uiz Space

May 2024 term · Deep Learning for Computer Vision · BSDA5006

Deep Learning for Computer Vision Quiz 1: 7 July 2024 (May 2024 term)

The IIT Madras BS Deep Learning for Computer Vision (Deep Learning for Computer Vision) Quiz 1 paper sat on 7 Jul 2024, in the May 2024 term: 29 questions for 50 marks in 120 minutes. Every question is below with its answer. Take it as a timed mock test to be marked, or read it through first.

Questions
29
Marks
50
Duration
120 min
MSQ
3
MCQ
11
Numerical
10
Written
5

Updated

Official paper: IIT M DEGREE AN EXAM QDB2 7 July 2024 · No negative marking.

Question 1

+2 marksOne or more correct options

Select all that apply.

  1. A
  2. B
  3. C
  4. D
Show answer

Correct answers

  • A
  • C

Question 2

+2 marksOne or more correct options

Select all that apply.

  1. A
  2. B
  3. C
  4. D
Show answer

Correct answers

  • A
  • D

Question 3

+2 marksOne or more correct options

Which of the following are true? (Select all that apply)

Select all that apply.

  1. A
  2. B
  3. C
  4. D
Show answer

Correct answers

  • A
  • B

Question 4

+2 marksOne correct option

Which of the following statements is True?

  1. A

    Gaussian filter is Separable filter because it is non linear.

  2. B

    Median filter is a non separable filter

  3. C

    Gaussian filter is a High Pass filter.

  4. D

    Mean filter is a non separable filter because it is non linear

Show answer

Correct answer

  • B

    Median filter is a non separable filter

Question 5

+2 marksOne correct option

In Bilateral filtering, we do not reject the pixels whose values differ too much from the central pixel value.

  1. A

    TRUE

  2. B

    FALSE

Show answer

Correct answer

  • B

    FALSE

Question 6

+2 marksOne correct option

Which of the following is the Fourier image of the given intensity image?

  1. A
  2. B
  3. C
  4. D
Show answer

Correct answer

  • B

Question 7

+2 marksOne correct option

Identify the correct sequence of steps in Scale Invariant Feature Transform (SIFT) method. Steps listed below:
1. Keypoint Descriptor
2. Keypoint Localization
3. Scale-space Extrema Detection
4. Orientation Estimation

  1. A

    4→ 2→ 1→ 3

  2. B

    3→ 2→ 4→ 1

  3. C

    3→ 1→ 2→ 4

  4. D

    None of these

Show answer

Correct answer

  • B

    3→ 2→ 4→ 1

Question 8

+2 marksOne correct option
  1. A

    1→iii, 2 → ii , 3→ i , 4 → iv

  2. B

    1→iv, 2→ i , 3 → ii , 4→ iii

  3. C

    1→ii, 2 → iii , 3→ iv , 4→ i

  4. D

    None of these

Show answer

Correct answer

  • C

    1→ii, 2 → iii , 3→ iv , 4→ i

Question 9

+2 marksOne correct option
  1. A

    1→ iii, 2→ i, 3 → ii

  2. B

    1→ iii, 2→ ii, 3 → i

  3. C

    1→ ii, 2→ iii, 3 → i

  4. D

    None of these

Show answer

Correct answer

  • A

    1→ iii, 2→ i, 3 → ii

Question 10

+2 marksOne correct option

In RANSAC, what is the probability that the algorithm never selects a whole set of inliers from 20 data points (which has 5 inliers in total) for k = 2 time steps? Here, n = 2 is the minimum number of samples to fit a model.

  1. A

    0.2

  2. B

    0.93

  3. C

    0.87

  4. D

    0

Show answer

Correct answer

  • C

    0.87

Question 11

+2 marksOne correct option

Suppose we have a codebook of 2048 SIFT visual words. We extract 1000 SIFT descriptors (SIFT is a 128-dimensional feature) from a new image. What is the dimensionality of the BoW (Bag-of-Words) descriptor?

  1. A

    1000

  2. B

    128

  3. C

    128 × 2048

  4. D

    2048

Show answer

Correct answer

  • D

    2048

Question 12

+2 marksOne correct option
  1. A

    1→ iii, 2→ ii, 3 → vi, 4→ i

  2. B

    1→ v, 2→i, 3 → vi, 4→ iii

  3. C

    1→ iii, 2→ i, 3 → ii, 4 → v

  4. D

    1→ ii, 2→ v, 3 → iv, 4→ iii

Show answer

Correct answer

  • D

    1→ ii, 2→ v, 3 → iv, 4→ iii

Question 13

+2 marksOne correct option
  1. A

    1→ vi, 2→ iii, 3→ v, 4 → i

  2. B

    1→ i, 2→ iv, 3 → iii, 4→ ii

  3. C

    1→ i, 2→ v, 3 → iii, 4→ iv

  4. D

    1→ iv, 2→ iii, 3→ ii, 4 → i

Show answer

Correct answer

  • D

    1→ iv, 2→ iii, 3→ ii, 4 → i

Question 14

+2 marksOne correct option

Consider a Convolutional Neural Network which processes an RGB image. It has 128 kernels each of spatial dimension 5 × 5 in the first layer. They are convolved with a stride 1. This is followed by a max-pooling layer with stride 2 and kernel size 5 × 5. What would be the receptive field size of a single neuron in the pooling layer? (Recap: A receptive field is the size of the region in the input image, which influences the activation of that specific neuron.)

  1. A

    5 × 5

  2. B

    7 × 7

  3. C

    9 × 9

  4. D

    3 × 3

Show answer

Correct answer

  • C

    9 × 9

Question 15

+2 marksNumerical answer

Consider the grayscale image shown below:

[20302530404510403520152030255050403515301035252045]\begin{bmatrix} 20 & 30 & 25 & 30 & 40 \\ 45 & 10 & 40 & 35 & 20 \\ 15 & 20 & 30 & 25 & 50 \\ 50 & 40 & 35 & 15 & 30 \\ 10 & 35 & 25 & 20 & 45 \end{bmatrix}

If a median filter with a 3×33 \times 3 neighborhood is applied to this image with a stride of 1 and no padding, __________ will be the value at position (2,2)(2, 2) in the filtered image? (Assume that the top-left pixel coordinate of output image is addressed as (1,1)(1, 1))?

Show answer

Correct answer: 30

Question 16

+2 marksNumerical answer

NOTE: Enter your answer in two decimal places.

Show answer

Correct answer: -0.33

Question 17

+2 marksNumerical answer

What is the size of the feature map after applying two successive convolution operations with given parameters? Image size = 64 x 64, Kernel size = 6 x 6, Padding = 1 and Stride = 2. (In calculation, take floor(x) whenever x is non-integer. If the answer is FxF, write F in the blank). ___________

Show answer

Correct answer: 14

Question 18

+2 marksNumerical answer

Let an input to a convolutional layer in a CNN have size Df × Df × M where Df = 64 and M = 16, and output feature map (after passing input through conv layer) has Df × Df × N size where N = 8. Let the kernel in the conv layer be k × k where k = 3. Calculate the number of parameters for this convolution layer. (Assume appropriate padding is applied for all convolutions so the input and output sizes are equal. Ignore the bias term in the calculation).

Show answer

Correct answer: 1152

Question 19

+1 markNumerical answer

Based on the above data, answer the given subquestions.

Fill in the blank for (a)________________

Show answer

Correct answer: 2

Question 20

+1 markNumerical answer

Based on the above data, answer the given subquestions.

Fill in the blank for (b)_____________________

Show answer

Correct answer: 5

Question 21

+2 marksWritten answer

Based on the above data, answer the given subquestions.

Fill in the blank for (a)_____________________

Show answer

Correct answer: high

Question 22

+1 markWritten answer

Based on the above data, answer the given subquestions.

Fill in the blank for (b) _____________________

Show answer

Correct answer: high

Question 23

+1 markWritten answer

Based on the above data, answer the given subquestions.

Fill in the blank for (c) _____________________

Show answer

Correct answer: smooth

Question 24

+2 marksWritten answer

Based on the above data, answer the given subquestions.

Fill in the blank for (a):

Show answer

Correct answer: thick or coarse or large scale

Question 25

+2 marksWritten answer

Based on the above data, answer the given subquestions.

Fill in the blank for (b):

Show answer

Correct answer: fine

Question 26

+1 markNumerical answer

Based on the above data, answer the given subquestions.

Show answer

Correct answer: 1

Question 27

+1 markNumerical answer

Based on the above data, answer the given subquestions.

Show answer

Correct answer: 0.5

Question 28

+1 markNumerical answer

Based on the above data, answer the given subquestions.

Show answer

Correct answer: 0

Question 29

+1 markNumerical answer

Based on the above data, answer the given subquestions.

Show answer

Correct answer: 1