How many faces do you see on the picture?
  • 11. 11 ● Occlusions ● Light conditions ● Pose ● Diversity ● ... Why is it difficult?
  • 13. 13 20 classes: • Person: person • Animal: bird, cat, cow, dog, horse, sheep • Vehicle: aeroplane, bicycle, boat, bus, car, motorbike, train • Indoor: bottle, chair, dining table, potted plant, sofa, tv/monitor Train/val size: VOC 2007 has 9,963 images containing 24,640 annotated objects. The PASCAL Visual Object Classes Challenge: A Retrospective Pascal VOC 2007
  • 14. 14 ● Consists of 32 203 images with 393 703 labeled faces ● The faces vary largely in appearance, pose and scale ● Multiple attributes annotated: occlusion, pose and event categories, which allows depth analysis of existing algorithms WIDER FACE: A Face Detection Benchmark WIDER FACE: A Face Detection Benchmark
  • 15. 15WIDER FACE: A Face Detection Benchmark WIDER FACE. Annotations
  • 16. How good is your Detection algorithm?
  • 21. 21 Main principles: ● Integral image ● Scanning window ● HAAR-like Features ● Boosted feature selection ● Cascaded classi ier Rapid object detection using a boosted cascade of simple feature Viola-Jones detector (1)
  • 22. 22 Integral image Rapid object detection using a boosted cascade of simple feature Viola-Jones detector (2)
  • 23. 23 Scanning window Rapid object detection using a boosted cascade of simple feature Viola-Jones detector (3)
  • 24. 24 HAAR-like Features Rapid object detection using a boosted cascade of simple feature Viola-Jones detector (4)
  • 25. 25 Boosted feature selection α α α α … … α α α … α Feature importance (hi ∈ ℜ) Feature (αi ∈ ℜ) Rapid object detection using a boosted cascade of simple feature Viola-Jones detector (5)
  • 26. 26 Cascaded classi ier Rapid object detection using a boosted cascade of simple feature Viola-Jones detector (5)
  • 27. 27 Pros: ● Really fast (can run at real-time on embedded devices) ● Low false-positive rate ● Easy to tune Cons: ● Hand-made features ● Hard to train ● Low detection rate on non frontal faces ● Detects only simple objects Rapid object detection using a boosted cascade of simple feature Viola-Jones detector (5)
  • 30. 30Selective Search for Object Recognition Selective Search (1)
  • 31. 31 Selective search + SIFT + bag-of-words + SVMs = 35.1% mAP on PASCAL 2007 Selective Search for Object Recognition Selective Search (2)
  • 33. 33Rich feature hierarchies for accurate object detection and semantic segmen ation ● Regions: ~2000 Selective Search proposals ● Feature Extractor: AlexNet pre-trained on ImageNet, ine-tuned on PASCAL 2007 ● Bounding box regression to re ine box locations ● Performance: mAP of 53.7% on PASCAL 2007 R-CNN (1)
  • 34. 34 Pros: ● Accurate ● Any architecture can be used as a feature extractor Cons: ● Hard to train (lots of training objectives: softmax classi ier, linear SVMs, bound-box regressions, lot of them train separately) ● Slow training (84h on GPU) ● Inference (detection) is slow (47s / image with VGG-16 feature extractor) Rich feature hierarchies for accurate object detection and semantic segmentation R-CNN (2)
  • 36. Multiple usage of CNN inference! How to use CNN only once on the whole image?
  • 37. Spatial Pyramid Pooling Network (SPP-Net) Viola-Jones detector CVPR, 2001 Selective Search mAP: 35.1% IJCV, 2013 R-CNN mAP: 53.7% FPS: 0.05 Nov, 2013 SPP-Net Jun, 2014
  • 38. 38 ● In each region proposal, used a 4-level spatial pyramid, with grids: ■ 1×1 ■ 2×2 ■ 3×3 ■ 6×6 ● To each grid's cells we apply some global pooling operation. ● Totally we get 50 bins to pool the features from each feature map. Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition SPP-Net (1): Spatial Pyramid Pooling Layer
  • 39. 39 ROIs from proposal method ● Fully-connected layers ● Forward whole image through Convolutional Network ● Get feature map of image ● Apply Spatial Pyramid Pooling layer to feature map ● Input image ● Classify regions and apply bounding box regressors Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition SPP-Net (2)
  • 40. 40 What’s good about SPP-net? Pascal VOC 2007 results It's really faster… Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition SPP-Net (3)
  • 41. 41 What’s wrong about SPP-net? ● Inherits the rest of R CNN’s problems ● Introduces a new problem: cannot update parameters below SPP layer during training Trainable (3 layers) Frozen (13 layers) Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition SPP-Net (4)
  • 42. Fast R-CNN Viola-Jones detector CVPR, 2001 Selective Search mAP: 35.1% IJCV, 2013 R-CNN mAP: 53.7% FPS: 0.05 Nov, 2013 SPP-Net mAP: 59.2% Jun, 2014 Fast R-CNN Apr, 2015
  • 43. 43 ● Fast test time, like SPP-net ● One network, trained in one stage ● Higher mean average precision than R CNN and SPP-net Fast R CNN Fast R-CNN (1)
  • 44. 44Fast R CNN R-CNN Fast R-CNN Training Time 84 hours 9.5 hours (Speedup) 1x 8.8x Test time per image (network only) 47 seconds 0.32 seconds (Speedup) 1x 146x mAP (VOC 2007) 53.7% 66.9% Comparison of R CNN and Fast R CNN (both use VGG-16 feature extractor) Fast R-CNN (2)
  • 45. But, work time do not include time for Selective Search...
  • 46. 46 R-CNN Fast R-CNN Test time per image (network only) 47 seconds 0.32 seconds (Speedup) 1x 146x Test time per image (with Selective Search) 50 seconds 2 seconds (Speedup) 1x 25x Comparison of R CNN and Fast R CNN (both use VGG-16 feature extractor) Fast R-CNN (3)
  • 51. Faster R-CNN Viola-Jones detector CVPR, 2001 Selective Search mAP: 35.1% IJCV, 2013 R-CNN mAP: 53.7% FPS: 0.05 Nov, 2013 SPP-Net mAP: 59.2% FPS: 0.47 Jun, 2014 Fast R-CNN mAP: 66.9% FPS: 0.5 Apr, 2015 Faster R-CNN Jun, 2015
  • 52. 52 ~ 100 FPS Faster R CNN: Towards Real-Time Object Detection with Region Proposal Networks Faster R-CNN (1): Region proposal network
  • 53. 53Faster R CNN: Towards Real-Time Object Detection with Region Proposal Networks Faster R-CNN (2)
  • 54. 54Faster R CNN: Towards Real-Time Object Detection with Region Proposal Networks R-CNN Fast R-CNN Faster R-CNN Test time per image (with proposals) 50 seconds 2 seconds 0.2 seconds (Speedup) 1x 25x 250x mAP (VOC 2007) 53.7% 66.9% 69.9% Comparison of R CNN/Fast R CNN/Faster R CNN (all use VGG-16 feature extractor) Faster R-CNN (3)
  • 56. You Only Look Once (YOLO) Viola-Jones detector CVPR, 2001 Selective Search mAP: 35.1% IJCV, 2013 R-CNN mAP: 53.7% FPS: 0.05 Nov, 2013 SPP-Net mAP: 59.2% FPS: 0.47 Jun, 2014 YOLO Jun, 2015 Fast R-CNN mAP: 66.9% FPS: 0.5 Apr, 2015 Faster R-CNN mAP: 69.9% FPS: 5 Jun, 2015
  • 57. 57You Only Look Once: Uni ied, Real-Time Object Detection YOLO’s pipeline YOLO (1)
  • 58. 58You Only Look Once: Uni ied, Real-Time Object Detection Bottom layers from GoogLeNet Custom layers YOLO architecture YOLO (2)
  • 59. 59 Pros: ● uite fast (~40 FPS on Nvidia Titan Black) ● End-to-end training ● Low Error Rate for Foreground/Background misclassi ication ● Learn very general representation of objects Cons: ● Less accurate than Fast R CNN (63.9% mAP comparte to 66.9%) ● Loss function is an approximation ● Can not detect small objects ● Low detection rate of objects that located close to each other You Only Look Once: Unified, Real-Time Object Detection Errors types comparison Fast R CNN vs YOLO YOLO (3)
  • 60. Single Shot MultiBox Detector (SSD) Viola-Jones detector CVPR, 2001 Selective Search mAP: 35.1% IJCV, 2013 R-CNN mAP: 53.7% FPS: 0.05 Nov, 2013 SPP-Net mAP: 59.2% FPS: 0.47 Jun, 2014 YOLO mAP: 63.9% FPS: 40 Jun, 2015 Faster R-CNN mAP: 69.9% FPS: 5 Jun, 2015 Fast R-CNN mAP: 66.9% FPS: 0.5 Apr, 2015 SSD Dec, 2015
  • 61. 61SSD: Single Shot MultiBox Detector SSD architecture SSD (1)
  • 62. 62 Apply regressors to default box and get result Regressors Confidences for 21 classes (20 VOC Pascal 2007 classes + background) 3 default boxes for each cell SSD: Single Shot MultiBox Detector SSD detector example SSD (2)
  • 63. 63 Model mAP FPS Faster R-CNN (VGG-16) 73.2% 7 Faster R-CNN (ZF) 62.1% 17 YOLO 63.4% 45 Tiny YOLO 52.7% 155 SSD300 (VGG-16) 72.1% 58 SSD500 (VGG-16) 75.1% 23 Pros: ● The best speed/accuracy trade-offs ● State of the art results on all object detection datasets ● Pretty well works with light feature extractors (InceprtionV2, S ueeze Net, MobileNet, Shu leNet, etc.) Cons: ● Default boxes as hyper parameter ● Poorly works with heavy feature extractors (ResNet-101, InceptionV4, VGG-16, etc.) SSD: Single Shot MultiBox Detector Comparison of SSD with other detectors SSD (3)
  • 65. Multi-task cascade NN (MTCNN) Viola-Jones detector CVPR, 2001 Selective Search mAP: 35.1% IJCV, 2013 R-CNN mAP: 53.7% FPS: 0.05 Nov, 2013 SPP-Net mAP: 59.2% FPS: 0.47 Jun, 2014 YOLO mAP: 63.9% FPS: 40 Jun, 2015 Faster R-CNN mAP: 69.9% FPS: 5 Jun, 2015 Fast R-CNN mAP: 66.9% FPS: 0.5 Apr, 2015 SSD mAP: 72.1% FPS: 58 Dec, 2015 MTCNN Apr, 2016
  • 66. 66 Network Input size FPS* Validation Accuracy P-Net 12x12 8000 94.6% R-Net 24x24 650 95.4% O-Net 48x48 220 95.4% Networks speed and accuracy on crops * - for original network input and batch size 1 Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks MTCNN (1)
  • 67. 67 MTCNN s Networks Architectures Landmarks example Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks MTCNN (2)
  • 68. 68 Recall/Precision curve Test set o Wider Face date set Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks MTCNN (3)
  • 69. 69 Pros: ● Really fast (100 FPS on GPU) ● Lot of speed/accuracy trade-offs ● State of the art results on big part of Face Detection Datasets (CelebA, FDDB, etc.) Cons: ● Hard to train ● Lot of hyper-parameters ● Low detection rate of small faces ● Poorly works without landmarks Model mAP FPS MTCNN 85.1% 100 Faster R-CNN (VGG-16) 93.2% 5 SSH (VGG-16) 91.9% 10 Different face detector models comparison Wider Face test set Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks MTCNN (4)
  • 71. 71 Thanks for your attention! Contact information: alexander.zarichkovyi@ring.com