uiz Space

September 2025 term · Deep Learning for Computer Vision · BSDA5006

Deep Learning for Computer Vision Quiz 1: 26 October 2025 (September 2025 term)

The IIT Madras BS Deep Learning for Computer Vision (Deep Learning for Computer Vision) Quiz 1 paper sat on 26 Oct 2025, in the September 2025 term: 34 questions for 79 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
34
Marks
79
Duration
120 min
MCQ
14
MSQ
5
Numerical
9
Written
6
Take as mock testPractise with answers

Updated

Official paper: IIT M DEGREE AN EXAM QDB2 26 Oct 2025 · No negative marking.

Question 1

+2 marksOne correct option
  1. A

    130.00

  2. B

    127.50

  3. C

    125.00

  4. D

    120.00

Show answer

Correct answer

  • B

    127.50

Question 1 on its own page

Question 2

+2 marksOne correct option

Which of the following statements is false?

  1. A

    Bilateral filtering is a non-linear, edge-preserving local operation.

  2. B

    Median filtering is a linear filtering operation.

  3. C

    Histogram matching uses CDFs to map intensities between images.

  4. D

    Unsharp masking implements a high-boost (high-pass) effect.

Show answer

Correct answer

  • B

    Median filtering is a linear filtering operation.

Question 2 on its own page

Question 3

+2 marksOne correct option

Which of the following statements is True?

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

Correct answer

  • A
Question 3 on its own page

Question 4

+2 marksOne correct option

Which filter leaves the center pixel unchanged for any image under convolution?

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

Correct answer

  • B
Question 4 on its own page

Question 5

+2 marksOne correct option
  1. A

    0.9829, 4.05, 1, 4.0673, 4.05, 4.05

  2. B

    0.8808, 3.50, 1, 3.54, 3.50, 3.50

  3. C

    0.7311, 2.00, 1, 2.13, 2.00, 2.00

  4. D

    0.5000, 0.00, 0, 0.69, 0.00, 0.00

Show answer

Correct answer

  • A

    0.9829, 4.05, 1, 4.0673, 4.05, 4.05

Question 5 on its own page

Question 6

+2 marksOne correct option

Choose the correct sequence for Canny edge detection:
1. Smooth with Gaussian
2. Compute gradient magnitude & direction
3. Non-maximum suppression
4. Double thresholding (strong/weak)
5. Edge tracking by hysteresis

  1. A

    2 → 1 → 3 → 4 → 5

  2. B

    1 → 2 → 3 → 4 → 5

  3. C

    1 → 3 → 2 → 4 → 5

  4. D

    3 → 1 → 2 → 5 → 4

Show answer

Correct answer

  • B

    1 → 2 → 3 → 4 → 5

Question 6 on its own page

Question 7

+2 marksOne correct option

Correct order of SIFT stages is:

  1. A

    Orientation→ Descriptor → Localization → Extrema Detection

  2. B

    Extrema Detection → Localization→ Orientation→ Descriptor

  3. C

    Extrema Detection → Descriptor → Localization → Orientation

  4. D

    None of these

Show answer

Correct answer

  • B

    Extrema Detection → Localization→ Orientation→ Descriptor

Question 7 on its own pageAlso asked in Quiz 1 15 Mar 2026, Quiz 1 19 Jul 2026

Question 8

+2 marksOne correct option

In double thresholding, Thigh = 120, Tlow = 50. A pixel with gradient magnitude 45 is classified as:

  1. A

    Strong edge

  2. B

    Weak edge

  3. C

    Non-edge

  4. D

    Ambiguous

Show answer

Correct answer

  • C

    Non-edge

Question 8 on its own page

Question 9

+2 marksOne correct option
  1. A

    1→ii, 2→i, 3→iii, 4→iv

  2. B

    1→i, 2→ii, 3→iii, 4→iv

  3. C

    1→i, 2→iv, 3→ii, 4→iii

  4. D

    1→iv, 2→ii, 3→i, 4→iii

Show answer

Correct answer

  • B

    1→i, 2→ii, 3→iii, 4→iv

Question 9 on its own page

Question 10

+2 marksOne correct option

An RGB image goes through Conv layer: 64 kernels of size 7 x 7, stride 2, then MaxPool 3 x 3, stride 2. The receptive field of a pooling-layer neuron is:

  1. A

    7 x 7

  2. B

    9 x 9

  3. C

    11 x 11

  4. D

    13 x 13

Show answer

Correct answer

  • C

    11 x 11

Question 10 on its own page

Question 11

+2 marksOne correct option

Which is True?

  1. A

    Nesterov momentum looks ahead and often converges faster than classical momentum.

  2. B

    A large fixed learning rate always speeds convergence.

  3. C

    Adam uses only a first-moment estimate of gradients.

  4. D

    None of these

Show answer

Correct answer

  • A

    Nesterov momentum looks ahead and often converges faster than classical momentum.

Question 11 on its own page

Question 12

+2 marksOne correct option
  1. A

    0.066

  2. B

    0.071

  3. C

    0.083

  4. D

    0.059

Show answer

Correct answer

  • B

    0.071

Question 12 on its own page

Question 13

+2 marksOne correct option
  1. A

    1→iii, 2→i, 3→v, 4→iv

  2. B

    1→i, 2→iii, 3→v, 4→ii

  3. C

    1→iii, 2→iv, 3→v, 4→ii

  4. D

    1→iii, 2→iv, 3→ii, 4→v

Show answer

Correct answer

  • C

    1→iii, 2→iv, 3→v, 4→ii

Question 13 on its own page

Question 14

+2 marksOne correct option
  1. A

    1→iii, 2→i, 3→ii

  2. B

    1→ii, 2→iii, 3→i

  3. C

    1→iii, 2→ii, 3→i

  4. D

    None of these

Show answer

Correct answer

  • A

    1→iii, 2→i, 3→ii

Question 14 on its own page

Question 15

+3 marksOne or more correct options

Which statements are true? (Select all that apply)

Select all that apply.

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

Correct answers

  • B
  • C
  • D
Question 15 on its own page

Question 16

+3 marksOne or more correct options

Which statements are true? (Select all that apply)

Select all that apply.

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

Correct answers

  • A
  • B
  • C
  • D
Question 16 on its own page

Question 17

+3 marksOne or more correct options

About convolution and Fourier analysis, which are true?

Select all that apply.

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

Correct answers

  • A
  • B
  • C
Question 17 on its own page

Question 18

+3 marksOne or more correct options

Which of the following 3 x 3 kernels are separable?

Select all that apply.

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

Correct answers

  • A
  • B
  • D
Question 18 on its own page

Question 19

+3 marksOne or more correct options

Which statements are false?

Select all that apply.

  1. A

    Momentum maintains an EMA-like velocity of gradients/updates.

  2. B

    RMSProp normalizes step sizes by a running RMS of gradients.

  3. C

    In the Adam optimizer, the hyper-parameters β1 and β2 control the exponential decay rates for the moving averages of the gradient and its squared vale. Adam with reduces to SGD with momentum. β1 = 0 and β2 = 0 reduces to SGD with momentum.

  4. D

    Cosine-annealed warm restarts can help escape sharp minima.

Show answer

Correct answer

  • C

    In the Adam optimizer, the hyper-parameters β1 and β2 control the exponential decay rates for the moving averages of the gradient and its squared vale. Adam with reduces to SGD with momentum. β1 = 0 and β2 = 0 reduces to SGD with momentum.

Question 19 on its own page

Question 20

+3 marksNumerical answer

Consider the 5×55 \times 5 grayscale image

[14182225311916202324272119262829232217183326242027]\begin{bmatrix} 14 & 18 & 22 & 25 & 31 \\ 19 & 16 & 20 & 23 & 24 \\ 27 & 21 & 19 & 26 & 28 \\ 29 & 23 & 22 & 17 & 18 \\ 33 & 26 & 24 & 20 & 27 \end{bmatrix}

After a median filter with 3×33 \times 3 window, stride 1, no padding, the value at position (3,3)(3, 3) of the output is __________.

Show answer

Correct answer: 22

Question 20 on its own page

Question 21

+3 marksNumerical answer
Show answer

Correct answer: 8

Question 21 on its own page

Question 22

+3 marksNumerical answer
Show answer

Correct answer: -0.515

Question 22 on its own page

Question 23

+3 marksNumerical answer
Show answer

Correct answer: 28

Question 23 on its own page

Question 24

+3 marksNumerical answer

Two successive convolutions each with: kernel 7 x 7, padding 3, stride 2. Input is 100 x 100. The final feature-map side length F is _________________.

Show answer

Correct answer: 25

Question 24 on its own page

Question 25

+3 marksNumerical answer
Show answer

Correct answer: 73728

Question 25 on its own page

Question 26

+3 marksNumerical answer

NOTE: Enter your answer in three decimal places.

Show answer

Correct answer: 1.223

Question 26 on its own page

Question 27

+3 marksNumerical answer
Show answer

Correct answer: 0

Question 27 on its own page

Question 28

+3 marksNumerical answer
Show answer

Correct answer: 99

Question 28 on its own page

Question 29

+1.5 marksWritten answer

In Canny, increasing the high threshold tends to (a) _______________ false positives and (b) ____________ false negatives.
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: decrease

Question 29 on its own page

Question 30

+1.5 marksWritten answer

In Canny, increasing the high threshold tends to (a) _______________ false positives and (b) ____________ false negatives.
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: increase

Question 30 on its own page

Question 31

+1.5 marksWritten answer

During non-maximum suppression, comparisons are made along the gradient (a) _____________ to keep only local (b) _______________.
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: direction

Question 31 on its own page

Question 32

+1.5 marksWritten answer

During non-maximum suppression, comparisons are made along the gradient (a) _____________ to keep only local (b) _______________.
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: maxima

Question 32 on its own page

Question 33

+1.5 marksWritten answer

The gradient of an image I points in the direction of the most rapid change in intensity. Taking image derivatives accentuates (a) ______________ frequencies and hence amplifies noise, since the proportion of noise to signal is larger at (b) _______________ frequencies. The common solution is to smooth the image prior to computing gradients.
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 or higher or large or largest

Question 33 on its own page

Question 34

+1.5 marksWritten answer

The gradient of an image I points in the direction of the most rapid change in intensity. Taking image derivatives accentuates (a) ______________ frequencies and hence amplifies noise, since the proportion of noise to signal is larger at (b) _______________ frequencies. The common solution is to smooth the image prior to computing gradients.
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 or higher or large or largest

Question 34 on its own page