SlideShare a Scribd company logo
Visual Attention
Zahra Sadeghi
1
Overview
• Attention
• Visual saliency
• Bottom-up attention
• Koch-Ulman framework
• Visual Attention in brain
• Coarse to Fine theory
• Top-Down Facilitation
• Comparing Attentional Neural Network with human behavior
2
Attention
• Attention implements an information-processing bottleneck that
allows only a small part of the incoming sensory information to reach
short-term memory and visual awareness.
• key challenge is to select which impressions are relevant and which
inputs should be ignored.
• This process of selecting a subset of the input, and ignoring the rest, is
referred to as attention
• bottom-up and top-down attention, or stimulus-driven and goal-
oriented attention
3
Visual saliency
• At a pre-attentive stage some parts
of the scene may pop out.
• Visual saliency refers to the idea that
certain parts of a scene are pre-
attentively distinctive and create
some form of immediate significant
visual arousal
• how can a machine vision system
extract the salient regions from an
unknown background?
4
1. low level feature
extraction
2. Saliency map
creation
3. Winner-Take-All
(WTA)
4. Inhibition of Return
(IoR)
5. Top-down attentional
bias
Flow diagram of a typical model for the control of attention
5
Feature extraction








0
0
0
2
/
)
(
R
R
b
g
r
R








0
0
0
2
/
)
(
G
G
b
r
g
G








0
0
0
2
/
)
(
B
B
g
r
b
B










0
0
0
2
/
2
/
)
(
Y
Y
b
g
r
g
r
Y
3
/
)
( b
g
r
I 
















cos
sin
sin
cos
)
2
cos(
)
2
exp(
)
,
,
,
,
;
,
(
'
'
'
2
2
'
2
2
'
y
x
y
y
x
x
x
y
x
y
x
g









Orientation feature Map: using Gabor filters with four
orientations (0,45,90,135)
3
/
)
( b
g
r
I 


6
Original image R G B
Y I O (0) O (45)
O (90) O (135) 7
R
Y
O(0)
8
9
Saliency map construction
1- Cross-scaling sum on all created feature channels
))
(
),
(
),
(
),
(
(
))
(
(
))
(
),
(
),
(
),
(
(
4
3
2
1
3
1
3
1
3
1
s
S
s
S
s
S
s
S
S
s
S
S
s
S
s
S
s
S
s
S
S
O
O
O
O
s
O
I
s
I
Y
B
G
R
s
c









3- Saliency maps are then smoothed
with Gaussian filter
O
o
I
i
C
c S
W
S
W
S
W
S *
*
* 


2- Integrated saliency map
c
S I
S
O
S
10
Segmentation
• Threshold segmentation (the saliency map is converted into a binary
image using a threshold)
)
(
)
(
0
)
(
1
)
(
sa
E
threshold
threshold
x
sa
threshold
x
sa
x
bm







}
)
(
{ 



 A
B
z
B
A z
dilation erosion 11
• The ventral (’what’) stream processes visual
shape appearance and is largely responsible
for object recognition.
• The dorsal (’where’) stream encodes spatial
locations and processes motion information.
• Bottom-up information that can guide
attention propagates thus from the visual
cortex to the PFC.
• PFC areas can provide top-down signals to
control attention to some degree
How does the brain process attention?
12
• coarse, low spatial frequency (LSF)
information is processed first
• quickly projects from primary visual
cortex to higher level visual areas (PFC, OFC)
• Psychophysical and single-unit recordings in monkeys
indicate that low spatial frequencies are extracted from
scenes earlier than high spatial frequencies
13
14
• We trained a 3 layer deep belief
network and performed an
unsupervised learning scheme
on the obtained deep
representations.
Developmental learning in DNNs: Fine to coarse development
• There’s a progression in
depth in hidden layers of
DBN where low level layers
represent finer distinctions
and high level layers
represent coarser
distinctions
Sadeghi, Zahra. "Deep learning and developmental learning: emergence of fine-to-coarse conceptual categories at layers of deep belief
network." Perception 45.9 (2016): 1036-1045.
• Input to the visual system is often noisy and ambiguous
• a growing body of theoretical work and empirical evidence support the idea
that visual recognition is facilitated by top-down expectations
• Context facilitates the recognition of related objects even if these objects are
ambiguous when seen in isolation
• an ambiguous object becomes recognizable if another object that shares the
same context is placed in an appropriate spatial relation to it.
15
Top-down processing contribution
+ +
inconsistent case consistent case
Effect of context in occluded object recognition
500 ms 500 ms
'Type the name of the object and then press enter’
300 ms
300 ms
16
Sadeghi, Zahra. "The effect of top-down attention in occluded object recognition." arXiv preprint arXiv:2007.10232 (2020).
+ +
+
+
Consistent setting inconsistent setting
Easy case
17
18
Hit const vs
hit inconst
Miss const vs
miss inconst
Sup hit const vs
sup hit inconst
Sup miss const vs
sup miss inconst
Hypo_pos1 vs
hypo_neg1
Hypo_pos2 vs
hypo_neg2
Resp-time
const vs
inconst
p-val 0.0027 0.0027 0.0027 0.0027 0.0027 0.0027 4.6921e-11
Sadeghi, Zahra. "The effect of top-down attention in occluded object recognition." arXiv preprint arXiv:2007.10232 (2020).
Clickme.ai experiment
• Collect human feature
importance map for
objects
19
Global-And-Local-Attention (GALA)
• Global-and-Local-attention (GALA) network extends the squeeze-and-
excitation (SE) network by adding a local saliency module.
• The attention mechanism is embedded in the cost function as a
regularization term
20
• three cases are considered:
1- networks trained on color images and tested on color images.
2- networks trained on grayscale image and tested on grayscale images.
3- networks trained on color images and tested on grayscale image.
the best performance in both color and grayscale
cases is achieved by gala click, while gala no click
and no gala no click obtained second and third best
results respectively.
the highest accuracy for all models is attributed to
the case in which images are trained on colorful
images and tested on colorful images.
21
Sadeghi, Zahra. "An Investigation on Performance of Attention Deep Neural Networks in Rapid Object
Recognition." Intelligent Computing Systems: Third International Symposium, ISICS 2020, Sharjah, United Arab Emirates,
March 18–19, 2020, Proceedings 3. Springer International Publishing, 2020.
• to test the effect of importance maps
collected in clickme.ai experiment, a rapid
object recognition experiment was
designed
• The dataset contains 100 images from
animal and non-animal.
• Phase scrambled masks are applied to
images
• eleven versions of each image ordered
ascendingly based on their level of pixel
revelation of important pixels.
22
Model and human performance
• Average accuracy of the two gala models
(gala-click and gala no-click) and ResNet-50
model (no-gala-no-click) is compared on
the behavioral test images at different
levels of pixel revelation.
• gala click and gala no click models
achieved similar accuracy.
• gala click model produces superior results
compared to all other models in full pixel
revelation.
• The second best performance in full level,
is achieved by gala-no-click model.
23
Sadeghi, Zahra. "An Investigation on Performance of Attention Deep Neural Networks in Rapid Object
Recognition." Intelligent Computing Systems: Third International Symposium, ISICS 2020, Sharjah, United Arab Emirates,
March 18–19, 2020, Proceedings 3. Springer International Publishing, 2020.
• Human visual attention is well-studied
• while there exist different models, they lack computational efficacy of
our visual system
• Attention Mechanisms in Neural Networks are still loosely based on
the visual attention mechanism found in humans.
24
Thanks for your attention 
25

More Related Content

Similar to Attention mechanism in brain and deep neural network

Top object detection algorithms in deep neural networks
Top object detection algorithms in deep neural networksTop object detection algorithms in deep neural networks
Top object detection algorithms in deep neural networksApuChandraw
 
A Deep Belief Network Approach to Learning Depth from Optical Flow
A Deep Belief Network Approach to Learning Depth from Optical FlowA Deep Belief Network Approach to Learning Depth from Optical Flow
A Deep Belief Network Approach to Learning Depth from Optical FlowReuben Feinman
 
Deep learning for pose-invariant face detection in unconstrained environment
Deep learning for pose-invariant face detection in unconstrained environmentDeep learning for pose-invariant face detection in unconstrained environment
Deep learning for pose-invariant face detection in unconstrained environmentIJECEIAES
 
GPU Computing for Cognitive Robotics
GPU Computing for Cognitive RoboticsGPU Computing for Cognitive Robotics
GPU Computing for Cognitive RoboticsMartin Peniak
 
IRJET- Real-Time Object Detection using Deep Learning: A Survey
IRJET- Real-Time Object Detection using Deep Learning: A SurveyIRJET- Real-Time Object Detection using Deep Learning: A Survey
IRJET- Real-Time Object Detection using Deep Learning: A SurveyIRJET Journal
 
Recent advances of AI for medical imaging : Engineering perspectives
Recent advances of AI for medical imaging : Engineering perspectivesRecent advances of AI for medical imaging : Engineering perspectives
Recent advances of AI for medical imaging : Engineering perspectivesNamkug Kim
 
Deep Learning in Robotics: Robot gains Social Intelligence through Multimodal...
Deep Learning in Robotics: Robot gains Social Intelligence through Multimodal...Deep Learning in Robotics: Robot gains Social Intelligence through Multimodal...
Deep Learning in Robotics: Robot gains Social Intelligence through Multimodal...gabrielesisinna
 
Dynamic routing between capsules - A brief presentation
Dynamic routing between capsules - A brief presentationDynamic routing between capsules - A brief presentation
Dynamic routing between capsules - A brief presentationRomain Sabathé
 
Neural Networks and Deep Learning: An Intro
Neural Networks and Deep Learning: An IntroNeural Networks and Deep Learning: An Intro
Neural Networks and Deep Learning: An IntroFariz Darari
 
A Survey of Deep Learning Algorithms for Malware Detection
A Survey of Deep Learning Algorithms for Malware DetectionA Survey of Deep Learning Algorithms for Malware Detection
A Survey of Deep Learning Algorithms for Malware DetectionIJCSIS Research Publications
 
20141003.journal club
20141003.journal club20141003.journal club
20141003.journal clubHayaru SHOUNO
 
Scene recognition using Convolutional Neural Network
Scene recognition using Convolutional Neural NetworkScene recognition using Convolutional Neural Network
Scene recognition using Convolutional Neural NetworkDhirajGidde
 
Fcv bio cv_cottrell
Fcv bio cv_cottrellFcv bio cv_cottrell
Fcv bio cv_cottrellzukun
 
Fcv bio cv_cottrell
Fcv bio cv_cottrellFcv bio cv_cottrell
Fcv bio cv_cottrellzukun
 
Facial emotion detection on babies' emotional face using Deep Learning.
Facial emotion detection on babies' emotional face using Deep Learning.Facial emotion detection on babies' emotional face using Deep Learning.
Facial emotion detection on babies' emotional face using Deep Learning.Takrim Ul Islam Laskar
 
one shot15729752 Deep Learning for AI and DS
one shot15729752 Deep Learning for AI and DSone shot15729752 Deep Learning for AI and DS
one shot15729752 Deep Learning for AI and DSManiMaran230751
 
Deep learning - A Visual Introduction
Deep learning - A Visual IntroductionDeep learning - A Visual Introduction
Deep learning - A Visual IntroductionLukas Masuch
 

Similar to Attention mechanism in brain and deep neural network (20)

Top object detection algorithms in deep neural networks
Top object detection algorithms in deep neural networksTop object detection algorithms in deep neural networks
Top object detection algorithms in deep neural networks
 
A Deep Belief Network Approach to Learning Depth from Optical Flow
A Deep Belief Network Approach to Learning Depth from Optical FlowA Deep Belief Network Approach to Learning Depth from Optical Flow
A Deep Belief Network Approach to Learning Depth from Optical Flow
 
Learning where to look: focus and attention in deep vision
Learning where to look: focus and attention in deep visionLearning where to look: focus and attention in deep vision
Learning where to look: focus and attention in deep vision
 
Deep learning for pose-invariant face detection in unconstrained environment
Deep learning for pose-invariant face detection in unconstrained environmentDeep learning for pose-invariant face detection in unconstrained environment
Deep learning for pose-invariant face detection in unconstrained environment
 
GPU Computing for Cognitive Robotics
GPU Computing for Cognitive RoboticsGPU Computing for Cognitive Robotics
GPU Computing for Cognitive Robotics
 
IRJET- Real-Time Object Detection using Deep Learning: A Survey
IRJET- Real-Time Object Detection using Deep Learning: A SurveyIRJET- Real-Time Object Detection using Deep Learning: A Survey
IRJET- Real-Time Object Detection using Deep Learning: A Survey
 
Recent advances of AI for medical imaging : Engineering perspectives
Recent advances of AI for medical imaging : Engineering perspectivesRecent advances of AI for medical imaging : Engineering perspectives
Recent advances of AI for medical imaging : Engineering perspectives
 
Deep Learning in Robotics: Robot gains Social Intelligence through Multimodal...
Deep Learning in Robotics: Robot gains Social Intelligence through Multimodal...Deep Learning in Robotics: Robot gains Social Intelligence through Multimodal...
Deep Learning in Robotics: Robot gains Social Intelligence through Multimodal...
 
Dynamic routing between capsules - A brief presentation
Dynamic routing between capsules - A brief presentationDynamic routing between capsules - A brief presentation
Dynamic routing between capsules - A brief presentation
 
Neural Networks and Deep Learning: An Intro
Neural Networks and Deep Learning: An IntroNeural Networks and Deep Learning: An Intro
Neural Networks and Deep Learning: An Intro
 
A Survey of Deep Learning Algorithms for Malware Detection
A Survey of Deep Learning Algorithms for Malware DetectionA Survey of Deep Learning Algorithms for Malware Detection
A Survey of Deep Learning Algorithms for Malware Detection
 
Introduction to Deep learning
Introduction to Deep learningIntroduction to Deep learning
Introduction to Deep learning
 
20141003.journal club
20141003.journal club20141003.journal club
20141003.journal club
 
Scene recognition using Convolutional Neural Network
Scene recognition using Convolutional Neural NetworkScene recognition using Convolutional Neural Network
Scene recognition using Convolutional Neural Network
 
Deborah_Sandoval
Deborah_SandovalDeborah_Sandoval
Deborah_Sandoval
 
Fcv bio cv_cottrell
Fcv bio cv_cottrellFcv bio cv_cottrell
Fcv bio cv_cottrell
 
Fcv bio cv_cottrell
Fcv bio cv_cottrellFcv bio cv_cottrell
Fcv bio cv_cottrell
 
Facial emotion detection on babies' emotional face using Deep Learning.
Facial emotion detection on babies' emotional face using Deep Learning.Facial emotion detection on babies' emotional face using Deep Learning.
Facial emotion detection on babies' emotional face using Deep Learning.
 
one shot15729752 Deep Learning for AI and DS
one shot15729752 Deep Learning for AI and DSone shot15729752 Deep Learning for AI and DS
one shot15729752 Deep Learning for AI and DS
 
Deep learning - A Visual Introduction
Deep learning - A Visual IntroductionDeep learning - A Visual Introduction
Deep learning - A Visual Introduction
 

More from Zahra Sadeghi

Maritime Anomaly Detection
Maritime Anomaly DetectionMaritime Anomaly Detection
Maritime Anomaly DetectionZahra Sadeghi
 
Quality Assurance in Modern Software Development
Quality Assurance in Modern Software DevelopmentQuality Assurance in Modern Software Development
Quality Assurance in Modern Software DevelopmentZahra Sadeghi
 
Perception, representation, structure, and recognition
Perception, representation, structure, and recognitionPerception, representation, structure, and recognition
Perception, representation, structure, and recognitionZahra Sadeghi
 
An introduction to Autonomous mobile robots
An introduction to Autonomous mobile robotsAn introduction to Autonomous mobile robots
An introduction to Autonomous mobile robotsZahra Sadeghi
 
Bluetooth Technoloty
Bluetooth TechnolotyBluetooth Technoloty
Bluetooth TechnolotyZahra Sadeghi
 
Self Organization Map
Self Organization MapSelf Organization Map
Self Organization MapZahra Sadeghi
 
A survey on ant colony clustering papers
A survey on ant colony clustering papersA survey on ant colony clustering papers
A survey on ant colony clustering papersZahra Sadeghi
 
Pittssburgh approach
Pittssburgh approachPittssburgh approach
Pittssburgh approachZahra Sadeghi
 
Cerebellar Model Articulation Controller
Cerebellar Model Articulation ControllerCerebellar Model Articulation Controller
Cerebellar Model Articulation ControllerZahra Sadeghi
 
Semantic Search with Semantic Web
Semantic Search with Semantic WebSemantic Search with Semantic Web
Semantic Search with Semantic WebZahra Sadeghi
 
Interval programming
Interval programming Interval programming
Interval programming Zahra Sadeghi
 
16-bit microprocessors
16-bit microprocessors16-bit microprocessors
16-bit microprocessorsZahra Sadeghi
 
Ms dos boot process
Ms dos boot process Ms dos boot process
Ms dos boot process Zahra Sadeghi
 
An Introduction to threads
An Introduction to threadsAn Introduction to threads
An Introduction to threadsZahra Sadeghi
 
An intoroduction to Multimedia
An intoroduction to MultimediaAn intoroduction to Multimedia
An intoroduction to MultimediaZahra Sadeghi
 
Parametric and non parametric classifiers
Parametric and non parametric classifiersParametric and non parametric classifiers
Parametric and non parametric classifiersZahra Sadeghi
 

More from Zahra Sadeghi (20)

Maritime Anomaly Detection
Maritime Anomaly DetectionMaritime Anomaly Detection
Maritime Anomaly Detection
 
Quality Assurance in Modern Software Development
Quality Assurance in Modern Software DevelopmentQuality Assurance in Modern Software Development
Quality Assurance in Modern Software Development
 
Perception, representation, structure, and recognition
Perception, representation, structure, and recognitionPerception, representation, structure, and recognition
Perception, representation, structure, and recognition
 
An introduction to Autonomous mobile robots
An introduction to Autonomous mobile robotsAn introduction to Autonomous mobile robots
An introduction to Autonomous mobile robots
 
Bluetooth Technoloty
Bluetooth TechnolotyBluetooth Technoloty
Bluetooth Technoloty
 
Self Organization Map
Self Organization MapSelf Organization Map
Self Organization Map
 
A survey on ant colony clustering papers
A survey on ant colony clustering papersA survey on ant colony clustering papers
A survey on ant colony clustering papers
 
Pittssburgh approach
Pittssburgh approachPittssburgh approach
Pittssburgh approach
 
Cerebellar Model Articulation Controller
Cerebellar Model Articulation ControllerCerebellar Model Articulation Controller
Cerebellar Model Articulation Controller
 
Semantic Search with Semantic Web
Semantic Search with Semantic WebSemantic Search with Semantic Web
Semantic Search with Semantic Web
 
Interval programming
Interval programming Interval programming
Interval programming
 
16-bit microprocessors
16-bit microprocessors16-bit microprocessors
16-bit microprocessors
 
Logic converter
Logic converterLogic converter
Logic converter
 
Ms dos boot process
Ms dos boot process Ms dos boot process
Ms dos boot process
 
An Introduction to threads
An Introduction to threadsAn Introduction to threads
An Introduction to threads
 
An intoroduction to Multimedia
An intoroduction to MultimediaAn intoroduction to Multimedia
An intoroduction to Multimedia
 
Penalty function
Penalty function Penalty function
Penalty function
 
Neural networks
Neural networksNeural networks
Neural networks
 
Parametric and non parametric classifiers
Parametric and non parametric classifiersParametric and non parametric classifiers
Parametric and non parametric classifiers
 
sampling
samplingsampling
sampling
 

Recently uploaded

Innovative Methods in Media and Communication Research by Sebastian Kubitschk...
Innovative Methods in Media and Communication Research by Sebastian Kubitschk...Innovative Methods in Media and Communication Research by Sebastian Kubitschk...
Innovative Methods in Media and Communication Research by Sebastian Kubitschk...correoyaya
 
2024 Q1 Tableau User Group Leader Quarterly Call
2024 Q1 Tableau User Group Leader Quarterly Call2024 Q1 Tableau User Group Leader Quarterly Call
2024 Q1 Tableau User Group Leader Quarterly Calllward7
 
basics of data science with application areas.pdf
basics of data science with application areas.pdfbasics of data science with application areas.pdf
basics of data science with application areas.pdfvyankatesh1
 
Machine Learning For Career Growth..pptx
Machine Learning For Career Growth..pptxMachine Learning For Career Growth..pptx
Machine Learning For Career Growth..pptxbenishzehra469
 
2024-05-14 - Tableau User Group - TC24 Hot Topics - Tableau Pulse and Einstei...
2024-05-14 - Tableau User Group - TC24 Hot Topics - Tableau Pulse and Einstei...2024-05-14 - Tableau User Group - TC24 Hot Topics - Tableau Pulse and Einstei...
2024-05-14 - Tableau User Group - TC24 Hot Topics - Tableau Pulse and Einstei...elinavihriala
 
Investigate & Recover / StarCompliance.io / Crypto_Crimes
Investigate & Recover / StarCompliance.io / Crypto_CrimesInvestigate & Recover / StarCompliance.io / Crypto_Crimes
Investigate & Recover / StarCompliance.io / Crypto_CrimesStarCompliance.io
 
how can i exchange pi coins for others currency like Bitcoin
how can i exchange pi coins for others currency like Bitcoinhow can i exchange pi coins for others currency like Bitcoin
how can i exchange pi coins for others currency like BitcoinDOT TECH
 
2024 Q2 Orange County (CA) Tableau User Group Meeting
2024 Q2 Orange County (CA) Tableau User Group Meeting2024 Q2 Orange County (CA) Tableau User Group Meeting
2024 Q2 Orange County (CA) Tableau User Group MeetingAlison Pitt
 
AI Imagen for data-storytelling Infographics.pdf
AI Imagen for data-storytelling Infographics.pdfAI Imagen for data-storytelling Infographics.pdf
AI Imagen for data-storytelling Infographics.pdfMichaelSenkow
 
Business update Q1 2024 Lar España Real Estate SOCIMI
Business update Q1 2024 Lar España Real Estate SOCIMIBusiness update Q1 2024 Lar España Real Estate SOCIMI
Business update Q1 2024 Lar España Real Estate SOCIMIAlejandraGmez176757
 
Pre-ProductionImproveddsfjgndflghtgg.pptx
Pre-ProductionImproveddsfjgndflghtgg.pptxPre-ProductionImproveddsfjgndflghtgg.pptx
Pre-ProductionImproveddsfjgndflghtgg.pptxStephen266013
 
Using PDB Relocation to Move a Single PDB to Another Existing CDB
Using PDB Relocation to Move a Single PDB to Another Existing CDBUsing PDB Relocation to Move a Single PDB to Another Existing CDB
Using PDB Relocation to Move a Single PDB to Another Existing CDBAlireza Kamrani
 
Jpolillo Amazon PPC - Bid Optimization Sample
Jpolillo Amazon PPC - Bid Optimization SampleJpolillo Amazon PPC - Bid Optimization Sample
Jpolillo Amazon PPC - Bid Optimization SampleJames Polillo
 
Webinar One View, Multiple Systems No-Code Integration of Salesforce and ERPs
Webinar One View, Multiple Systems No-Code Integration of Salesforce and ERPsWebinar One View, Multiple Systems No-Code Integration of Salesforce and ERPs
Webinar One View, Multiple Systems No-Code Integration of Salesforce and ERPsCEPTES Software Inc
 
How can I successfully sell my pi coins in Philippines?
How can I successfully sell my pi coins in Philippines?How can I successfully sell my pi coins in Philippines?
How can I successfully sell my pi coins in Philippines?DOT TECH
 
Tabula.io Cheatsheet: automate your data workflows
Tabula.io Cheatsheet: automate your data workflowsTabula.io Cheatsheet: automate your data workflows
Tabula.io Cheatsheet: automate your data workflowsalex933524
 
Artificial_General_Intelligence__storm_gen_article.pdf
Artificial_General_Intelligence__storm_gen_article.pdfArtificial_General_Intelligence__storm_gen_article.pdf
Artificial_General_Intelligence__storm_gen_article.pdfscitechtalktv
 
社内勉強会資料_LLM Agents                              .
社内勉強会資料_LLM Agents                              .社内勉強会資料_LLM Agents                              .
社内勉強会資料_LLM Agents                              .NABLAS株式会社
 
Supply chain analytics to combat the effects of Ukraine-Russia-conflict
Supply chain analytics to combat the effects of Ukraine-Russia-conflictSupply chain analytics to combat the effects of Ukraine-Russia-conflict
Supply chain analytics to combat the effects of Ukraine-Russia-conflictJack Cole
 

Recently uploaded (20)

Innovative Methods in Media and Communication Research by Sebastian Kubitschk...
Innovative Methods in Media and Communication Research by Sebastian Kubitschk...Innovative Methods in Media and Communication Research by Sebastian Kubitschk...
Innovative Methods in Media and Communication Research by Sebastian Kubitschk...
 
Slip-and-fall Injuries: Top Workers' Comp Claims
Slip-and-fall Injuries: Top Workers' Comp ClaimsSlip-and-fall Injuries: Top Workers' Comp Claims
Slip-and-fall Injuries: Top Workers' Comp Claims
 
2024 Q1 Tableau User Group Leader Quarterly Call
2024 Q1 Tableau User Group Leader Quarterly Call2024 Q1 Tableau User Group Leader Quarterly Call
2024 Q1 Tableau User Group Leader Quarterly Call
 
basics of data science with application areas.pdf
basics of data science with application areas.pdfbasics of data science with application areas.pdf
basics of data science with application areas.pdf
 
Machine Learning For Career Growth..pptx
Machine Learning For Career Growth..pptxMachine Learning For Career Growth..pptx
Machine Learning For Career Growth..pptx
 
2024-05-14 - Tableau User Group - TC24 Hot Topics - Tableau Pulse and Einstei...
2024-05-14 - Tableau User Group - TC24 Hot Topics - Tableau Pulse and Einstei...2024-05-14 - Tableau User Group - TC24 Hot Topics - Tableau Pulse and Einstei...
2024-05-14 - Tableau User Group - TC24 Hot Topics - Tableau Pulse and Einstei...
 
Investigate & Recover / StarCompliance.io / Crypto_Crimes
Investigate & Recover / StarCompliance.io / Crypto_CrimesInvestigate & Recover / StarCompliance.io / Crypto_Crimes
Investigate & Recover / StarCompliance.io / Crypto_Crimes
 
how can i exchange pi coins for others currency like Bitcoin
how can i exchange pi coins for others currency like Bitcoinhow can i exchange pi coins for others currency like Bitcoin
how can i exchange pi coins for others currency like Bitcoin
 
2024 Q2 Orange County (CA) Tableau User Group Meeting
2024 Q2 Orange County (CA) Tableau User Group Meeting2024 Q2 Orange County (CA) Tableau User Group Meeting
2024 Q2 Orange County (CA) Tableau User Group Meeting
 
AI Imagen for data-storytelling Infographics.pdf
AI Imagen for data-storytelling Infographics.pdfAI Imagen for data-storytelling Infographics.pdf
AI Imagen for data-storytelling Infographics.pdf
 
Business update Q1 2024 Lar España Real Estate SOCIMI
Business update Q1 2024 Lar España Real Estate SOCIMIBusiness update Q1 2024 Lar España Real Estate SOCIMI
Business update Q1 2024 Lar España Real Estate SOCIMI
 
Pre-ProductionImproveddsfjgndflghtgg.pptx
Pre-ProductionImproveddsfjgndflghtgg.pptxPre-ProductionImproveddsfjgndflghtgg.pptx
Pre-ProductionImproveddsfjgndflghtgg.pptx
 
Using PDB Relocation to Move a Single PDB to Another Existing CDB
Using PDB Relocation to Move a Single PDB to Another Existing CDBUsing PDB Relocation to Move a Single PDB to Another Existing CDB
Using PDB Relocation to Move a Single PDB to Another Existing CDB
 
Jpolillo Amazon PPC - Bid Optimization Sample
Jpolillo Amazon PPC - Bid Optimization SampleJpolillo Amazon PPC - Bid Optimization Sample
Jpolillo Amazon PPC - Bid Optimization Sample
 
Webinar One View, Multiple Systems No-Code Integration of Salesforce and ERPs
Webinar One View, Multiple Systems No-Code Integration of Salesforce and ERPsWebinar One View, Multiple Systems No-Code Integration of Salesforce and ERPs
Webinar One View, Multiple Systems No-Code Integration of Salesforce and ERPs
 
How can I successfully sell my pi coins in Philippines?
How can I successfully sell my pi coins in Philippines?How can I successfully sell my pi coins in Philippines?
How can I successfully sell my pi coins in Philippines?
 
Tabula.io Cheatsheet: automate your data workflows
Tabula.io Cheatsheet: automate your data workflowsTabula.io Cheatsheet: automate your data workflows
Tabula.io Cheatsheet: automate your data workflows
 
Artificial_General_Intelligence__storm_gen_article.pdf
Artificial_General_Intelligence__storm_gen_article.pdfArtificial_General_Intelligence__storm_gen_article.pdf
Artificial_General_Intelligence__storm_gen_article.pdf
 
社内勉強会資料_LLM Agents                              .
社内勉強会資料_LLM Agents                              .社内勉強会資料_LLM Agents                              .
社内勉強会資料_LLM Agents                              .
 
Supply chain analytics to combat the effects of Ukraine-Russia-conflict
Supply chain analytics to combat the effects of Ukraine-Russia-conflictSupply chain analytics to combat the effects of Ukraine-Russia-conflict
Supply chain analytics to combat the effects of Ukraine-Russia-conflict
 

Attention mechanism in brain and deep neural network

  • 2. Overview • Attention • Visual saliency • Bottom-up attention • Koch-Ulman framework • Visual Attention in brain • Coarse to Fine theory • Top-Down Facilitation • Comparing Attentional Neural Network with human behavior 2
  • 3. Attention • Attention implements an information-processing bottleneck that allows only a small part of the incoming sensory information to reach short-term memory and visual awareness. • key challenge is to select which impressions are relevant and which inputs should be ignored. • This process of selecting a subset of the input, and ignoring the rest, is referred to as attention • bottom-up and top-down attention, or stimulus-driven and goal- oriented attention 3
  • 4. Visual saliency • At a pre-attentive stage some parts of the scene may pop out. • Visual saliency refers to the idea that certain parts of a scene are pre- attentively distinctive and create some form of immediate significant visual arousal • how can a machine vision system extract the salient regions from an unknown background? 4
  • 5. 1. low level feature extraction 2. Saliency map creation 3. Winner-Take-All (WTA) 4. Inhibition of Return (IoR) 5. Top-down attentional bias Flow diagram of a typical model for the control of attention 5
  • 6. Feature extraction         0 0 0 2 / ) ( R R b g r R         0 0 0 2 / ) ( G G b r g G         0 0 0 2 / ) ( B B g r b B           0 0 0 2 / 2 / ) ( Y Y b g r g r Y 3 / ) ( b g r I                  cos sin sin cos ) 2 cos( ) 2 exp( ) , , , , ; , ( ' ' ' 2 2 ' 2 2 ' y x y y x x x y x y x g          Orientation feature Map: using Gabor filters with four orientations (0,45,90,135) 3 / ) ( b g r I    6
  • 7. Original image R G B Y I O (0) O (45) O (90) O (135) 7
  • 9. 9
  • 10. Saliency map construction 1- Cross-scaling sum on all created feature channels )) ( ), ( ), ( ), ( ( )) ( ( )) ( ), ( ), ( ), ( ( 4 3 2 1 3 1 3 1 3 1 s S s S s S s S S s S S s S s S s S s S S O O O O s O I s I Y B G R s c          3- Saliency maps are then smoothed with Gaussian filter O o I i C c S W S W S W S * * *    2- Integrated saliency map c S I S O S 10
  • 11. Segmentation • Threshold segmentation (the saliency map is converted into a binary image using a threshold) ) ( ) ( 0 ) ( 1 ) ( sa E threshold threshold x sa threshold x sa x bm        } ) ( {      A B z B A z dilation erosion 11
  • 12. • The ventral (’what’) stream processes visual shape appearance and is largely responsible for object recognition. • The dorsal (’where’) stream encodes spatial locations and processes motion information. • Bottom-up information that can guide attention propagates thus from the visual cortex to the PFC. • PFC areas can provide top-down signals to control attention to some degree How does the brain process attention? 12
  • 13. • coarse, low spatial frequency (LSF) information is processed first • quickly projects from primary visual cortex to higher level visual areas (PFC, OFC) • Psychophysical and single-unit recordings in monkeys indicate that low spatial frequencies are extracted from scenes earlier than high spatial frequencies 13
  • 14. 14 • We trained a 3 layer deep belief network and performed an unsupervised learning scheme on the obtained deep representations. Developmental learning in DNNs: Fine to coarse development • There’s a progression in depth in hidden layers of DBN where low level layers represent finer distinctions and high level layers represent coarser distinctions Sadeghi, Zahra. "Deep learning and developmental learning: emergence of fine-to-coarse conceptual categories at layers of deep belief network." Perception 45.9 (2016): 1036-1045.
  • 15. • Input to the visual system is often noisy and ambiguous • a growing body of theoretical work and empirical evidence support the idea that visual recognition is facilitated by top-down expectations • Context facilitates the recognition of related objects even if these objects are ambiguous when seen in isolation • an ambiguous object becomes recognizable if another object that shares the same context is placed in an appropriate spatial relation to it. 15 Top-down processing contribution
  • 16. + + inconsistent case consistent case Effect of context in occluded object recognition 500 ms 500 ms 'Type the name of the object and then press enter’ 300 ms 300 ms 16 Sadeghi, Zahra. "The effect of top-down attention in occluded object recognition." arXiv preprint arXiv:2007.10232 (2020).
  • 17. + + + + Consistent setting inconsistent setting Easy case 17
  • 18. 18 Hit const vs hit inconst Miss const vs miss inconst Sup hit const vs sup hit inconst Sup miss const vs sup miss inconst Hypo_pos1 vs hypo_neg1 Hypo_pos2 vs hypo_neg2 Resp-time const vs inconst p-val 0.0027 0.0027 0.0027 0.0027 0.0027 0.0027 4.6921e-11 Sadeghi, Zahra. "The effect of top-down attention in occluded object recognition." arXiv preprint arXiv:2007.10232 (2020).
  • 19. Clickme.ai experiment • Collect human feature importance map for objects 19
  • 20. Global-And-Local-Attention (GALA) • Global-and-Local-attention (GALA) network extends the squeeze-and- excitation (SE) network by adding a local saliency module. • The attention mechanism is embedded in the cost function as a regularization term 20
  • 21. • three cases are considered: 1- networks trained on color images and tested on color images. 2- networks trained on grayscale image and tested on grayscale images. 3- networks trained on color images and tested on grayscale image. the best performance in both color and grayscale cases is achieved by gala click, while gala no click and no gala no click obtained second and third best results respectively. the highest accuracy for all models is attributed to the case in which images are trained on colorful images and tested on colorful images. 21 Sadeghi, Zahra. "An Investigation on Performance of Attention Deep Neural Networks in Rapid Object Recognition." Intelligent Computing Systems: Third International Symposium, ISICS 2020, Sharjah, United Arab Emirates, March 18–19, 2020, Proceedings 3. Springer International Publishing, 2020.
  • 22. • to test the effect of importance maps collected in clickme.ai experiment, a rapid object recognition experiment was designed • The dataset contains 100 images from animal and non-animal. • Phase scrambled masks are applied to images • eleven versions of each image ordered ascendingly based on their level of pixel revelation of important pixels. 22
  • 23. Model and human performance • Average accuracy of the two gala models (gala-click and gala no-click) and ResNet-50 model (no-gala-no-click) is compared on the behavioral test images at different levels of pixel revelation. • gala click and gala no click models achieved similar accuracy. • gala click model produces superior results compared to all other models in full pixel revelation. • The second best performance in full level, is achieved by gala-no-click model. 23 Sadeghi, Zahra. "An Investigation on Performance of Attention Deep Neural Networks in Rapid Object Recognition." Intelligent Computing Systems: Third International Symposium, ISICS 2020, Sharjah, United Arab Emirates, March 18–19, 2020, Proceedings 3. Springer International Publishing, 2020.
  • 24. • Human visual attention is well-studied • while there exist different models, they lack computational efficacy of our visual system • Attention Mechanisms in Neural Networks are still loosely based on the visual attention mechanism found in humans. 24
  • 25. Thanks for your attention  25