da5006_2025T3_Q2_NA.pdf

Deep Learning for Computer Vision · Quiz 2 · Sep 2025

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

Question 130 MCQ · 2.0 marks

[[IMAGE:25623151533c4118_2_6]]

[[IMAGE:25623151533c4118_2_7]]
[[IMAGE:25623151533c4118_2_8]]
[[IMAGE:25623151533c4118_2_9]]
[[IMAGE:25623151533c4118_2_10]]

A published solution is not available for this question yet.

Question 131 MCQ · 2.0 marks

Which of the following architectures introduced the ROI pooling layer for extracting fixed-size feature maps from variable-size region proposals?

R-CNN
Fast R-CNN
Faster R-CNN
YOLO

A published solution is not available for this question yet.

Question 132 MCQ · 2.0 marks

Which object detection method first integrated a Region Proposal Network (RPN) to generate region proposals within the detection model?

R-CNN
Fast R-CNN
Faster R-CNN
YOLO

A published solution is not available for this question yet.

Question 133 MCQ · 2.0 marks

Which architecture performs object detection as a single regression problem from image pixels to bounding boxes and class probabilities?

R-CNN
Fast R-CNN
Faster R-CNN
YOLO

A published solution is not available for this question yet.

Question 134 MCQ · 2.0 marks

[[IMAGE:25623151533c4118_3_11]]

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

A published solution is not available for this question yet.

Question 135 MCQ · 2.0 marks

Consider the following statements P and Q regarding AlexNet and choose the correct option: **(P)** In AlexNet, a trainable Local Response Normalization Layers were introduced to emulate the competitive nature of real neurons, where highly active neurons suppress the activity of neighboring neurons, creating competition among different kernel outputs. **(Q)** In AlexNet, a total of 8 Convolutional layers contain only about 6-7% of the total parameters hence account for the least computation.

Only statement P is true
Only statement Q is true
Both statements are true
None of the statements is true

A published solution is not available for this question yet.

Question 136 MCQ · 2.0 marks

Consider two bounding boxes in an image: - Box A: top-left at (0, 0), bottom-right at (12, 12) - Box B: top-left at (4, 4), bottom-right at (16, 16) What is the Intersection over Union (IoU) between these two boxes ______________

A published solution is not available for this question yet.

Question 137 MCQ · 2.0 marks

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

Attention mechanisms can be applied to the bidirectional RNN model
An image captioning network cannot be trained end-to-end even though we are using 2 different modalities to train the network
One of the key components in the vanilla transformer are the recurrent connections that help them to deal with variable input length.
All Attention mechanisms can be applied to the bidirectional RNN model, An image captioning network cannot be trained end-to-end even though we are using 2 different modalities to train the network, One of the key components in the vanilla transformer are the recurrent connections that help them to deal with variable input length.
None of these

A published solution is not available for this question yet.

Question 138 MCQ · 2.0 marks

[[IMAGE:25623151533c4118_5_12]]

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

A published solution is not available for this question yet.

Question 139 MCQ · 2.0 marks

[[IMAGE:25623151533c4118_5_13]]

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

A published solution is not available for this question yet.

Question 140 MCQ · 2.0 marks

[[IMAGE:25623151533c4118_6_14]]

1→iii, 2→ii, 3→v, 4→iv,5→i
1→iii, 2→iv, 3→i, 4→ii,5→v
1→i, 2→iii, 3→iv, 4→ii,5→v
1→v, 2→iv, 3→iii, 4→i,5→ii

A published solution is not available for this question yet.

Question 141 MCQ · 2.0 marks

Which of the following techniques help mitigate the **vanishing gradient problem** in recurrent neural networks? 1. Gradient clipping 2. Use of ReLU activation to preserve gradient flow 3. Use of LSTM units 4. Data augmentation (e.g., reversing input sequence)

1 and 2 only
2 and 3 only
3 and 4 only
1, 2, and 3 only

A published solution is not available for this question yet.

Question 142 MCQ · 2.0 marks

Which of the following techniques help mitigate the **exploding gradient problem** in recurrent neural networks? 1. Gradient clipping 2. Use of Sigmoid activation to prevent gradient growth 3. Use of LSTM units 4. Data augmentation (e.g., reversing input sequence)

1 and 2 only
1 and 3 only
1, 2, and 3
All of these

A published solution is not available for this question yet.

Question 143 MCQ · 2.0 marks

Which one of the following statements is false? (Pick the most appropriate one.)

Attention mechanisms cannot be applied to the bidirectional RNN model
An image captioning network cannot be trained end-to-end even though we are using 2 different modalities to train the network
One of the key components in the vanilla transformer is the recurrent connection that help them to deal with variable input length.
All of these

A published solution is not available for this question yet.

Question 144 NAT · 2.0 marks

[[IMAGE:25623151533c4118_7_15]]

A published solution is not available for this question yet.

Question 145 MSQ · 3.0 marks

Which of the following is true regarding Hard Attention and Soft Attention?

Soft Attention is smooth and differentiable
Variance reduction techniques are used to train Soft Attention models
Soft Attention is computationally cheaper than Hard Attention when the source input is large
The inference (test time) overhead is low in Hard Attention when compared to Soft Attention models

A published solution is not available for this question yet.

Question 146 MSQ · 3.0 marks

Which of the following are **False:**

[[IMAGE:25623151533c4118_8_16]]
[[IMAGE:25623151533c4118_8_17]]
[[IMAGE:25623151533c4118_8_18]]
[[IMAGE:25623151533c4118_8_19]]

A published solution is not available for this question yet.

Question 147 MSQ · 3.0 marks

Which techniques help mitigate exploding/vanishing gradients in RNNs? (Select all that apply.)

Gradient clipping
Orthogonal or identity initialization of recurrent weights
Using LSTM/GRU cells
Randomly reversing input sequences as augmentation

A published solution is not available for this question yet.

Question 148 NAT · 0.5 marks

[[IMAGE:25623151533c4118_9_20]] Based on the above data, answer the given subquestions.

[[IMAGE:25623151533c4118_9_21]]

A published solution is not available for this question yet.

Question 149 NAT · 0.5 marks

[[IMAGE:25623151533c4118_9_20]] Based on the above data, answer the given subquestions.

[[IMAGE:25623151533c4118_9_22]]

A published solution is not available for this question yet.

Question 150 NAT · 0.5 marks

[[IMAGE:25623151533c4118_9_20]] Based on the above data, answer the given subquestions.

[[IMAGE:25623151533c4118_10_23]]

A published solution is not available for this question yet.

Question 151 NAT · 0.5 marks

[[IMAGE:25623151533c4118_9_20]] Based on the above data, answer the given subquestions.

[[IMAGE:25623151533c4118_10_24]]

A published solution is not available for this question yet.

Question 152 NAT · 1.0 marks

[[IMAGE:25623151533c4118_9_20]] Based on the above data, answer the given subquestions.

[[IMAGE:25623151533c4118_10_25]]

A published solution is not available for this question yet.

Question 153 NAT · 1.0 marks

[[IMAGE:25623151533c4118_9_20]] Based on the above data, answer the given subquestions.

[[IMAGE:25623151533c4118_11_26]]

A published solution is not available for this question yet.

Question 154 NAT · 2.0 marks

[[IMAGE:25623151533c4118_11_27]] Based on the above data, answer the given subquestions.

Number of Parameters:_____________

A published solution is not available for this question yet.

Question 155 NAT · 2.0 marks

[[IMAGE:25623151533c4118_11_27]] Based on the above data, answer the given subquestions.

Computational Cost:________________

A published solution is not available for this question yet.

Question 156 NAT · 1.0 marks

Using the same dimensions specified in the previous question main data, calculate the number of parameters and computational cost, but make use of **Depthwise Seperable convolution** and **pointwise convolution** instead of standard convolution. Based on the above data, answer the given subquestions.

Number of parameters for depthwise seperable convolution: __________

A published solution is not available for this question yet.

Question 157 NAT · 1.0 marks

Computational Cost for depthwise seperable convolution:____________

A published solution is not available for this question yet.

Question 158 NAT · 1.0 marks

Number of parameters for pointwise convolution:_____________

A published solution is not available for this question yet.

Question 159 NAT · 1.0 marks

Computational cost for pointwise convolution:____________

A published solution is not available for this question yet.

Question 160 NAT · 1.0 marks

[[IMAGE:25623151533c4118_14_28]] Based on the above data, answer the given subquestions.

Number of weights in Weight Matrix U1 is:_____________

A published solution is not available for this question yet.

Question 161 NAT · 1.0 marks

[[IMAGE:25623151533c4118_14_28]] Based on the above data, answer the given subquestions.

Number of weights in Weight Matrix V1 is:_____________

A published solution is not available for this question yet.

Question 162 NAT · 1.0 marks

[[IMAGE:25623151533c4118_14_28]] Based on the above data, answer the given subquestions.

Number of weights in Weight Matrix U2 is:_____________

A published solution is not available for this question yet.

Question 163 NAT · 0.5 marks

[[IMAGE:25623151533c4118_14_28]] Based on the above data, answer the given subquestions.

Number of weights in Weight Matrix V2 is:_____________

A published solution is not available for this question yet.

Question 164 NAT · 0.5 marks

[[IMAGE:25623151533c4118_14_28]] Based on the above data, answer the given subquestions.

Number of weights in Weight Matrix W is:_____________

A published solution is not available for this question yet.

Question 165 NAT · 0.5 marks

[[IMAGE:25623151533c4118_16_29]]

[[IMAGE:25623151533c4118_16_30]]

A published solution is not available for this question yet.

Question 166 NAT · 0.5 marks

[[IMAGE:25623151533c4118_16_29]]

[[IMAGE:25623151533c4118_17_31]]

A published solution is not available for this question yet.

Question 167 NAT · 0.5 marks

[[IMAGE:25623151533c4118_16_29]]

[[IMAGE:25623151533c4118_17_32]]

A published solution is not available for this question yet.

Question 168 NAT · 0.5 marks

[[IMAGE:25623151533c4118_16_29]]

[[IMAGE:25623151533c4118_17_33]]

A published solution is not available for this question yet.

Question 169 NAT · 0.5 marks

[[IMAGE:25623151533c4118_16_29]]

[[IMAGE:25623151533c4118_18_34]]

A published solution is not available for this question yet.

Question 170 NAT · 0.5 marks

[[IMAGE:25623151533c4118_16_29]]

[[IMAGE:25623151533c4118_18_35]]

A published solution is not available for this question yet.

Question 171 NAT · 0.5 marks

[[IMAGE:25623151533c4118_16_29]]

[[IMAGE:25623151533c4118_18_36]]

A published solution is not available for this question yet.

Question 172 NAT · 0.5 marks

[[IMAGE:25623151533c4118_16_29]]

[[IMAGE:25623151533c4118_19_37]]

A published solution is not available for this question yet.

Question 173 NAT · 0.5 marks

[[IMAGE:25623151533c4118_19_38]] Based on the above data, answer the given subquestions.

[[IMAGE:25623151533c4118_20_39]]

A published solution is not available for this question yet.

Question 174 NAT · 0.5 marks

[[IMAGE:25623151533c4118_19_38]] Based on the above data, answer the given subquestions.

[[IMAGE:25623151533c4118_20_40]]

A published solution is not available for this question yet.

Question 175 NAT · 0.5 marks

[[IMAGE:25623151533c4118_19_38]] Based on the above data, answer the given subquestions.

[[IMAGE:25623151533c4118_20_41]]

A published solution is not available for this question yet.

Question 176 NAT · 0.5 marks

[[IMAGE:25623151533c4118_19_38]] Based on the above data, answer the given subquestions.

[[IMAGE:25623151533c4118_20_42]]

A published solution is not available for this question yet.

Question 177 NAT · 0.5 marks

[[IMAGE:25623151533c4118_19_38]] Based on the above data, answer the given subquestions.

[[IMAGE:25623151533c4118_21_43]]

A published solution is not available for this question yet.

Question 178 NAT · 0.5 marks

[[IMAGE:25623151533c4118_19_38]] Based on the above data, answer the given subquestions.

[[IMAGE:25623151533c4118_21_44]]

A published solution is not available for this question yet.

Question 179 NAT · 0.5 marks

[[IMAGE:25623151533c4118_19_38]] Based on the above data, answer the given subquestions.

[[IMAGE:25623151533c4118_21_45]]

A published solution is not available for this question yet.