da5006_2025T3_Q1_NA.pdf

Deep Learning for Computer Vision · Quiz 1 · Sep 2025

Questions and published explanations below are available without starting a test. Some questions may not have a published solution yet.

Question 180 MSQ · 1.0 marks

Consider N cities in a Euclidean plane and use the Euclidean Distance as the distance measure. For each city, take that city as the fulcrum (base) city and compute its Savings tour. From the resulting N Savings tours, select the cheapest tour. What can you conclude about the above procedure?

This procedure can be used to compute the optimal TSP tour.
This procedure is not suitable for computing the optimal TSP tour.
This procedure may not always terminate.
This procedure will always terminate. **DL(CV)** **Section Id :** 640653106082 **Section Number :** 11 **Section type :** Online **Mandatory or Optional :** Mandatory **Number of Questions :** 32 **Number of Questions to be attempted :** 32 **Section Marks :** 79 **Display Number Panel :** Yes **Section Negative Marks :** 0 **Group All Questions :** No **Enable Mark as Answered Mark for Review and** No **Clear Response :** **Section Maximum Duration :** 0 **Section Minimum Duration :** 0 **Section Time In :** Minutes **Maximum Instruction Time :** 0

A published solution is not available for this question yet.

Question 182 MCQ · 2.0 marks

[[IMAGE:abc91c59021acca6_2_0]]

130.00
127.50
125.00
120.00

A published solution is not available for this question yet.

Question 183 MCQ · 2.0 marks

Which of the following statements is **false**?

Bilateral filtering is a non-linear, edge-preserving local operation.
Median filtering is a linear filtering operation.
Histogram matching uses CDFs to map intensities between images.
Unsharp masking implements a high-boost (high-pass) effect.

A published solution is not available for this question yet.

Question 184 MCQ · 2.0 marks

Which of the following statements is **True**?

[[IMAGE:abc91c59021acca6_3_1]]
[[IMAGE:abc91c59021acca6_3_2]]
[[IMAGE:abc91c59021acca6_3_3]]
[[IMAGE:abc91c59021acca6_3_4]]

A published solution is not available for this question yet.

Question 185 MCQ · 2.0 marks

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

[[IMAGE:abc91c59021acca6_3_5]]
[[IMAGE:abc91c59021acca6_3_6]]
[[IMAGE:abc91c59021acca6_3_7]]
[[IMAGE:abc91c59021acca6_3_8]]

A published solution is not available for this question yet.

Question 186 MCQ · 2.0 marks

[[IMAGE:abc91c59021acca6_4_9]]

0.9829, 4.05, 1, 4.0673, 4.05, 4.05
0.8808, 3.50, 1, 3.54, 3.50, 3.50
0.7311, 2.00, 1, 2.13, 2.00, 2.00
0.5000, 0.00, 0, 0.69, 0.00, 0.00

A published solution is not available for this question yet.

Question 187 MCQ · 2.0 marks

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

2 → 1 → 3 → 4 → 5
1 → 2 → 3 → 4 → 5
1 → 3 → 2 → 4 → 5
3 → 1 → 2 → 5 → 4

A published solution is not available for this question yet.

Question 188 MCQ · 2.0 marks

Correct order of SIFT stages is:

Orientation→ Descriptor → Localization → Extrema Detection
Extrema Detection → Localization→ Orientation→ Descriptor
Extrema Detection → Descriptor → Localization → Orientation
None of these

A published solution is not available for this question yet.

Question 189 MCQ · 2.0 marks

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

Strong edge
Weak edge
Non-edge
Ambiguous

A published solution is not available for this question yet.

Question 190 MCQ · 2.0 marks

[[IMAGE:abc91c59021acca6_5_10]]

1→ii, 2→i, 3→iii, 4→iv
1→i, 2→ii, 3→iii, 4→iv
1→i, 2→iv, 3→ii, 4→iii
1→iv, 2→ii, 3→i, 4→iii

A published solution is not available for this question yet.

Question 191 MCQ · 2.0 marks

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:

7 x 7
9 x 9
11 x 11
13 x 13

A published solution is not available for this question yet.

Question 192 MCQ · 2.0 marks

Which is **True**?

Nesterov momentum looks ahead and often converges faster than classical momentum.
A large fixed learning rate always speeds convergence.
Adam uses only a first-moment estimate of gradients.
None of these

A published solution is not available for this question yet.

Question 193 MCQ · 2.0 marks

[[IMAGE:abc91c59021acca6_6_11]]

0.066
0.071
0.083
0.059

A published solution is not available for this question yet.

Question 194 MCQ · 2.0 marks

[[IMAGE:abc91c59021acca6_6_12]]

1→iii, 2→i, 3→v, 4→iv
1→i, 2→iii, 3→v, 4→ii
1→iii, 2→iv, 3→v, 4→ii
1→iii, 2→iv, 3→ii, 4→v

A published solution is not available for this question yet.

Question 195 MCQ · 2.0 marks

[[IMAGE:abc91c59021acca6_6_13]]

1→iii, 2→i, 3→ii
1→ii, 2→iii, 3→i
1→iii, 2→ii, 3→i
None of these

A published solution is not available for this question yet.

Question 196 MSQ · 3.0 marks

Which statements are **true**? (Select all that apply)

[[IMAGE:abc91c59021acca6_7_14]]
[[IMAGE:abc91c59021acca6_7_15]]
[[IMAGE:abc91c59021acca6_7_16]]
[[IMAGE:abc91c59021acca6_7_17]]

A published solution is not available for this question yet.

Question 197 MSQ · 3.0 marks

Which statements are **true**? (Select all that apply)

[[IMAGE:abc91c59021acca6_7_18]]
[[IMAGE:abc91c59021acca6_7_19]]
[[IMAGE:abc91c59021acca6_7_20]]
[[IMAGE:abc91c59021acca6_7_21]]

A published solution is not available for this question yet.

Question 198 MSQ · 3.0 marks

About convolution and Fourier analysis, which are **true**?

[[IMAGE:abc91c59021acca6_8_22]]
[[IMAGE:abc91c59021acca6_8_23]]
[[IMAGE:abc91c59021acca6_8_24]]
[[IMAGE:abc91c59021acca6_8_25]]

A published solution is not available for this question yet.

Question 199 MSQ · 3.0 marks

Which of the following 3 x 3 kernels are separable?

[[IMAGE:abc91c59021acca6_8_26]]
[[IMAGE:abc91c59021acca6_8_27]]
[[IMAGE:abc91c59021acca6_8_28]]
[[IMAGE:abc91c59021acca6_8_29]]

A published solution is not available for this question yet.

Question 200 MSQ · 3.0 marks

Which statements are **false**?

Momentum maintains an EMA-like velocity of gradients/updates.
RMSProp normalizes step sizes by a running RMS of gradients.
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.
Cosine-annealed warm restarts can help escape sharp minima.

A published solution is not available for this question yet.

Question 201 NAT · 3.0 marks

[[IMAGE:abc91c59021acca6_9_30]]

A published solution is not available for this question yet.

Question 202 NAT · 3.0 marks

[[IMAGE:abc91c59021acca6_10_31]]

A published solution is not available for this question yet.

Question 203 NAT · 3.0 marks

[[IMAGE:abc91c59021acca6_10_32]]

A published solution is not available for this question yet.

Question 204 NAT · 3.0 marks

[[IMAGE:abc91c59021acca6_10_33]]

A published solution is not available for this question yet.

Question 205 NAT · 3.0 marks

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 _________________.

A published solution is not available for this question yet.

Question 206 NAT · 3.0 marks

[[IMAGE:abc91c59021acca6_11_34]]

A published solution is not available for this question yet.

Question 207 NAT · 3.0 marks

[[IMAGE:abc91c59021acca6_11_35]] **NOTE:** Enter your answer in three decimal places.

A published solution is not available for this question yet.

Question 208 NAT · 3.0 marks

[[IMAGE:abc91c59021acca6_12_36]]

A published solution is not available for this question yet.

Question 209 NAT · 3.0 marks

[[IMAGE:abc91c59021acca6_12_37]]

A published solution is not available for this question yet.

Question 210 SHORT_TEXT · 1.5 marks

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.

A published solution is not available for this question yet.

Question 211 SHORT_TEXT · 1.5 marks

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.

A published solution is not available for this question yet.

Question 212 SHORT_TEXT · 1.5 marks

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.

A published solution is not available for this question yet.

Question 213 SHORT_TEXT · 1.5 marks

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.

A published solution is not available for this question yet.

Question 214 SHORT_TEXT · 1.5 marks

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.

A published solution is not available for this question yet.

Question 215 SHORT_TEXT · 1.5 marks

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

A published solution is not available for this question yet.