Question 154 NAT · 3.0 marks
A published solution is not available for this question yet.
Deep Learning for Computer Vision · End Term · May 2025 · FN
Deep Learning for Computer Vision · End Term · May 2025 FN
← Course papers · Start practice / exam
This page contains the reliably extracted subset, not the complete original paper.
Questions and published explanations below are available without starting a test. Some questions may not have a published solution yet.
0 / 53 published solutions
Question 156 MCQ · 2.0 marks
Choose the correct matching:
A published solution is not available for this question yet.
Question 157 MCQ · 2.0 marks
1→ iii, 2→ iv, 3→ i, 4 → ii
1→ iii, 2→ i, 3 → ii, 4 → v
1→ iii, 2→ iv, 3→ v, 4 → ii
1→ iv, 2→ iii, 3→ i, 4 → ii
A published solution is not available for this question yet.
Question 158 MCQ · 2.0 marks
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
6→ 1→ 4→ 5 → 2
3→ 1→ 6→ 4 → 2
3→ 5→ 1→ 4 → 2
6→ 3→ 5→ 7 → 2
A published solution is not available for this question yet.
Question 159 MCQ · 2.0 marks
Only statement P is true
Only statement Q is true
Both statements are true
None of these statements is true
A published solution is not available for this question yet.
Question 160 MCQ · 2.0 marks
1→ vi, 2→ iii, 3 →v, 4 → i
1→ i, 2→ iv, 3 → iii, 4→ ii
1→ i, 2→ v, 3 → iii, 4→ iv
1→ iv, 2→ iii, 3→ ii, 4 → i
A published solution is not available for this question yet.
Question 161 MCQ · 2.0 marks
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.
5, 2, 1, 3, 4
5, 1, 3, 2, 4
1, 3, 2, 4, 5
1, 5, 3, 2, 4
A published solution is not available for this question yet.
Question 162 MCQ · 2.0 marks
Sigmoid of alignment scores
ReLU of alignment scores
Softmax of alignment scores
Linear projections of alignment scores
A published solution is not available for this question yet.
Question 163 MCQ · 2.0 marks
Which one of the following statements is true?
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 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 164 MCQ · 2.0 marks
A published solution is not available for this question yet.
Question 165 MCQ · 2.0 marks
Which one of the following statements regarding hyperparameter tuning is false?
Validation set is the best choice for tuning hyperparameters
Picking hyperparameters that perform the best on the training set leads to
overfitting
Tuning hyperparameters on the test set is an acceptable approach to find the
most powerful model for generalization performance
Test set performance, with hyperparameters tuned on the validation set,
would be a realistic measure of how the model will generalize to new data.
A published solution is not available for this question yet.
Question 166 MCQ · 2.0 marks
A published solution is not available for this question yet.
Question 167 MCQ · 2.0 marks
1→ iii, 2→ iv, 3→ ii, 4 → i
1→ i, 2→ iv, 3 → iii, 4→ ii
1→ iv, 2→ iii, 3→ ii, 4 → i
1→ iii, 2→ i, 3 → ii, 4 →v
A published solution is not available for this question yet.
Question 168 MCQ · 2.0 marks
1→ iv, 2→ v, 3→ i, 4 → ii
1→ iii, 2→ i, 3 → v, 4→ ii
1→ iv, 2→ iii, 3→ ii, 4 → i
1→ iii, 2→ i, 3 → ii, 4→ v
A published solution is not available for this question yet.
Question 169 MCQ · 2.0 marks
What makes the Segment Anything Model (SAM) particularly advantageous for image annotation
tasks compared to conventional segmentation approaches?
It has perfect segmentation accuracy
It has minimal hardware requirements for operation
It can generalize to segment objects it wasn’t specifically trained on
It automatically identifies and labels all objects in an image without user
prompts
A published solution is not available for this question yet.
Question 170 MCQ · 2.0 marks
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?
Both statements are correct, and Statement 2 correctly explains Statement 1.
Both statements are correct, but Statement 2 does not correctly explain
Statement 1.
Statement 1 is correct, but Statement 2 is incorrect.
Statement 1 is incorrect, but Statement 2 is correct.
Both statements are incorrect.
A published solution is not available for this question yet.
Question 171 MCQ · 2.0 marks
Why does DETR typically exhibit poor performance in detecting small objects compared to larger
ones?
The CNN backbone used in DETR has a fixed receptive field that’s too large for
small objects
The global self-attention mechanism in DETR tends to dilute the signal from
small objects across all image locations
DETR’s loss function actively discards all detections smaller than 50x50 pixels
The object queries in DETR are programmed to ignore any object smaller than
10
DETR’s encoder-decoder architecture was specifically designed to only detect
large objects
A published solution is not available for this question yet.
Question 172 MSQ · 2.0 marks
Which of the following statements are false? (Select all that apply)
Generative adversarial networks (GANs) generate sharper images compared
to Variational AutoEncoders (VAE)
GAN is an example of an implicit density estimation model
Fully connected layers in mapping network of Style-GAN do not change the
dimension of its input
The generator and discriminator are always trained together in a GAN
A published solution is not available for this question yet.
Question 173 MSQ · 2.0 marks
Which of the following statements are true? (Select all possible correct options)
Autoencoder are equivalent to Principal Component Analysis (PCA) provided
we don’t use of non-linear activation functions
When using global attention on temporal data, alignment weights are learnt
for encoder hidden representations for all time steps
Positional encoding is an important component of the transformer
architecture as it conveys information about order in a given sequence
It is not possible to generate different captions for the same image that have
similar meaning but different tone/style
Autoencoders can not be used for data compression as its input and output
dimensions are different
A published solution is not available for this question yet.
Question 174 MSQ · 2.0 marks
Which of the following statements about CLIP are TRUE? (Select ALL that apply)
CLIP uses a contrastive loss function to align text and image embeddings.
CLIP requires image labels for training.
CLIP is trained to maximize cosine similarity between embeddings of matching
text-image pairs.
CLIP model is trained with pretext tasks such as rotation prediction and
inpainting to learn effective feature representations.
To use the CLIP model for image classification, it is imperative to finetune it on
downstream datasets.
A published solution is not available for this question yet.
Question 175 MSQ · 2.0 marks
Which one of the following statements is true:
Weight 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.
L1 norm tends to create more sparse weights than L2 norm.
During 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.
A single McCulloch-Pitts neuron is capable of modeling AND, OR, XOR, NOR,
and NAND functions.
A published solution is not available for this question yet.
Question 176 MSQ · 2.0 marks
Which of the following are examples of a high-pass filter?
A published solution is not available for this question yet.
Question 177 MSQ · 2.0 marks
Which of the following statements are true? (Select all that apply)
A published solution is not available for this question yet.
Question 178 MSQ · 2.0 marks
Which of the following techniques help control the exploding or vanishing gradient problem in
recurrent neural networks?
Gradient clipping
Use ReLU activation funtion to control exploding gradient and sigmoid
activation to control vanishing gradients
Use Long Short-Term Memory (LSTM)
Use data augmentation methods (for example, reversing the input sequence)
A published solution is not available for this question yet.
Question 179 NAT · 2.0 marks
A published solution is not available for this question yet.
Question 180 NAT · 2.0 marks
A published solution is not available for this question yet.
Question 181 NAT · 2.0 marks
A published solution is not available for this question yet.
Question 182 NAT · 2.0 marks
A published solution is not available for this question yet.
Question 183 NAT · 2.0 marks
A published solution is not available for this question yet.
Question 184 NAT · 2.0 marks
A published solution is not available for this question yet.
Question 185 NAT · 1.0 marks
A published solution is not available for this question yet.
Question 186 NAT · 1.0 marks
A published solution is not available for this question yet.
Question 187 NAT · 1.0 marks
Based on the above data, answer the given subquestions.
Element 1: _______________
A published solution is not available for this question yet.
Question 188 NAT · 1.0 marks
Based on the above data, answer the given subquestions.
Element 2: _______________
A published solution is not available for this question yet.
Question 189 NAT · 1.0 marks
Based on the above data, answer the given subquestions.
Element 3: _______________
A published solution is not available for this question yet.
Question 190 NAT · 1.0 marks
Based on the above data, answer the given subquestions.
Element 4: _______________
A published solution is not available for this question yet.
Question 191 NAT · 1.0 marks
Based on the above data, answer the given subquestions.
Sigmoid _______________
A published solution is not available for this question yet.
Question 192 NAT · 1.0 marks
Based on the above data, answer the given subquestions.
Linear _______________
A published solution is not available for this question yet.
Question 193 NAT · 1.0 marks
Based on the above data, answer the given subquestions.
Indicator Function _______________
A published solution is not available for this question yet.
Question 194 NAT · 1.0 marks
Based on the above data, answer the given subquestions.
Softplus _______________
A published solution is not available for this question yet.
Question 195 NAT · 1.0 marks
Based on the above data, answer the given subquestions.
ReLu _______________
A published solution is not available for this question yet.
Question 196 NAT · 1.0 marks
Based on the above data, answer the given subquestions.
Leaky-ReLu _______________
A published solution is not available for this question yet.
Question 197 NAT · 0.55 marks
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.
A published solution is not available for this question yet.
Question 198 NAT · 0.55 marks
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.
A published solution is not available for this question yet.
Question 199 NAT · 0.55 marks
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.
A published solution is not available for this question yet.
Question 200 NAT · 0.55 marks
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.
A published solution is not available for this question yet.
Question 201 NAT · 0.55 marks
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.
A published solution is not available for this question yet.
Question 202 NAT · 0.55 marks
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.
A published solution is not available for this question yet.
Question 203 NAT · 0.54 marks
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.
A published solution is not available for this question yet.
Question 204 NAT · 0.54 marks
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.
A published solution is not available for this question yet.
Question 205 NAT · 0.54 marks
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.
A published solution is not available for this question yet.
Question 206 NAT · 0.54 marks
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.
A published solution is not available for this question yet.
Question 207 NAT · 0.54 marks
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.
A published solution is not available for this question yet.