Title: Standard Brain Model for Vision
1Standard Brain Model for Vision
The talk is given by Tomer Livne and Maria Zeldin
2Overview
- Introduction to biological basis of vision
- Computer analogy to biology
- Implementation
- Discussion
3Overview of biological vision
- Hierarchical structure
- From simple features to complex ones (Hubel
Weisel) - Increased invariance
4The basic idea
Hubel and Weisel (1962, 1965) following
experimental results proposed a model in which
neighbouring simple cells are combined into
complex cell. The result is complex cells with
phase independence.
5Max vs. sum pooling
- Electrophysiological results indicate that
pooling may not be linear, the response of a
complex cell can be best described by the
activity of its maximal afferent.
6From simple to complex cells
7A straightforward extension of this is to start
with simple cells and end up with
higher-order-hyper-complex cells.
This is the basis for all the hierarchy idea!
8The hierarchy based on the brain model
Hierarchical models of object recognition in
cortex. Reisenhuber and Poggio. Nature, november
1999.
9Clearer explanation of the hierarchy
orientations
Simple cells
Max pooling
Complex cells
10Computer vision
- Usual approach image patching
- Biological motivated approach - hierarchy
11Representing objects by invariant complex features
The IT area in the brain is dealing with object
recognition. In this area there are cells that
respond best to a specific object
Hierarchical models of object recognition in
cortex. Reisenhuber and Poggio. Nature, november
1999.
12Recognize the same faces
13In the previous task our brains did a very good
job in recognizing same face even thou the scale,
impression, illumination were different. And did
not classified different faces as same even thou
they have similar physical conditions
14Motivation
- The presented approach is trying to implement
into a computer system the hierarchical idea that
was presented. In order to achieve similar
robustness.
15- The models that we present deal with more
general problem which is object classification. - We can say that the problem of recognition of
different transformations of an object is similar
to the problem of classification.
16Can computers reach similar properties to biology?
Reisenhuber Poggio (1999) demonstrate that it
can. Comparing electrophysiological results from
cells in the monkey brain with implemented
hierarchical model.
17Training stage
The monkey was trained to recognize restricted
set of views of unfamiliar target stimuli
resembling paperclips. They check which IT cell
responds best to all views. After finding the
cell that responded the most was picked for the
study.
18Test stage
The best reaction of the cell was to the trained
data. The second best was to new transformations
of the trained object. And very little response
to new objects (distractors)
19Learning the results
Hierarchical models of object recognition in
cortex. Reisenhuber and Poggio. Nature America
Inc, november 1999.
20The hierarchy based on the brain model
We saw this part
Now lets compare it to the model
Hierarchical models of object recognition in
cortex. Reisenhuber and Poggio. Nature, november
1999.
21Hierarchical models of object recognition in
cortex. Reisenhuber and Poggio. Nature America
Inc, november 1999.
22Results of scrambling
Hierarchical models of object recognition in
cortex. Reisenhuber and Poggio. Nature America
Inc, november 1999.
23Summary
- Goal- brain based object classification
- Biology view of the problem
- implementation of hierarchical structure
- comparing true results to model results
24Whats next?
- Models based on the hierarchical idea we already
discussed - Riesenhuber Poggio (1999)
- Serre Riesenhuber (2004)
- Serre, Wolf, Bileschi, Riesenhuber, Poggio
(2007) - Mutch Lowe (2006)
- Modifications of the basic ideas
- limitations and shortcomings
25Method 1 Riesenhuber Poggio , Hierarchical
models of objects recognition in cortex, Nature
1999 Later it was modified by Serre, Wolf,
Bileschi, Riesenhuber, Poggio, Robust object
recognition with cortex-like mechanisms, 2007.
26(No Transcript)
27- S1 Gabor filters
- 16 different sizes (7X7, 9X9,,37X37)
- 4 orientations
- A total of 64 S1 type detectors
Robust object recognition with cortex-like
mechanisms. Serre, Wolf, Bileschi, Reisenhuber
and Poggio. IEEE, march 2007.
28 A serial implementation of filtering
29- C1 MAX pooling
- 8 different sizes (8X8, 10X10,,22X22)
- 4 orientations
- A total of 32 C1 type detectors
- Used to define features during the learning stage
Robust object recognition with cortex-like
mechanisms. Serre, Wolf, Bileschi, Reisenhuber
and Poggio. IEEE, march 2007.
30- S2 learned features
- Holds N learned features
- 4 patch sizes (4X4, 8X8, 12X12, 16X16)
indicating how many C1 neighboring cells are
considered (this is done separately for each C1
scale) - For each image patch X, a Gaussian radial basis
function that depends on an Euclidean distance,
is calculated from each of the stored features Pi
(i1N) rexp(-ß X Pi²)
31Robust object recognition with cortex-like
mechanisms. Serre, Wolf, Bileschi, Reisenhuber
and Poggio. IEEE, march 2007.
32- C2 max pooling
- For each stored feature the best match (closest)
- Classifier
- Classification is based on both C1 and C2
Robust object recognition with cortex-like
mechanisms. Serre, Wolf, Bileschi, Reisenhuber
and Poggio. IEEE, march 2007.
33Summery
- 4 Layers of processing
- 2 types of operations (Max, Sum)
- Output N dimensional vector
34Models performance
- Testing the model
- Defining features
- Flexibility of the design
35Robustness to background
- Ignoring presented unrelated data
- Training and test images contains both targets
and distractors - Performed best with C2 type detectors
- Simple detection present/absent (no location
information) - Approaches maximal performance with 1000-5000
features - Performance improve with increased training (more
examples)
Robust object recognition with cortex-like
mechanisms. Serre, Wolf, Bileschi, Reisenhuber
and Poggio. IEEE, march 2007.
36Object specific features or a universal dictionary
- A Universal dictionary based system is good for
small training sets (10,000 features) - An object specific based system is better when
using large training sets (improves with practice
increased number of features 200 an image) -
37Robust object recognition with cortex-like
mechanisms. Serre, Wolf, Bileschi, Reisenhuber
and Poggio. IEEE, march 2007.
38Object recognition without a clutter
- Scene understanding using a windowing strategy
- Large inter-category variability
- Training sets of only either positive (target) or
negative (no target) - 2 classification systems C1 and C2 based
- C1 based system performs better (able to
efficiently represent objects boundaries)
39Robust object recognition with cortex-like
mechanisms. Serre, Wolf, Bileschi, Reisenhuber
and Poggio. IEEE, march 2007.
40Texture based objects
- Again C1 and C2 based classifiers
- C2 features are now evaluated only locally, not
over all image locations - C2 based classification is better (the features
are more invariant and complex) - Evaluated by correct labeling of pixels in the
image
Robust object recognition with cortex-like
mechanisms. Serre, Wolf, Bileschi, Reisenhuber
and Poggio. IEEE, march 2007.
41A unified system looking at multiple processing
levels
- The hierarchical nature of the described system
enables the use of multiple levels of feature - Recognizing both shape and texture based objects
in the same image - Two processing pathways
42Robust object recognition with cortex-like
mechanisms. Serre, Wolf, Bileschi, Reisenhuber
and Poggio. IEEE, march 2007.
43Scene understanding task
- Complex scene understanding requires more than
just detection of objects, location information
of the detected objects is also required - Shape-based objects
- C1 based classification, using a windowing
approach, for both identification and
localization - Local neighborhood suppression by the maximal
detected result - Texture-based objects
- C2 based classification
- texture boundaries posses a problem (solved by
additionally segmenting the image and averaging
the responses within each segment)
44Model summery
- Hierarchical design
- Efficiency
- Multiple processing pathways
- Universality Vs. specificity
- Limitations
45Method 2 Mutch Lowe Multiclass Object
Recognition with Sparse, Localized Features. 2006.
46- S1 Gabor filters
- Single scale (11X11)
- 4 orientations
- applied to every location
- Evaluated at all possible locations
Multiclass Object Recognition with Sparse,
Localized Features. By Mutch Lowe. IEEE 2006
47- C1 local invariance
- Max pooling using a 10X10(size)X2(scale) filter
- Each orientation is tested separately
- used to define features during the learning stage
- Larger skips
Multiclass Object Recognition with Sparse,
Localized Features. By Mutch Lowe. IEEE 2006
48- S2 intermediate features
- 4 filter sizes (4X4, 8X8, 12X12, 16X16) defined
by the stored features - A Universal feature set
- Response to each filter (feature) is calculated
as - R(X,P) exp-(X P²)/2s²a
Multiclass Object Recognition with Sparse,
Localized Features. By Mutch Lowe. IEEE 2006
49- C2 Global invariance
- A vector of size d of the maximal response
(anywhere in the image) to each feature. - SVM classifier
- Majority-voting based decision
Multiclass Object Recognition with Sparse,
Localized Features. By Mutch Lowe. IEEE 2006
50The overall look on all the stages
Multiclass Object Recognition with Sparse,
Localized Features. By Mutch Lowe. IEEE 2006
51Summary
- Similar assumptions
- Differences in construction
52Model performance and improvements
- Testing classification
- More biologically motivated improvements
53Tests classification
- 101 categories (from Caltech101)
- Trained sets of 15 (or 30) images of each
category - Learn random features (in both size and
location), an equal number for each category - Construct C2 vectors
- Train the SVM (on the improved model also perform
feature selection) - Test stage
54Results of the test
Multiclass Object Recognition with Sparse,
Localized Features. By Mutch Lowe. IEEE 2006
55To get better results, some improvements were
added to the model
- S2 encodes only the dominant orientation at
each location. - Increased number of tested orientations (from 4
to 12) - Lateral inhibition suppressing below threshold
filter outputs in S1 C1 layers - Limited S2 invariance in order to allow for
preserving a certain amount of geometrical
relations, S2 feature are limited to certain
places in the image (relative to the center of
the object) - Select only good features for classification
56Running the previous test on the improved model
lead to the following results
Multiclass Object Recognition with Sparse,
Localized Features. By Mutch Lowe. IEEE 2006
57Refining the model
Multiclass Object Recognition with Sparse,
Localized Features. By Mutch Lowe. IEEE 2006
58Testsdetection/localization
- Sliding window
- Merging overlapping detections
- Single/multiple scale test images
Multiclass Object Recognition with Sparse,
Localized Features. By Mutch Lowe. IEEE 2006
59Summery
- Efficiency
- Improvements
- Limitations
60THE ENDThank you for listening!
61- Simple cell is an early visual neuron meaning it
responds best to a line of a specific size,
orientation, and phase.
This cell responds best to 180 deg. phase.
This cell responds best to 90 deg. phase.
62back
63Image
Simple cell (phase sensitive)
Complex cell (phase insensitive)
back