Figure from the original question paper

(C) 0.18,−1.5, 0, 0.20, 0,−0.015

(A) 0.18, 1.5, 1.5, 0.20,−1.5,−0.015

Figure from the original question paper

(C) 1→ ii, 2→ iii, 3 → ii

Match the derivative of activation functions f(x) with their counterparts on the right column accordingly. | 1) Leaky ReLU | i) f(x)(1 - f(x)) | |---|---| | 2) Tanh | ii) 0 if x 0 | | 3) ReLU | iii) 1 - f(x)^2 | | 4) Sigmoid | iv) 0.01 if x 0 | | | v) 0 if x \geqslant 0 and 1 if x < 0 | | | vi) 0.01 if x \geqslant 0 and 1 if x < 0 |

(D) 1→ iv, 2→ iii, 3→ ii, 4 → i

(A) 1→ vi, 2→ iii, 3→ v, 4 → i

(B) 1→ i, 2→ iv, 3 → iii, 4→ ii

(C) 1→ i, 2→ v, 3 → iii, 4→ iv

Figure from the original question paper

(C) 1→ iii, 2→ iv, 3→ v, 4 → ii

(A) 1→ iii, 2→ iv, 3→ i, 4 → ii

(B) 1→ iii, 2→ i, 3 → ii, 4 →v

(D) 1→ iv, 2→ iii, 3→ i, 4 → ii

Figure from the original question paper

(A) Option figure from the original question paper

(B) Option figure from the original question paper

(C) Option figure from the original question paper

(D) Option figure from the original question paper

January 2025 term · Deep Learning for Computer Vision · BSDA5006

Deep Learning for Computer Vision Quiz 1: 23 February 2025 (January 2025 term)

The IIT Madras BS Deep Learning for Computer Vision (Deep Learning for Computer Vision) Quiz 1 paper sat on 23 Feb 2025, in the January 2025 term: 36 questions for 60 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: 36
Marks: 60
Duration: 120 min
Numerical: 13
MCQ: 13
MSQ: 6
Written: 4

Take as mock test Practise with answers

Updated 25 Sept 2026

Official paper: IIT M DEGREE AN EXAM QDB2 23 Feb 2025 · No negative marking.

Question 1

+2 marksNumerical answer

Consider the following numpy array

$\text{arr} = \begin{bmatrix} 0 & 1 \\ 2 & 3 \\ 4 & 5 \end{bmatrix}$

Now consider the following operations

$\text{flattened\_arr} = \text{arr.flatten()}$

$\text{flattened\_arr[2]} = 10$

Write the value of arr[2]

Show answer

Correct answer: 2

Question 1 on its own page

Question 2

+2 marksNumerical answer

Consider the following numpy array

$\text{arr} = \begin{bmatrix} 0 & 1 \\ 2 & 3 \\ 4 & 5 \end{bmatrix}$

Now consider the following operations

$\text{raveled\_arr} = \text{arr.ravel()}$

$\text{raveled\_arr[2]} = 20$

Write the value of arr[2]

Show answer

Correct answer: 20

Question 2 on its own page

Question 3

+2 marksNumerical answer

Consider the grayscale image shown below:

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

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

Show answer

Correct answer: 30

Question 3 on its own pageAlso asked in Quiz 1 25 Feb 2024, Quiz 1 7 Jul 2024, Quiz 1 27 Oct 2024

Question 4

+2 marksNumerical answer

Show answer

Correct answer: -0.335 (accepted within ±0.005)

Question 4 on its own page

Question 5

+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 = 3 x 3, Padding = 2 and Stride = 3. (In calculation, take floor(x) whenever x is non-integer. If the answer is FxF, write F in the blank).

Show answer

Correct answer: 8

Question 5 on its own page

Question 6

+2 marksNumerical answer

Let an input to a convolutional layer in a CNN have size Df × Df × M where Df = 32 and M = 100, and output feature map (after passing input through conv layer) has Df × Df × N size where N = 64. Let the kernel in the conv layer be k × k where k = 5. 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: 160000

Question 6 on its own page

Question 7

+2 marksNumerical answer

Show answer

Correct answer: -0.235 (accepted within ±0.025)

Question 7 on its own page

Question 8

+2 marksOne correct option

Given is a $3 \times 3$ 8-bit grayscale image:

$\begin{bmatrix} 50 & 70 & 120 \\ 90 & 30 & 80 \\ 40 & 60 & 110 \end{bmatrix}$

What is the mean of transformed pixels of after applying linear contrast stretching? Linear contrast stretching is an image enhancement technique used to improve the contrast in an image. This is achieved by linearly scaling the pixel values so that they span a desired range (0 to 255 for an 8-bit grayscale image).

A
119.33
B
110.5
C
134.25
D
0

Show answer

Correct answer

A
119.33

Question 8 on its own page

Question 9

+2 marksOne correct option

Which of the following statements is True ?

A
Gaussian filter is Separable filter because it is non linear.
B
Median filter is a non separable filter
C
Gaussian filter is a High Pass filter.
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 9 on its own pageAlso asked in Quiz 1 25 Feb 2024, Quiz 1 7 Jul 2024, Quiz 1 27 Oct 2024

Question 10

+2 marksOne correct option

A
0.18, 1.5, 1.5, 0.20,−1.5,−0.015
B
0.92, 2.5, 1, 2.5, 2.5, 1
C
0.18,−1.5, 0, 0.20, 0,−0.015
D
0.91, 1, 0, 0.2, 1, 1.7

Show answer

Correct answer

C
0.18,−1.5, 0, 0.20, 0,−0.015

Question 10 on its own page

Question 11

+2 marksOne correct option

Identify the correct sequence of steps in a Canny edge detection pipeline. Steps are listed below: 1. Compute gradient magnitude and direction
2. Connect individual components
3. Smoothen the image
4. Threshold into strong, weak, or no edge
5. Gaussian Filter and Hysteresis
6. Non-maximum suppression
7. Apply derivative to get edges

A
6→ 1→ 4→ 5 → 2
B
3→ 1→ 6→ 4 → 2
C
3→ 5→ 1→ 4 → 2
D
6→ 1→ 5→ 7 → 2

Show answer

Correct answer

B
3→ 1→ 6→ 4 → 2

Question 11 on its own page

Question 12

+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

A
4→ 2→ 1→ 3
B
3→ 2→ 4→ 1
C
3→ 1→ 2→ 4
D
None of these.

Show answer

Correct answer

B
3→ 2→ 4→ 1

Question 12 on its own pageAlso asked in Quiz 1 7 Jul 2024, Quiz 1 27 Oct 2024

Question 13

+2 marksOne correct option

A
1→ iii, 2→ i, 3 → ii
B
1→ iii, 2→ ii, 3 → i
C
1→ ii, 2→ iii, 3 → ii
D
None of these

Show answer

Correct answer

A
1→ iii, 2→ i, 3 → ii

Question 13 on its own page

Question 14

+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?

A
1000
B
128
C
128 × 2048
D
2048

Show answer

Correct answer

D
2048

Question 14 on its own pageAlso asked in Quiz 1 25 Feb 2024, Quiz 1 7 Jul 2024, Quiz 1 27 Oct 2024

Question 15

+2 marksOne correct option

Match the derivative of activation functions $f(x)$ with their counterparts on the right column accordingly.

1) Leaky ReLU	i) $f(x)(1 - f(x))$
2) Tanh	ii) 0 if $x < 0$ and 1 if $x > 0$
3) ReLU	iii) $1 - f(x)^2$
4) Sigmoid	iv) 0.01 if $x < 0$ and 1 if $x > 0$
	v) 0 if $x \geqslant 0$ and 1 if $x < 0$
	vi) 0.01 if $x \geqslant 0$ and 1 if $x < 0$

A
1→ vi, 2→ iii, 3→ v, 4 → i
B
1→ i, 2→ iv, 3 → iii, 4→ ii
C
1→ i, 2→ v, 3 → iii, 4→ iv
D
1→ iv, 2→ iii, 3→ ii, 4 → i

Show answer

Correct answer

D
1→ iv, 2→ iii, 3→ ii, 4 → i

Question 15 on its own pageAlso asked in Quiz 1 27 Oct 2024, End Term 22 Dec 2024, End Term 31 Aug 2025

Question 16

+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.)

A
5 × 5
B
7 × 7
C
9 × 9
D
3 × 3

Show answer

Correct answer

C
9 × 9

Question 16 on its own pageAlso asked in Quiz 1 7 Jul 2024

Question 17

+2 marksOne correct option

Consider the following two statements. Which of the following statements are true?
(a) Convolution operator is both commutative and associative.
(b) Fourier transform of a convolved image FT (a * b), is not the product of the Fourier transform of the constituent images FT(a) x FT(b)

A
a and b
B
not a but b
C
a but not b
D
Neither a nor b

Show answer

Correct answer

C
a but not b

Question 17 on its own page

Question 18

+2 marksOne correct option

A 3x3 kernel generates an output image of dimension 20x20 after convolution. The (approximate) number of computations performed to obtain this output image is:

A
3600
B
180
C
400
D
9

Show answer

Correct answer

A
3600

Question 18 on its own page

Question 19

+2 marksOne correct option

Which of the following statements are True?

A
Vanilla Gradient Descent converges faster than Momentum-based GD.
B
Momentum based GD oscillates around minima before convergence.
C
Noise in Stochastic Gradient descent weight updates – can lead to faster convergence.
D
None of these

Show answer

Correct answer

B
Momentum based GD oscillates around minima before convergence.

Question 19 on its own pageAlso asked in Quiz 1 13 Jul 2025

Question 20

+2 marksOne correct option

A
1→ iii, 2→ iv, 3→ i, 4 → ii
B
1→ iii, 2→ i, 3 → ii, 4 →v
C
1→ iii, 2→ iv, 3→ v, 4 → ii
D
1→ iv, 2→ iii, 3→ i, 4 → ii

Show answer

Correct answer

C
1→ iii, 2→ iv, 3→ v, 4 → ii

Question 20 on its own page

Question 21

+2 marksOne or more correct options

Which of the following statements is false?

Select all that apply.

A
Linear contrast stretching is a local operation.
B
Moving average is an example of local operation.
C
Convolution in the spatial domain can be obtained through addition in the frequency domain.
D
All of these.

Show answer

Correct answers

A
Linear contrast stretching is a local operation.
C
Convolution in the spatial domain can be obtained through addition in the frequency domain.

Question 21 on its own page

Question 22

+2 marksOne or more correct options

Which of the following statements are false?

Select all that apply.

A
Momentum in optimization can cause oscillations around minima when encountering flat regions or saddle points due to the dominance of the momentum term over the small gradient.
B
Stochastic Gradient Descent (SGD) with its inherent noise can be beneficial in escaping local minima and saddle points, provided that there is enough gradient information in the neighborhood.
C
Adagrad is an optimization algorithm introduced to overcome the diminishing learning rate problem in techniques like RMSProp.
D
ADAM is introduced to solve problems in RMSProp by combining RMSProp and Adagrad techniques.

Show answer

Correct answers

C
Adagrad is an optimization algorithm introduced to overcome the diminishing learning rate problem in techniques like RMSProp.
D
ADAM is introduced to solve problems in RMSProp by combining RMSProp and Adagrad techniques.

Question 22 on its own pageAlso asked in Quiz 1 27 Oct 2024, Quiz 1 13 Jul 2025

Question 23

+2 marksOne or more correct options

Select all that apply.

Show answer

Correct answer

Question 23 on its own page

Question 24

+2 marksOne or more correct options

Certain 2D kernel $K$ can be decomposed into two 1D kernels ( $v$ and $h$ ) to reduce the computation cost such as $K = vh^\top$ . The 2D kernel is called as Separable Kernel.

Consider the following 2D kernels

$\text{(a)} \quad \begin{bmatrix} 2 & 4 & 6 \\ 3 & 6 & 9 \\ 1 & 2 & 3 \end{bmatrix}$

$\text{(b)} \quad \begin{bmatrix} 2 & 4 & 6 \\ 3 & 6 & 9 \\ 2 & 3 & 4 \end{bmatrix}$

$\text{(c)} \quad \begin{bmatrix} 5 & 0 & 5 \\ 10 & 0 & 10 \\ -5 & 0 & 5 \end{bmatrix}$

$\text{(d)} \quad \begin{bmatrix} 5 & 0 & 5 \\ 10 & 0 & 10 \\ -5 & 0 & -5 \end{bmatrix}$

Which of the above kernels are separable?

Select all that apply.

A
(a)
B
(b)
C
(c)
D
(d)

Show answer

Correct answers

A
(a)
D
(d)

Question 24 on its own page

Question 25

+2 marksOne or more correct options

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

Select all that apply.

Show answer

Correct answers

Question 25 on its own page

Question 26

+2 marksOne or more correct options

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

Select all that apply.

Show answer

Correct answers

Question 26 on its own page

Question 27

+1 markWritten answer

Based on the above data answer the given subquestions.

Enter the correct answer for blank (a) ____________
NOTE: Enter the exact answer without any extra space in the beginning or at the end.

Show answer

Correct answer: high

Question 27 on its own page

Question 28

+1 markWritten answer

Based on the above data answer the given subquestions.

Enter the correct answer for blank (b) ____________
NOTE: Enter the exact answer without any extra space in the beginning or at the end.

Show answer

Correct answer: high

Question 28 on its own page

Question 29

+1 markWritten answer

Based on the above data answer the given subquestions.

Enter the correct answer for blank (a) ____________
NOTE: Enter the exact answer without any extra space in the beginning or at the end.

Show answer

Correct answer: thick or coarse or large scale

Question 29 on its own page

Question 30

+1 markWritten answer

Based on the above data answer the given subquestions.

Enter the correct answer for blank (b) ____________
NOTE: Enter the exact answer without any extra space in the beginning or at the end.

Show answer

Correct answer: fine

Question 30 on its own page

Question 31

+0.5 marksNumerical answer

Based on the above data answer the given subquestions.

a11= ____________

Show answer

Correct answer: 1

Question 31 on its own page

Question 32

+0.5 marksNumerical answer

Based on the above data answer the given subquestions.

a12= ____________

Show answer

Correct answer: 0.5

Question 32 on its own page

Question 33

+0.5 marksNumerical answer

Based on the above data answer the given subquestions.

a21= ____________

Show answer

Correct answer: 0

Question 33 on its own page

Question 34

+0.5 marksNumerical answer

Based on the above data answer the given subquestions.

a22= ____________

Show answer

Correct answer: 1

Question 34 on its own page

Question 35

+1 markNumerical answer

Show answer

Correct answer: 3

Question 35 on its own page

Question 36

+1 markNumerical answer

Show answer

Correct answer: 55

Question 36 on its own page