L9: Segmentation Flashcards

1
Q

What is the difference between segmentation and object detection?

A

object detection → makes bounding box (nothing of the shape of the object)
segentation → Gives information of the shape, uses pixel-wise mask for each object in the image)

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

Clusteirng

Why would you do color space clustering?

A

A way of doing image segmentation as objects with similar colors distributed in it will describe the same object. Grouping similar colors describe separation of dirrent objects.
- Each pixels gets a label according to the nearest cluster

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

Clustering

What is clustering

A

Given a bunch of data points in some space, clustering is about discovering dense regions of that space, and separating these from each other.

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

Clustering

K-means clustering

A

This can be done in pixel space, k cluster should be defined in advance.
- K-means has hard limitations (black or white). If the clusters overlap it will be a problem, which GMM can solve.

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

Clustering - GMM

❗️❗️❗️Know the GMM model

A

Initialize it with mahalnobis (elipse) distance instead of euclidean (spherical).
- GMM is k-dimensional ellipse

Goal is to estimate k means (μ), covariance (Σ) and k mixing coefficients (π)
- π is weights summing to 1. The higher the cluster is, the higher π is.

Softly assigned → e.g. 67% to k_1, 12% to k_2 and 21% to k_3.
- probability of each data point for one of the the k Gaussians is really the “distance” measure used during GMM optimization.

Iteratively compute (a local) maximum likely estimate for the unknown mixture parameters (πk, μk, Σk)
- Expectation step:
- Maximization step:

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

Clustering: GMM

❗️❗️❗️Know the EM algorithm for GMM optimization

A

Step 1: Initialize the means (using k-means often) as a starting step and then proceed with EM afterwards.
E first, then M.
- E: calculate the “probability” that the i’th data point belongs to the k’th cluster
-M: Estimate the number of points assigned to each cluster k.
Updates (πk, μk, Σk).

Alternates between the E and M steps, and when done the likelihood of all of the data points given the K cluster will be as high as possible.

GMM reaches local optima and thus depends on a good initialization.

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

Clustering: Mean shift

❗️❗️❗️Know the update method for the mean shift algorithm

A

Updates iteratively by shifting each point uphill intil it reaches peak.
- For color segmentation; when all the points have been shifted to their respective mode, we can assign them the value of that mode

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

Clustering: Mean shift

❗️❗️❗️Know the role of the kernel and the bandwidth for mean shift

A

Smaller bandwidth results in more clusters, while larger results in fewer.

Kernel Density Estimation (KDE)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

Clustering: Mean Shift

❗️❗️❗️Know the differences between and pros/cons of k-means, GMMs, and mean shift

A

K-means:
- hard assigned to a cluster
- dependent on number of k
- hope we separate enough and do not overlap
- parametric (k)
GMM:
- softly assigned to a cluster (probability of belonging to one cluster and a probability of belonging too another)
- great at overlaps
- parametric (πk, μk, Σk)
MS:
- mode finding method
- non parametric, has internal parameter tuning (kernal size and bandwidth)

Mean Shift (MS)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

U-Net

❗️❗️❗️The structure of the network

A

U-net is a learning-based neural segmentation algorithm. Predicts correct class labels for each pixel in the input image.
- NEEDS LABELED TRAININF SET!

Upsamples bottom high-level features back to its original dimensions.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

U-Net

❗️❗️❗️The modified loss weighting terms

A

1- w_c is a class-balancing term
Associates a smaller weight (and thereby a smaller gradient during training) to big segments to make room for also learning labels for small segments in the image
2. w_0 is a border term between touching segments
Focus more on the difficult borders between touching segments.

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

U-Net

❗️❗️❗️What it takes to set up a training/testing pipeline on a new segmentation task using U-Net

A

Utilizes augmentation during training, size of training set is not needed to be big.

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

U-Net

❗️❗️❗️The pros and cons of using U-Net vs. clustering methods for segmentation

A

U-Net:
- Separates colors with apperance variation and many similar structure across objects. Cant be done with color alone.
- defines a clear border (color segmentation does not do that)
- Uses small training set

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

Clustering

What is clustering

A

Given a bunch of data points in some space, clustering is about discovering dense regions of that space, and separating these from each other.

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

Clustering

What is clustering

A

Given a bunch of data points in some space, clustering is about discovering dense regions of that space, and separating these from each other.

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

Clustering

What is clustering

A

Given a bunch of data points in some space, clustering is about discovering dense regions of that space, and separating these from each other.