da5006_2025T2_Q1_NA.pdf

Deep Learning for Computer Vision · Quiz 1 · May 2025

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

Question 155 NAT · 2.0 marks

If we use top-k sampling with k=2 at timestep 1, what is the normalized probability of selecting token “sky” at the timestep=1?

A published solution is not available for this question yet.

Question 157 MCQ · 2.0 marks

[[IMAGE:ca3537c411037961_2_0]]

104.94
100.25
110.56
98.78

A published solution is not available for this question yet.

Question 158 MCQ · 2.0 marks

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

Histogram equalization is a global operation.
Gaussian filtering is a local operation.
Convolution in the spatial domain corresponds to multiplication in the frequency domain.
Median filtering is a global operation.

A published solution is not available for this question yet.

Question 159 MCQ · 2.0 marks

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

Gaussian filter is a separable filter because it is linear.
Median filter is a non-separable filter.
Gaussian filter is a high-pass filter.
Mean filter is a non-separable filter because it is non-linear.

A published solution is not available for this question yet.

Question 160 MCQ · 2.0 marks

[[IMAGE:ca3537c411037961_4_1]]

[[IMAGE:ca3537c411037961_4_2]]
[[IMAGE:ca3537c411037961_4_3]]
[[IMAGE:ca3537c411037961_4_4]]
[[IMAGE:ca3537c411037961_4_5]]

A published solution is not available for this question yet.

Question 161 MCQ · 2.0 marks

[[IMAGE:ca3537c411037961_5_6]]

0.9820, 4.00, 1, 4.02, 4.00, 4.00
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 162 MCQ · 2.0 marks

[[IMAGE:ca3537c411037961_5_7]]

[[IMAGE:ca3537c411037961_5_8]]
[[IMAGE:ca3537c411037961_5_9]]
[[IMAGE:ca3537c411037961_5_10]]
[[IMAGE:ca3537c411037961_5_11]]

A published solution is not available for this question yet.

Question 163 MCQ · 2.0 marks

[[IMAGE:ca3537c411037961_6_12]]

[[IMAGE:ca3537c411037961_6_13]]
[[IMAGE:ca3537c411037961_6_14]]
[[IMAGE:ca3537c411037961_6_15]]
[[IMAGE:ca3537c411037961_6_16]]

A published solution is not available for this question yet.

Question 164 MCQ · 2.0 marks

During the double thresholding step in Canny edge detection, the high threshold is set at 100 and the low threshold is 40. A pixel gradient magnitude of 65 will be classified as:

Strong edge
Weak edge
Non-edge
Ambiguous edge

A published solution is not available for this question yet.

Question 165 MCQ · 2.0 marks

[[IMAGE:ca3537c411037961_7_17]]

[[IMAGE:ca3537c411037961_7_18]]
[[IMAGE:ca3537c411037961_7_19]]
[[IMAGE:ca3537c411037961_7_20]]
[[IMAGE:ca3537c411037961_7_21]]

A published solution is not available for this question yet.

Question 166 MCQ · 2.0 marks

[[IMAGE:ca3537c411037961_7_22]]

[[IMAGE:ca3537c411037961_7_23]]
[[IMAGE:ca3537c411037961_7_24]]
[[IMAGE:ca3537c411037961_7_25]]
[[IMAGE:ca3537c411037961_7_26]]

A published solution is not available for this question yet.

Question 167 MCQ · 2.0 marks

Which of the following statements are True?

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

A published solution is not available for this question yet.

Question 168 MCQ · 2.0 marks

[[IMAGE:ca3537c411037961_8_27]]

0.16
0.08
0.20
0.12

A published solution is not available for this question yet.

Question 169 MCQ · 2.0 marks

[[IMAGE:ca3537c411037961_9_28]]

[[IMAGE:ca3537c411037961_9_29]]
[[IMAGE:ca3537c411037961_9_30]]
[[IMAGE:ca3537c411037961_9_31]]
[[IMAGE:ca3537c411037961_9_32]]

A published solution is not available for this question yet.

Question 170 MCQ · 2.0 marks

[[IMAGE:ca3537c411037961_9_33]]

[[IMAGE:ca3537c411037961_9_34]]
[[IMAGE:ca3537c411037961_9_35]]
[[IMAGE:ca3537c411037961_9_36]]
[[IMAGE:ca3537c411037961_9_37]]

A published solution is not available for this question yet.

Question 171 MSQ · 3.0 marks

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

[[IMAGE:ca3537c411037961_10_38]]
[[IMAGE:ca3537c411037961_10_39]]
[[IMAGE:ca3537c411037961_10_40]]
[[IMAGE:ca3537c411037961_10_41]]

A published solution is not available for this question yet.

Question 172 MSQ · 3.0 marks

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

[[IMAGE:ca3537c411037961_10_42]]
[[IMAGE:ca3537c411037961_10_43]]
[[IMAGE:ca3537c411037961_10_44]]
[[IMAGE:ca3537c411037961_10_45]]

A published solution is not available for this question yet.

Question 173 MSQ · 3.0 marks

Consider the following statements. Which of the following statements are true?

[[IMAGE:ca3537c411037961_11_46]]
[[IMAGE:ca3537c411037961_11_47]]
[[IMAGE:ca3537c411037961_11_48]]
[[IMAGE:ca3537c411037961_11_49]]
[[IMAGE:ca3537c411037961_11_50]]
[[IMAGE:ca3537c411037961_11_51]]

A published solution is not available for this question yet.

Question 174 MSQ · 3.0 marks

[[IMAGE:ca3537c411037961_12_52]]

[[IMAGE:ca3537c411037961_12_53]]
[[IMAGE:ca3537c411037961_12_54]]
[[IMAGE:ca3537c411037961_12_55]]
[[IMAGE:ca3537c411037961_12_56]]

A published solution is not available for this question yet.

Question 175 MSQ · 3.0 marks

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

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

A published solution is not available for this question yet.

Question 176 NAT · 3.0 marks

[[IMAGE:ca3537c411037961_13_57]]

A published solution is not available for this question yet.

Question 177 NAT · 3.0 marks

[[IMAGE:ca3537c411037961_14_58]]

A published solution is not available for this question yet.

Question 178 NAT · 3.0 marks

[[IMAGE:ca3537c411037961_14_59]]

A published solution is not available for this question yet.

Question 179 NAT · 3.0 marks

[[IMAGE:ca3537c411037961_15_60]]

A published solution is not available for this question yet.

Question 180 NAT · 3.0 marks

[[IMAGE:ca3537c411037961_15_61]]

A published solution is not available for this question yet.

Question 181 NAT · 3.0 marks

[[IMAGE:ca3537c411037961_16_62]]

A published solution is not available for this question yet.

Question 182 NAT · 3.0 marks

[[IMAGE:ca3537c411037961_16_63]]

A published solution is not available for this question yet.

Question 183 NAT · 3.0 marks

[[IMAGE:ca3537c411037961_17_64]]

A published solution is not available for this question yet.

Question 184 NAT · 3.0 marks

[[IMAGE:ca3537c411037961_18_65]]

A published solution is not available for this question yet.

Question 185 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 186 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.

Question 187 SHORT_TEXT · 1.5 marks

In Canny edge detection, a large value of the Gaussian kernel spread σ leads to (a)________________ edges, while a small value of σ leads to (b)_________________ edges. 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 188 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.

Question 189 NAT · 1.5 marks

You have a visual codebook with 1500 visual words. From a test image, you extract 1200 SIFT descriptors, each of 128 dimensions. After assigning each descriptor to its nearest visual word, you compute the Bag-of-Words histogram by counting descriptor assignments. Based on the above data, answer the given subquestions.

What is the dimensionality of the Bag-of-Words (BoW) feature vector for this image?________________

A published solution is not available for this question yet.

Question 190 NAT · 1.5 marks

If instead, you concatenate all the 1200 descriptors into a single vector (without using BoW), what will be the dimensionality of that vector?__________________

A published solution is not available for this question yet.