Question 196 NAT · 2.0 marks
A published solution is not available for this question yet.
Deep Learning for Computer Vision · End Term · Sep 2024 · AN
Deep Learning for Computer Vision · End Term · Sep 2024 AN
← Course papers · Start practice / exam
Questions and published explanations below are available without starting a test. Some questions may not have a published solution yet.
0 / 26 published solutions
Question 198 MCQ · 2.0 marks
What is the correct order of operations for processing an image through a Vision Transformer
(ViT)?
Image patching → Positional embedding → Linear projection of flattened
patches → Transformer encoder→ Classification head
Image patching → Linear projection of flattened patches → Positional
embedding → Transformer encoder→ Classification head
Positional embedding → Image patching → Linear projection of flattened
patches → Transformer encoder→ Classification head
Linear projection of Images → Image patching → Positional embedding →
Transformer encoder → Classification head
Linear projection of Images → Image patching → Positional embedding →
Transformer encoder→ Transformer decoder→ Classification head
A published solution is not available for this question yet.
Question 199 MCQ · 2.0 marks
Vector Quantized Variational Autoencoder (VQ-VAE) utilizes a discrete latent representation as
opposed to continuous latent spaces used in traditional VAEs. One of the key components of a VQ-
VAE is the codebook, which consists of a set of learnable vectors. What is the primary role of the
codebook in VQ-VAE?
It performs the non-linear transformation of the input data to a higher
dimensional space.
It regularizes the encoder by penalizing complex encodings.
It provides a finite set of vectors which the encoder’s outputs are mapped to,
effectively quantizing the latent space.
It decodes the quantized vectors back into the reconstructed input space.
A published solution is not available for this question yet.
Question 200 MCQ · 2.0 marks
Consider a reverse process in a diffusion model where the goal is to reconstruct the original data
from the noise. If the model correctly reduces the variance of the noise by 0.02 in each reverse
step, and starts with a noise variance of 1.0 at timestep T = 50, how many steps are required to
reduce the noise variance to 0.1?
45
50
40
30
A published solution is not available for this question yet.
Question 201 MCQ · 2.0 marks
3.25
4.5
7.5
3.75
A published solution is not available for this question yet.
Question 202 MCQ · 2.0 marks
Given two normalized embeddings from CLIP, I = [0.2,−0.5, 0.3, 0.4] for an image and T = [−0.1,
0.6,−0.3], for a text description, compute the CLIPScore(I, T).
−69%
0%
−30%
50%
A published solution is not available for this question yet.
Question 203 MCQ · 2.0 marks
A published solution is not available for this question yet.
Question 204 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 205 MCQ · 2.0 marks
True
False
A published solution is not available for this question yet.
Question 206 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 207 MCQ · 2.0 marks
Consider two 10×10 bounding boxes(one on the upper left and one of the lower right) in an
images with an overlapping region of 6 × 6. The Intersection over Union (IoU) between the two
boxes is (choose the closest value):
21%
25%
33%
37%
A published solution is not available for this question yet.
Question 208 MCQ · 2.0 marks
A published solution is not available for this question yet.
Question 209 MCQ · 2.0 marks
0.18, 1.5, 1.5, 0.20,−1.5,−0.015
0.92, 2.5, 1, 2.5, 2.5, 1
0.18,−1.5, 0, 0.20, 0,−0.015
0.91, 1, 0, 0.2, 1, 1.7
A published solution is not available for this question yet.
Question 210 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→ 8→ 5→ 7 → 2
A published solution is not available for this question yet.
Question 211 MCQ · 2.0 marks
Consider an object detection system evaluated on a dataset consisting of 1000 images. The system
makes 1500 predictions across these images, and for each image, there are annotated ground
truth bounding boxes.
The system’s precision-recall curve is calculated, and the precision at different recall levels for one
of the classes is as follows:
Calculate the Average Precision (AP) for this class using the 11-point interpolation method, which
averages the precision values at recall levels {0.0, 0.1, 0.2, ..., 1.0}. The precision at recall 0.0 can be
assumed to be 1.0.
Additionally, the system’s AP values for the other two classes are as follows:
- AP for class 2: 0.78
- AP for class 3: 0.72
Based on these AP values, what is the mean Average Precision (mAP) across all three classes?
0.70
0.69
0.73
0.76
A published solution is not available for this question yet.
Question 212 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 213 MSQ · 2.0 marks
A published solution is not available for this question yet.
Question 214 MSQ · 2.0 marks
Which of the following statements are true? (Select all possible correct options)
Autoencoder can be equivalent to Principal Component Analysis (PCA)
provided we make 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 trans-former
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 215 NAT · 2.0 marks
Based on the above data, answer the given subquestions.
A published solution is not available for this question yet.
Question 216 NAT · 2.0 marks
Based on the above data, answer the given subquestions.
A published solution is not available for this question yet.
Question 217 NAT · 2.0 marks
A published solution is not available for this question yet.
Question 218 NAT · 2.0 marks
What is the size of the feature map after applying two successive convolution operations with
given parameters? Image size = 64 x 64, Kernel size = 6 x 6, Padding = 1 and Stride = 2. (In
calculation, take floor(x) whenever x is non-integer. If the answer is FxF, write F in the blank).
______________________
A published solution is not available for this question yet.
Question 219 NAT · 2.0 marks
A published solution is not available for this question yet.
Question 220 NAT · 2.0 marks
Based on the above data, answer the given subquestions.
A published solution is not available for this question yet.
Question 221 NAT · 2.0 marks
Based on the above data, answer the given subquestions.
A published solution is not available for this question yet.
Question 222 NAT · 2.0 marks
Based on the above data, answer the given subquestions.
A published solution is not available for this question yet.