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

DL for CV · End Term · 31 Aug 2025 (Forenoon)

52 questions · 76.00000000000001 marks · 90 min

Answer key Take as mock

Indian Institute of Technology Madras

BS Degree Programme · Examination & Study Paper

Deep Learning for Computer Vision

End Term · 31 Aug 2025 (Forenoon)

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
Key ↓
Choose the correct matching:
1. A
2. B
3. C
4. D
Q2MCQ2 Marks·Choose one option
Asked 3 times Key ↓
1. A1→ iii, 2→ iv, 3→ i, 4 → ii
2. B1→ iii, 2→ i, 3 → ii, 4 → v
3. C1→ iii, 2→ iv, 3→ v, 4 → ii
4. D1→ iv, 2→ iii, 3→ i, 4 → ii
Q3MCQ2 Marks·Choose one option
Asked 2 times Key ↓
Identify the correct sequence of steps in a Canny edge detection pipeline. Steps are listed below: 1. Compute gradient magnitude and direction 2. Connect individual components 3. Smoothen the image 4. Threshold into strong, weak, or no edge 5. Gaussian Filter and Hysteresis 6. Non-maximum suppression 7. Apply derivative to get edges
1. A6→ 1→ 4→ 5 → 2
2. B3→ 1→ 6→ 4 → 2
3. C3→ 5→ 1→ 4 → 2
4. D6→ 3→ 5→ 7 → 2
Q4MCQ2 Marks·Choose one option
Asked 2 times Key ↓
1. AOnly statement P is true
2. BOnly statement Q is true
3. CBoth statements are true
4. DNone of these statements is true
Q5MCQ2 Marks·Choose one option
Asked 2 times Key ↓
1. A1→ vi, 2→ iii, 3 →v, 4 → i
2. B1→ i, 2→ iv, 3 → iii, 4→ ii
3. C1→ i, 2→ v, 3 → iii, 4→ iv
4. D1→ iv, 2→ iii, 3→ ii, 4 → i
Q6MCQ2 Marks·Choose one option
Asked 2 times Key ↓
Which of the following is the correct sequence of steps of the SIFT algorithm? 1. Using the Taylor series expansion of the scale-space function, lo-calize the key points. 2. Estimate the orientation of keypoints using the local image gra-dients. 3. Find the edge points using the eigenvalues of the Hessian and reject these points. 4. Find a raw SIFT descriptor vector using the gradient orientations of the neighborhood around the key points. 5. Detect extreme points in scale space using an approximation of the Laplacian of Gaussian.
1. A5, 2, 1, 3, 4
2. B5, 1, 3, 2, 4
3. C1, 3, 2, 4, 5
4. D1, 5, 3, 2, 4
Q7MCQ2 Marks·Choose one option
Key ↓
1. ASigmoid of alignment scores
2. BReLU of alignment scores
3. CSoftmax of alignment scores
4. DLinear projections of alignment scores
Q8MCQ2 Marks·Choose one option
Asked 4 times Key ↓
Which one of the following statements is true?
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 are the recurrent connections that help them to deal with variable input length.
4. DNone 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 ↓
Which one of the following statements regarding hyperparameter tuning is false?
1. AValidation set is the best choice for tuning hyperparameters
2. BPicking hyperparameters that perform the best on the training set leads to overfitting
3. CTuning hyperparameters on the test set is an acceptable approach to find the most powerful model for generalization performance
4. DTest set performance, with hyperparameters tuned on the validation set, would be a realistic measure of how the model will generalize to new data.
Q11MCQ2 Marks·Choose one option
Asked 3 times Key ↓
1. A
2. B
3. C
4. D
Q12MCQ2 Marks·Choose one option
Asked 2 times Key ↓
1. A1→ iii, 2→ iv, 3→ ii, 4 → i
2. B1→ i, 2→ iv, 3 → iii, 4→ ii
3. C1→ iv, 2→ iii, 3→ ii, 4 → i
4. D1→ iii, 2→ i, 3 → ii, 4 →v
Q13MCQ2 Marks·Choose one option
Asked 2 times Key ↓
1. A1→ iv, 2→ v, 3→ i, 4 → ii
2. B1→ iii, 2→ i, 3 → v, 4→ ii
3. C1→ iv, 2→ iii, 3→ ii, 4 → i
4. D1→ iii, 2→ i, 3 → ii, 4→ v
Q14MCQ2 Marks·Choose one option
Asked 2 times Key ↓
What makes the Segment Anything Model (SAM) particularly advantageous for image annotation tasks compared to conventional segmentation approaches?
1. AIt has perfect segmentation accuracy
2. BIt has minimal hardware requirements for operation
3. CIt can generalize to segment objects it wasn’t specifically trained on
4. DIt automatically identifies and labels all objects in an image without user prompts
Q15MCQ2 Marks·Choose one option
Key ↓
Statement 1: The Segment Anything Model (SAM) demonstrates zero-shot generalization capabilities across various downstream tasks. Statement 2: SAM’s training involves a largescale, diverse mask dataset using a prompt-based segmentation approach. Which one of the following options is most appropriate?
1. ABoth statements are correct, and Statement 2 correctly explains Statement 1.
2. BBoth statements are correct, but Statement 2 does not correctly explain Statement 1.
3. CStatement 1 is correct, but Statement 2 is incorrect.
4. DStatement 1 is incorrect, but Statement 2 is correct.
5. EBoth statements are incorrect.
Q16MCQ2 Marks·Choose one option
Asked 2 times Key ↓
Why does DETR typically exhibit poor performance in detecting small objects compared to larger ones?
1. AThe CNN backbone used in DETR has a fixed receptive field that’s too large for small objects
2. BThe global self-attention mechanism in DETR tends to dilute the signal from small objects across all image locations
3. CDETR’s loss function actively discards all detections smaller than 50x50 pixels
4. DThe object queries in DETR are programmed to ignore any object smaller than 10
5. EDETR’s encoder-decoder architecture was specifically designed to only detect large objects
Q17MSQ2 Marks·Choose all correct options
Asked 2 times Key ↓
Which of the following statements are false? (Select all that apply)
1. AGenerative adversarial networks (GANs) generate sharper images compared to Variational AutoEncoders (VAE)
2. BGAN is an example of an implicit density estimation model
3. CFully connected layers in mapping network of Style-GAN do not change the dimension of its input
4. DThe generator and discriminator are always trained together in a GAN
Q18MSQ2 Marks·Choose all correct options
Asked 2 times Key ↓
Which of the following statements are true? (Select all possible correct options)
1. AAutoencoder are equivalent to Principal Component Analysis (PCA) provided we don’t use of non-linear activation functions
2. BWhen using global attention on temporal data, alignment weights are learnt for encoder hidden representations for all time steps
3. CPositional encoding is an important component of the transformer architecture as it conveys information about order in a given sequence
4. DIt is not possible to generate different captions for the same image that have similar meaning but different tone/style
5. EAutoencoders can not be used for data compression as its input and output dimensions are different
Q19MSQ2 Marks·Choose all correct options
Asked 2 times Key ↓
Which of the following statements about CLIP are TRUE? (Select ALL that apply)
1. ACLIP uses a contrastive loss function to align text and image embeddings.
2. BCLIP requires image labels for training.
3. CCLIP is trained to maximize cosine similarity between embeddings of matching text-image pairs.
4. DCLIP model is trained with pretext tasks such as rotation prediction and inpainting to learn effective feature representations.
5. ETo use the CLIP model for image classification, it is imperative to finetune it on downstream datasets.
Q20MSQ2 Marks·Choose all correct options
Asked 2 times Key ↓
Which one of the following statements is true:
1. AWeight change criterion is a method of ‘early stopping’ that checks whether or not the error is dropping over epochs to decide whether to continue training or stop.
2. BL1 norm tends to create more sparse weights than L2 norm.
3. CDuring the training phase, for each iteration, Dropout ignores a random fraction, p, of nodes, and accounts for it in the test phase by scaling down the activations by a factor of p.
4. DA single McCulloch-Pitts neuron is capable of modeling AND, OR, XOR, NOR, and NAND functions.
Q21MSQ2 Marks·Choose all correct options
Asked 2 times Key ↓
Which of the following are examples of a high-pass filter?
1. A
2. B
3. C
4. D
Q22MSQ2 Marks·Choose all correct options
Key ↓
Which of the following statements are true? (Select all that apply)
1. A
2. B
3. C
4. D
Q23MSQ2 Marks·Choose all correct options
Asked 3 times Key ↓
Which of the following techniques help control the exploding or vanishing gradient problem in recurrent neural networks?
1. AGradient clipping
2. BUse ReLU activation funtion to control exploding gradient and sigmoid activation to control vanishing gradients
3. CUse Long Short-Term Memory (LSTM)
4. DUse data augmentation methods (for example, reversing the input sequence)
Q24NAT2 Marks·Write the number
Asked 3 times Key ↓
Your answer:
Q25NAT2 Marks·Write the number
Asked 2 times Key ↓
Your answer:
Q26NAT2 Marks·Write the number
Asked 3 times Key ↓
Your answer:
Q27NAT2 Marks·Write the number
Asked 2 times Key ↓
Your answer:
Q28NAT2 Marks·Write the number
Asked 2 times Key ↓
Your answer:
Q29NAT2 Marks·Write the number
Asked 3 times Key ↓
Your answer:
Read the passage below, then answer Q30–Q31
Q30NAT1 Mark·Write the number
Asked 4 times Key ↓
Your answer:
Q31NAT1 Mark·Write the number
Asked 4 times Key ↓
Your answer:
Read the passage below, then answer Q32–Q35
Based on the above data, answer the given subquestions.
Q32NAT1 Mark·Write the number
Key ↓
Element 1: _______________
Your answer:
Q33NAT1 Mark·Write the number
Key ↓
Element 2: _______________
Your answer:
Q34NAT1 Mark·Write the number
Key ↓
Element 3: _______________
Your answer:
Q35NAT1 Mark·Write the number
Key ↓
Element 4: _______________
Your answer:
Read the passage below, then answer Q36–Q41
Based on the above data, answer the given subquestions.
Q36NAT1 Mark·Write the number
Asked 13 times Key ↓
Sigmoid _______________
Your answer:
Q37NAT1 Mark·Write the number
Asked 13 times Key ↓
Linear _______________
Your answer:
Q38NAT1 Mark·Write the number
Asked 13 times Key ↓
Indicator Function _______________
Your answer:
Q39NAT1 Mark·Write the number
Asked 13 times Key ↓
Softplus _______________
Your answer:
Q40NAT1 Mark·Write the number
Asked 13 times Key ↓
ReLu _______________
Your answer:
Q41NAT1 Mark·Write the number
Asked 13 times Key ↓
Leaky-ReLu _______________
Your answer:
Read the passage below, then answer Q42–Q52
Consider the BLIP model architecture with an input (image-text pair) as shown below: For each of the given entities, enter the appropriate number from the figure that corresponds to it:
Based on the above data, answer the given subquestions.
Q42NAT0.55 Marks·Write the number
Asked 22 times Key ↓
Your answer:
Q43NAT0.55 Marks·Write the number
Asked 22 times Key ↓
Your answer:
Q44NAT0.55 Marks·Write the number
Asked 22 times Key ↓
Your answer:
Q45NAT0.55 Marks·Write the number
Asked 22 times Key ↓
Your answer:
Q46NAT0.55 Marks·Write the number
Asked 22 times Key ↓
Your answer:
Q47NAT0.55 Marks·Write the number
Asked 22 times Key ↓
Your answer:
Q48NAT0.54 Marks·Write the number
Asked 22 times Key ↓
Your answer:
Q49NAT0.54 Marks·Write the number
Asked 22 times Key ↓
Your answer:
Q50NAT0.54 Marks·Write the number
Asked 22 times Key ↓
Your answer:
Q51NAT0.54 Marks·Write the number
Asked 22 times Key ↓
Your answer:
Q52NAT0.54 Marks·Write the number
Asked 22 times Key ↓
Your answer:

Official Key

Master Answer Key & Explanations

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

Reveal Key

Q1D

Q2C

Q3B

Q4A

Q5D

Q6B

Q7C

Q8D

Q9D

Q10C

Q11A

Q12D

Q13A

Q14C

Q15A

Q16B

Q17C, D

Q18A, B, C

Q19A, C

Q20B, C

Q21A, B, C, D

Q22B, C

Q23A, C, D

Q240

Q2530

Q26-0.215 to -0.205

Q2745

Q283.75

Q29100

Q30-2

Q315

Q320.54

Q330.25

Q340.19

Q350.58

Q360.95

Q373

Q381

Q393.05

Q403

Q413

Q421

Q435

Q4411

Q457

Q468

Q474

Q4810

Q499

Q503

Q512

Q526

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