Professional Documents
Culture Documents
attention
Sharat Chikkerur, Thomas Serre & Tomaso Poggio
CBCL, McGovern Institute for Brain Research, MIT
•Filter theory (Broadbent) •Bayesian surprise (Itti)
•Biased competition (Desimone) •Bottleneck (Tsotsos)
•Feature integration theory (Treisman)
•Guided search (Wolfe)
•Scanpath theory (Noton)
Computational Role
Attention
Biology Effects
•Contrast gain
• V1 •Response gain
• V4 •Modulation under spatial attention
• MT •Modulation under feature attention
• LIP
• FEF
•Pop-out
•Serial vs. Parallel
•Bottom-up vs. Top-down
Role of attention
Invariant recognition: mixed blessing
Large pooling in the higher regions leads to invariance
xV1
x0
Attention as Bayesian inference
(MIT, Chikkerur, Serre, Poggio)
PFC
LIP/FEF
IT
V4
V2
Desimone ,MIT (unpublished)
Spatial attention:
Feature-based What isWhere
attention: at location L? O?
is object
Model description
“Where” “What”
L Fi
Fil
N Feature-maps
Feature-maps
Image
Model properties: invariance
“Where” “What”
L Fi
Fil
N
Model properties: crowding
“Where” “What”
L Fi
Fil
N
Model: spatial attention
L Fi
X
Fil
* * *
N
What is at location X?
Model: feature-based attention
X
L Fi
Fil
* * * N
Where is object X?
Effects of attention
Spatial Invariance
Spatial Attention
Feature Attention
Feature Popout
Parallel vs. Serial Search
Recognition under clutter: Feature+Spatial
Spatial attention
Model
McAdams and Maunsell ‘99
Unattended
Attended
P stim/P cue
NP stim/ P.cue
P.stim/NP cue
NP stim/NP cue
Top-down
Bottom-up
spatialattention
and feature attention
Method Method ROC area
ROC(Cars) ROC area (Pedestrian)
area (absolute)
Bruce and Tsotos ’06 42.3%
Itti et al. ’01 72.8% 42.3%
Torralba et al. Itti et al ’01 78.9% 72.7% 77.1%
Proposed Proposed 80.4% 77.9% 80.1%
Humans 87.8% 87.4%
Recognition performance improves with attention
0.75
ROC area
0.5
0.25
0
car pedestrian
Humans Bottom-up
Top-down (feature-based) Feaure-based + contextual cues
performance (d’)
1
one shift of
no attention
attention
Model Humans