Object recognition Flashcards

1
Q

The object recognition problem

A

Isolated neurons in V1 cannot draw conclusions by themselves on the nature of a whole object

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

Template Theory

A

visual system recognizes objects by matching the neural representation of the image with an internal representation of the same “shape” in the brain
Many templates for different object positions
- flexibility is limited because you cannot store a template for every object

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

General recognition theory (Ashby)

A

Categorization based on multivariate signal detection theory
- Categories are defined by probabilistic distributions, and categorization is based on decision boundaries that separate perceptual regions.
- If 2 objects have very similar features, they will be harder to distinguish. If 2 objects do not overlap in features, it is easier to detect differences and distinguish them.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

Generalized Context Model (GCM) (Nosofsky)

A

Examplar based similarity : comparing new object to stored examples
Whatever exemplar is more similar to new object = what this new object is

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

GCM (Nosofsky) : categorizing faces

A

You store many specific faces you’ve seen before. When seeing a new face, you compare it to stored examples and assign the category based on similarity to past faces.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

GRT (Ashby) : categorizing faces

A

rely on perceptual dimensions (e.g., face shape, jaw width, eye size) and make a decision based on statistical boundaries between the two categories.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

Recognition by components (Irving Biederman)

A

We recognize objects using an alphabet of shapes, or geons (geometric ions) that together combined can form any given object
- 36 geons, that can make up any object
Limitations : does not handle object variability, very crude

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

Grandmother cell theory

A
  • Suggests we have a single neuron for every single concept in our world
  • Extreme version of localized representation in the brain (like template theory)
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

Jennifer Aniston cell?

A
  • A single responded solely when presented with a picture of Jennifer Aniston
  • If that cell died, the person would still probably recognize her
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

Deep Neural Network (DNN)

A
  • Multilayer neural networks capable of being trained to recognise objects.
  • Numerous instances of an object are shown to the network, with feedback
  • Over time, the network learns to recognize label new instances of the object that it has never been explicitly trained on (generalization over the training set)
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

Deep Neural Networks (DNNs) rivalled the representational performance of the … in monkeys on an object recognition task.

A

inferior temporal cortex (IT)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

Retinal Ganglion Cells & LGN detect _____ (localized contrast)

A

Spots

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

Primary Visual Cortex (V1) detects …

A

Edges and bars (orientation selectivity)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

Role of Intermediate-level vision (V2, V3, V4, etc)

A

Grouping features into contours, textures, and surfaces.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

Role of high-level vision (IT cortex)

A

Recognizing complex shapes, objects, and categories.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

Object recognition is not just about simple features but about _______ processing across multiple visual areas.

A

Hierarchical

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
17
Q

The receptive fields of _______ cells respond to visual properties crucial for object perception.

A

Extrastriate

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
18
Q

Boundary Ownership

A

For a given edge or contour, V2 extrastriate neurons determine which side belongs to the object and which side belongs to the background—a fundamental process in figure-ground segregation.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
19
Q

Intermediate (mid) level vision

A

Loosely defined stage of visual processing after low-level feature extraction (e.g., edges, contrast) and before high-level object recognition and scene understanding.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
20
Q

Key Functions of intermediate vision

A
  • Perception of edges and surfaces
  • Determines which regions of an image should be grouped into objects
  • Bridges low-level feature detection and high-level object recognition
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
21
Q

Primary visual cortex (V1) neurons have ____ receptive fields that detect local edges and contrast.

A

Small

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
22
Q

orientation-selective v1 neurons

A

Respond to edges at specific angles

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
23
Q

Computerized edge detectors are not as effective as humans in detecting …

A

meaningful edges

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
24
Q

Why do computers miss edges that humans easily perceive ?

A

Computers rely purely on local contrast and intensity differences.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
25
Illusory contour
A contour that is perceived even though no physical edge exists between one side and the other.
26
Gestalt theory opposes ______
Structuralism - perception is holistic : we naturally organize elements into meaningful wholes rather than processing each part independently
27
Gestalt Grouping Principles
Set of rules that describe when and how elements in an image appear grouped together:
28
Similarity Gestalt rule
Similar objects (color, shape, size) appear grouped.
29
Proximity Gestalt rule
Objects that are close to each other tend to be grouped together
30
Parallelism Gestalt rule
Parallel contours are likely to belong to the same group.
31
Symmetry Gestalt rule
Symmetrical regions are more likely to be perceived as a group.
32
Good continuation Gestalt rule
- Lines and edges are perceived as following the smoothest path
33
Closure Gestalt rule
The mind fills in missing information to perceive complete shapes.
34
Common fate Gestalt rule
Objects that move together are seen as moving in same direction
35
Figure ground Gestalt rule
The brain separates objects from the background.
36
Common Region Gestalt rule
Elements are grouped together if they appear to belong to the same larger region.
37
Connectedness Gestalt rule
Elements tend to be grouped if they are connected. Overrules proximity.
38
Camouflage
Animals use Gestalt rules to merge with their environements Camouflage is more effective for dichromats
39
Perception emerges as the result of the _______ interpretation agreed upon by Gestalt processes.
Dominant
40
5 principles of intermediate vision
1. Group what should be grouped together. 2. Separate what should be separated. 3. Use prior knowledge to predict. 4. Avoid accidents (coincidences making appear objects as something else). 5. Seek consensus and minimize ambiguity.
41
After processing in the _____ cortex, object information is divided into 2 pathways
Extrastriate (visual areas beyond the primary visual cortex (V1 or striate cortex)
42
“Where” Pathway (Dorsal Stream)
- Processes locations and shapes of objects. - Does not encode object names or functions. - Extends from the occipital lobe to the parietal lobe
43
“What” Pathway (Ventral Stream)
- Processes object identity (names) and functions, independent of location. - Extends from the occipital lobe to the temporal lobe.
44
Feedforward processes
information leaving early visual cortex V1 moving to V4
45
Feedback processes
- information sent from V4 back to V1, for example to ask for more edge information
46
As we move from V1 to V2, V3, V4, posterior, anterior, prefrontal cortex; the neurons respond to more and more... information
abstract and complex
47
V4 neurons respond to ... gratings.
polar, hyperbolic, radial and Cartesian instead of sine and linear - Supports the idea that V4 represents intermediate level shape information
48
V4 extracts ... and is specialized for...
curves, textures, and complex contour Specialization : local features
49
Stimuli that activate the neurons in posterior IT (PIT) the best are ...
object parts (intermediate processing)
50
Difference between Posterior IT and anterior IT
Posterior IT : integrates shape features; not whole objects Anterior IT : whole objects
51
The ... is thought to be the first stage in visual processing to explicitly represent whole objects
Lateral occipital complex LOC (bilateral)
52
LOC responds strongly to the ____ of objects, even when texture or color is removed
Shape
53
Invariant representation in LOC
Representations that do not depend on the viewpoint, texture & color
54
LOC is also involved in ...
figure-ground segmentation, helps distinguish objects from their background
55
The LOC bridges ... with ....
mid-level feature processing (V4, PIT) and high-level object recognition (IT cortex, FFA, PPA). - Part of ventral visual stream
56
Why can we say the fusiform face area FFA is category preferential instead of category selective ?
The FFA does not only respond to faces (expertise effect too)
57
Prosopagnosia
inability to recognize faces due to FFA damage
58
Invariant Face Recognition in the FFA
FFA helps recognise faces across different angles, lighting conditions, and expressions
59
Where is the FFA ?
in the fusiform gyrus of the ventral temporal lobe (right hemisphere; sometimes bilaterally).
60
Parahippocampal Place Area (PPA) is a ______-processing region
Scene and place category selective
61
PPA is a cortical representation of the ...
local visual environment
62
How does the PPA challenge the idea that object recognition is enough to explain scene perception ?
The PPA shows that patial layout is key to scene perception : a scene is not just a collection of objects.
63
scene perception vs. memory-based navigation
Scene perception : PPA Memory-based navigation : hippocampus
64
Provides a functional link between vision and spatial cognition, bridging perception and higher-order place representation.
PPA
65
How is real world size represented in the brain ?
Not far from the fusiform gyrus, there is a medial and lateral contrast between small/big objects - It extends to the dorsal stream, showing that it has a role beyond location identification
66
What suggests that IT neurons encode more abstract representations of objects rather than raw sensory features ?
IT neurons demonstrate invariance : they continue to respond to an object regardless of its size, position, or viewpoint.
67
Machine learning as a decoding method
Collect fMRI scans of a participant while they view images from multiple known categories. ● Train a computer model to recognize the brain activity patterns associated with each category. ● Test the model to see if it can correctly identify an unseen image based on learned brain activity patterns.
68
Distributed representations in decoding faces perception
If you remove the FFA of the pattern, you can still decode whether you are looking at a face or not - There is information about object categories and faces throughout the visual ventral stream
69
Gabor patches
Sinusoidal gradings with different frequencies, positions and orientations
70
Second order isomorphism (Roger Shepard)
Similar objects in the world must have similar representations in the mind.