BTechibtechi.in
Loading Loading
Free IIT Madras BS notes, PYQs and mock tests at btechi.in

DL for CV · Quiz 2 · 3 Aug 2025 (Afternoon)

52 questions · 61.999999999999986 marks · 60 min

Answer key Take as mock

Indian Institute of Technology Madras

BS Degree Programme · Examination & Study Paper

Deep Learning for Computer Vision

Quiz 2 · 3 Aug 2025 (Afternoon)

Official Paper

Examination Instructions & Guidelines

Solve on notebook/paper first before checking solutions.
MCQ: Exactly 1 option is correct. Negative marking applies.
MSQ: One or more options correct. Select all to score.
NAT: Numerical response. No negative marking.
Scientific calculator allowed for all calculations.
Official answer key is sealed at the end of this sheet.

Q1MCQ2 Marks·Choose one option
Asked 2 times Key ↓
1. A
2. B
3. C
4. D
Q2MCQ2 Marks·Choose one option
Key ↓
Which of the following architectures introduced the ROI pooling layer for extracting fixed-size feature maps from variable-size region proposals?
1. AR-CNN
2. BFast R-CNN
3. CFaster R-CNN
4. DYOLO
Q3MCQ2 Marks·Choose one option
Key ↓
Which object detection method first integrated a Region Proposal Network (RPN) to generate region proposals within the detection model?
1. AR-CNN
2. BFast R-CNN
3. CFaster R-CNN
4. DYOLO
Q4MCQ2 Marks·Choose one option
Key ↓
Which architecture performs object detection as a single regression problem from image pixels to bounding boxes and class probabilities?
1. AR-CNN
2. BFast R-CNN
3. CFaster R-CNN
4. DYOLO
Q5MCQ2 Marks·Choose one option
Key ↓
1. A
2. B
3. C
4. D
Q6MCQ2 Marks·Choose one option
Asked 2 times Key ↓
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.
1. AOnly statement P is true
2. BOnly statement Q is true
3. CBoth statements are true
4. DNone of these statements is true
Q7NAT2 Marks·Write the number
Key ↓
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 ____________(in %)
Your answer:
Q8MCQ2 Marks·Choose one option
Asked 4 times Key ↓
Which one of the following statements is True?
1. AAttention mechanisms can be applied to the bidirectional RNN model
2. BAn image captioning network cannot be trained end-to-end even though we are using 2 different modalities to train the network
3. COne of the key components in the vanilla transformer are the recurrent connections that help them to deal with variable input length.
4. DAll of these.
Q9MCQ2 Marks·Choose one option
Key ↓
1. A
2. B
3. C
4. D
Q10MCQ2 Marks·Choose one option
Asked 2 times Key ↓
1. A
2. B
3. C
4. D
Q11MCQ2 Marks·Choose one option
Key ↓
1. A
2. B
3. C
4. D
Q12MCQ2 Marks·Choose one option
Asked 3 times Key ↓
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. A1 and 2 only
2. B2 and 3 only
3. C3 and 4 only
4. D1, 2, and 3 only
Q13MCQ2 Marks·Choose one option
Asked 3 times Key ↓
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. A1 and 2 only
2. B1 and 3 only
3. C1, 2, and 3
4. DAll of these
Q14MCQ2 Marks·Choose one option
Asked 4 times Key ↓
Which one of the following statements is false? (Pick the most appropriate one.)
1. AAttention mechanisms cannot be applied to the bidirectional RNN model
2. BAn image captioning network cannot be trained end-to-end even though we are using 2 different modalities to train the network
3. COne of the key components in the vanilla transformer is the recurrent connection that help them to deal with variable input length.
4. DAll of these
Q15MSQ3 Marks·Choose all correct options
Key ↓
Which of the following is true regarding Hard Attention and Soft Attention?
1. ASoft Attention is smooth and differentiable
2. BVariance reduction techniques are used to train Soft Attention models
3. CSoft Attention is computationally cheaper than Hard Attention when the source input is large
4. DThe inference (test time) overhead is low in Hard Attention when compared to Soft Attention models
Q16MSQ3 Marks·Choose all correct options
Key ↓
Which of the following are true:
1. A
2. B
3. C
4. D
Q17NAT2 Marks·Write the number
Key ↓
Consider a Faster R-CNN object detection framework, which is being trained with a mini-batch size of 2. The RPN produces 512 proposals, out of which 256 and 128 of them are foreground proposals, corresponding to each image in the mini-batch. For a single mini-batch update, the bounding box regression loss will be computed_____________ times.
Your answer:
Read the passage below, then answer Q18–Q19
Suppose you want to build an encoder-decoder recurrent model with attention. The context vector at time step t is given by:
where α_(tj) refers to the alignment score between the decoder state at time t _____________and the encoder state at time _____________. Note: Please write your answer using variables
Based on the above data, answer the given subquestions.
Q18NAT1 Mark·Write the number
Key ↓
Decoder state at time t : _______________
Your answer:
Q19Short answer1 Mark·Write the answer
Key ↓
Encoder state at time: _______________
Your answer:
Read the passage below, then answer Q20–Q25
Consider a Gated Recurrent Unit (GRU) cell at time step ’t’.
For each of the entities in the given subquestions, enter the appropriate number from the figure that corresponds to it:
Based on the above data, answer the given subquestions.
Q20NAT0.66 Marks·Write the number
Key ↓
Hidden state h_(t−1)______________
Your answer:
Q21NAT0.66 Marks·Write the number
Key ↓
Hidden state h_t_____________
Your answer:
Q22NAT0.67 Marks·Write the number
Key ↓
Current Input x_t________________
Your answer:
Q23NAT0.67 Marks·Write the number
Key ↓
Update gate z_t_______________
Your answer:
Q24NAT0.67 Marks·Write the number
Key ↓
Reset gate r_t ______________
Your answer:
Q25NAT0.67 Marks·Write the number
Key ↓
New hidden state content e_h____________
Your answer:
Read the passage below, then answer Q26–Q27
Let input have size D_f × D_f × M where D_f = 10 and M = 256 and output feature map (after passing input through conv layer) has D_f × D_f × N size where N = 512. Assume padded convolution. Let width of the square kernel in conv layer be k where k = 7 (Ignore the bias term in the calculation). Calculate the number of parameters and computational cost for this convolution layer. Based on the above data, answer the given subquestions.
Q26NAT2 Marks·Write the number
Asked 2 times Key ↓
Number of Parameters:_____________
Your answer:
Q27NAT2 Marks·Write the number
Key ↓
Computational Cost:___________________
Your answer:
Read the passage below, then answer Q28–Q31
Let input have size D_f × D_f × M where D_f = 10 and M = 256 and output feature map (after passing input through conv layer) has D_f × D_f × N size where N = 512. Assume padded convolution. Let width of the square kernel in conv layer be k where k = 7 (Ignore the bias term in the calculation), 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.
Q28NAT1 Mark·Write the number
Key ↓
Number of parameters for depthwise seperable convolution:_______________
Your answer:
Q29NAT1 Mark·Write the number
Key ↓
Computational Cost for depthwise seperable convolution:____________________
Your answer:
Q30NAT1 Mark·Write the number
Key ↓
Number of parameters for pointwise convolution:___________________
Your answer:
Q31NAT1 Mark·Write the number
Key ↓
Computational cost for pointwise convolution:__________________
Your answer:
Read the passage below, then answer Q32–Q36
Based on the above data, answer the given subquestions.
Q32NAT0.8 Marks·Write the number
Key ↓
Number of weights in Weight Matrix U1 is:______________
Your answer:
Q33NAT0.8 Marks·Write the number
Key ↓
Number of weights in Weight Matrix V1 is:______________
Your answer:
Q34NAT0.8 Marks·Write the number
Key ↓
Number of weights in Weight Matrix U2 is:__________________
Your answer:
Q35NAT0.8 Marks·Write the number
Key ↓
Number of weights in Weight Matrix V2 is:___________________
Your answer:
Q36NAT0.8 Marks·Write the number
Key ↓
Number of weights in Weight Matrix W is:_______________
Your answer:
Read the passage below, then answer Q37–Q44
Q37NAT0.5 Marks·Write the number
Key ↓
e_(21): _________________
Your answer:
Q38NAT0.5 Marks·Write the number
Key ↓
e_(22): _________________
Your answer:
Q39NAT0.5 Marks·Write the number
Key ↓
e_(23): _________________
Your answer:
Q40NAT0.5 Marks·Write the number
Key ↓
α_(21): _________________
Your answer:
Q41NAT0.5 Marks·Write the number
Key ↓
α_(22): _________________
Your answer:
Q42NAT0.5 Marks·Write the number
Key ↓
α_(23): _________________
Your answer:
Q43NAT0.5 Marks·Write the number
Key ↓
c_(21): _________________
Your answer:
Q44NAT0.5 Marks·Write the number
Key ↓
c_(22): _________________
Your answer:
Read the passage below, then answer Q45–Q52
Q45NAT0.5 Marks·Write the number
Key ↓
e_(21):_________________
Your answer:
Q46NAT0.5 Marks·Write the number
Key ↓
e_(22):_________________
Your answer:
Q47NAT0.5 Marks·Write the number
Key ↓
e_(23):_________________
Your answer:
Q48NAT0.5 Marks·Write the number
Key ↓
α_(21):_________________
Your answer:
Q49NAT0.5 Marks·Write the number
Key ↓
α_(22):_________________
Your answer:
Q50NAT0.5 Marks·Write the number
Key ↓
α_(23):_________________
Your answer:
Q51NAT0.5 Marks·Write the number
Key ↓
c_(21):_________________
Your answer:
Q52NAT0.5 Marks·Write the number
Key ↓
c_(22):_________________
Your answer:

Official Key

Master Answer Key & Explanations

Official answer keys from IIT Madras BS past papers. Click any question to review.

Reveal Key

Q1A

Q2B

Q3C

Q4D

Q5D

Q6D

Q728

Q8A

Q9C

Q10B

Q11D

Q12B

Q13B

Q14D

Q15A, C, D

Q16B, D

Q17384

Q18-1

Q19j

Q204

Q216

Q223

Q231

Q242

Q255

Q266422528

Q27642252800

Q2812544

Q291254400

Q30131072

Q3113107200

Q3250

Q3325

Q34100

Q35400

Q36800

Q371

Q380

Q392

Q400.24 to 0.25

Q410.09 to 0.1

Q420.66 to 0.68

Q431.5 to 1.6

Q442.5 to 2.6

Q45-0.01 to 0.01

Q46-0.462

Q470.462

Q480.32 to 0.34

Q490.22 to 0.24

Q500.43 to 0.45

Q511.4 to 1.6

Q522.4 to 2.6

Detailed Answer Notes & Working

Q19Answer: j: Case-sensitive: the answer must match exactly.

Questions and answer keys are reproduced from the official IIT Madras BS papers. BTechi is not affiliated with IIT Madras.