MauryaHub PYQ Practice

Deep Learning for Computer Vision · End Term · May 2025 · AN

Deep Learning for Computer Vision · End Term · May 2025 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 / 49 published solutions

Question 83 MCQ · 2.0 marks

Why does DETR typically exhibit poor performance in detecting small objects compared to larger ones? Choose the best answer in your opinion.
A.
The CNN backbone used in DETR has a fixed receptive field that’s too large for small objects.
B.
The global self-attention mechanism in DETR tends to dilute the signal from small objects across all image locations.
C.
DETR’s loss function actively discards all detections smaller than 50 × 50 pixels.
D.
The object queries in DETR are programmed to ignore any object smaller than 10% of the image size.
E.
DETR’s encoder-decoder architecture was specifically designed to only detect objects larger than a cat.

A published solution is not available for this question yet.

Report a correction for Q83

Question 84 MCQ · 2.0 marks

Consider the following Pytorch code: 1. x = torch.tensor([[-3.,2.,3.],[4.,-5.,7.],[20.,3.,2.]]) 2. print(torch.mean(x,dim=0,keepdim=True)) The output of the code is:
A.
tensor([ 7., 0., 4.])
B.
tensor([[ -7., 10., -4.]])
C.
tensor([[ -7.],[7.],[4.]])
D.
tensor([ -7., 7., 3.])
E.
tensor([[7., 0., 4.]])
F.
tensor([[ 0.],[7.],[4.]])

A published solution is not available for this question yet.

Report a correction for Q84

Question 85 MCQ · 2.0 marks

Which one of the following statements is false?
A.
Linear contrast stretching is a point operation.
B.
Moving average is an example of a local operation.
C.
Convolution in the spatial domain cannot be obtained through addition in the frequency domain.
D.
All of these.

A published solution is not available for this question yet.

Report a correction for Q85

Question 86 MCQ · 2.0 marks

What is the correct order of operations for processing an image through a Vision Transformer (ViT)?
A.
Image patching → Positional embedding → Linear projection of flattened patches → Transformer encoder→ Classification head
B.
Image patching → Linear projection of flattened patches → Positional embedding → Transformer encoder→ Classification head
C.
Positional embedding → Image patching → Linear projection of flattened patches → Transformer encoder→ Classification head
D.
Linear projection of Images → Image patching → Positional embedding → Transformer encoder → Classification head
E.
Linear projection of Images → Image patching → Positional embedding → Transformer encoder → Transformer decoder→ Classification head

A published solution is not available for this question yet.

Report a correction for Q86

Question 87 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?
A.
It performs the non-linear transformation of the input data to a higher dimensional space.
B.
It regularizes the encoder by penalizing complex encodings.
C.
It provides a finite set of vectors which the encoder’s outputs are mapped to, effectively quantizing the latent space.
D.
It decodes the quantized vectors back into the reconstructed input space.

A published solution is not available for this question yet.

Report a correction for Q87

Question 88 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, 0.7] for a text description, compute the CLIPScore(I,T).
A.
− 69%
B.
0%
C.
69%
D.
50%

A published solution is not available for this question yet.

Report a correction for Q88

Question 89 MCQ · 2.0 marks

Which one of the following statements regarding hyperparameter tuning is false?
A.
Validation set is the best choice for tuning hyperparameters
B.
Picking hyperparameters that perform the best on the training set leads to overfitting
C.
Tuning hyperparameters on the test set is an acceptable approach to find the most powerful model for generalization performance
D.
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.

Report a correction for Q89

Question 90 MCQ · 2.0 marks

Which one of the following statements is false? (Pick the most appropriate one.)
A.
Attention mechanisms can be applied to the bidirectional RNN model
B.
An image captioning network can be trained end-to-end even though we are using 2 different modalities to train the network
C.
One of the key components in the vanilla transformer is the recurrent connection that help them to deal with variable input length.
D.
All of these.

A published solution is not available for this question yet.

Report a correction for Q90

Question 91 MCQ · 2.0 marks

You are designing an edge detection pipeline for noisy grayscale images. For each of the following goals, choose the most appropriate filter or method: 1. Smooth out noise before any edge detection step 2. Detect edges by finding zero-crossings in the second derivative 3. Highlight regions with a strong intensity gradient 4. Perform basic edge detection with a simple directional gradient filter
A.
1 → Gaussian filter, 2 → Laplacian of Gaussian, 3 → First derivative of Gaussian, 4 → Sobel operator
B.
1 → Sobel operator, 2 → Gaussian filter, 3 → Laplacian of Gaussian, 4 → First derivative of Gaussian
C.
1 → First derivative of Gaussian, 2 → Sobel operator, 3 → Gaussian filter, 4 → Laplacian of Gaussian
D.
1→Laplacian of Gaussian, 2→First derivative of Gaussian, 3→Sobel operator, 4→Gaussian filter

A published solution is not available for this question yet.

Report a correction for Q91

Question 92 MCQ · 2.0 marks

Source diagram or notation
A.Source diagram or notation
B.Source diagram or notation
C.Source diagram or notation
D.Source diagram or notation

A published solution is not available for this question yet.

Report a correction for Q92

Question 93 MCQ · 2.0 marks

Source diagram or notation
A.
1→ iii, 2→ iv, 3→ ii, 4 → i
B.
1→ i, 2→ iv, 3 → iii, 4→ ii
C.
1→ iv, 2→ iii, 3→ ii, 4 → i
D.
1→ iii, 2→ i, 3 → ii, 4 →v

A published solution is not available for this question yet.

Report a correction for Q93

Question 94 MCQ · 2.0 marks

Source diagram or notation
A.
1→ iv, 2→ v, 3→ i, 4 → ii
B.
1→ iii, 2→ i, 3 → v, 4→ ii
C.
1→ iv, 2→ iii, 3→ ii, 4 → i
D.
1→ iii, 2→ i, 3 → ii, 4→ v

A published solution is not available for this question yet.

Report a correction for Q94

Question 95 MCQ · 2.0 marks

In which one of the following applications would you use a many- to-one RNN architecture? Choose the most appropriate answer.
A.
Input is a review of a movie and output is the sentiment of the given review
B.
Input is an image and output is the textual description of the given image
C.
Input is an image and output is the class to which the given image belongs
D.
Input is a sentence in English language and output is the same sentence translated to Hindi language

A published solution is not available for this question yet.

Report a correction for Q95

Question 96 MCQ · 2.0 marks

Why might Segment Anything (SAM) be particularly useful in data annotation tasks compared to traditional segmentation models?
A.
It produces perfect segmentation masks.
B.
It can adapt to segment any object, even those not seen during training
C.
It requires less computational resources
D.
It automatically labels all objects in an image without user input

A published solution is not available for this question yet.

Report a correction for Q96

Question 97 MSQ · 2.0 marks

Which of the following statements are true? (Select all possible correct options)
A.
Variational AutoEncoders (VAE) generate sharper images compared to Generative adversarial networks (GANs)
B.
GAN is an example of an implicit density estimation model
C.
Fully connected layers in mapping network of Style-GAN change the dimension of its input
D.
In a GAN, the generator and discriminator are trained in an alternating fashion, each using the other’s output to improve.

A published solution is not available for this question yet.

Report a correction for Q97

Question 98 MSQ · 2.0 marks

Classifier-free guidance is a technique used in diffusion models to improve sample quality without the explicit use of a classifier. This technique involves modifying the sampling process based on a control parameter. If the control parameter, denoted as γ, is set to zero, what effect does this have on the generation process?
A.
It fails to generate realistic samples
B.
It removes all guidance, effectively making the process equivalent to the unconditional generation.
C.
It maximizes the influence of the classifier, leading to highly detailed generations.
D.
It can lead to more diverse samples compared to higher values of γ, as the generation process is less constrained by the conditional information.

A published solution is not available for this question yet.

Report a correction for Q98

Question 99 MSQ · 2.0 marks

Which of the following statements are true? (Select all possible correct options)
A.
Autoencoder are equivalent to Principal Component Analysis (PCA) provided we don’t use of non-linear activation functions
B.
When using global attention on temporal data, alignment weights are learnt for encoder hidden representations for all time steps
C.
Positional encoding is an important component of the trans- former architecture as it conveys information about order in a given sequence
D.
It is not possible to generate different captions for the same image that have similar meaning but different tone/style
E.
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.

Report a correction for Q99

Question 100 MSQ · 2.0 marks

Which of the following statements about CLIP are TRUE? (Select ALL that apply)
A.
CLIP uses a cross-entropy loss function to align text and image embeddings.
B.
CLIP requires image labels for training.
C.
CLIP is trained to maximize cosine similarity between embeddings of matching text-image pairs.
D.
CLIP model is trained with pretext tasks such as rotation prediction and inpainting to learn effective feature representations.
E.
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.

Report a correction for Q100

Question 101 MSQ · 2.0 marks

Which one of the following statements is true:
A.
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.
B.
L1 norm tends to create more sparse weights than L2 norm.
C.
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.
D.
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.

Report a correction for Q101

Question 102 MSQ · 2.0 marks

Which of the following are examples of a high-pass filter?
A.Source diagram or notation
B.Source diagram or notation
C.Source diagram or notation
D.Source diagram or notation

A published solution is not available for this question yet.

Report a correction for Q102

Question 103 NAT · 2.0 marks

Source diagram or notation

A published solution is not available for this question yet.

Report a correction for Q103

Question 104 NAT · 2.0 marks

Source diagram or notation

A published solution is not available for this question yet.

Report a correction for Q104

Question 105 NAT · 2.0 marks

Source diagram or notation

A published solution is not available for this question yet.

Report a correction for Q105

Question 106 NAT · 2.0 marks

Source diagram or notation

A published solution is not available for this question yet.

Report a correction for Q106

Question 107 NAT · 2.0 marks

Source diagram or notation

A published solution is not available for this question yet.

Report a correction for Q107

Question 108 NAT · 2.0 marks

What is the size of the feature map after applying two successive convolution operations with given parameters? Image size = 72×72, Kernel size = 5×5, Padding = 2 and Stride = 3. (In calculation, take floor(x) whenever x is non-integer.If the answer is N × N, write just one value N in the blank) __________________ .

A published solution is not available for this question yet.

Report a correction for Q108

Question 109 NAT · 1.0 marks

Source diagram or notation
Based on the above data, answer the given subquestions.
Source diagram or notation

A published solution is not available for this question yet.

Report a correction for Q109

Question 110 NAT · 1.0 marks

Source diagram or notation
Based on the above data, answer the given subquestions.
Source diagram or notation

A published solution is not available for this question yet.

Report a correction for Q110

Question 111 NAT · 2.0 marks

Source diagram or notation
Based on the above data, answer the given subquestions.
Element 1:___________

A published solution is not available for this question yet.

Report a correction for Q111

Question 112 NAT · 2.0 marks

Source diagram or notation
Based on the above data, answer the given subquestions.
Element 2:___________

A published solution is not available for this question yet.

Report a correction for Q112

Question 113 NAT · 1.0 marks

Source diagram or notation
Based on the above data, answer the given subquestions.
Element 3:___________

A published solution is not available for this question yet.

Report a correction for Q113

Question 114 NAT · 1.0 marks

Source diagram or notation
Based on the above data, answer the given subquestions.
Element 4:___________

A published solution is not available for this question yet.

Report a correction for Q114

Question 115 NAT · 1.0 marks

Consider the BLIP model architecture with an input (image-text pair) as shown below:
Source diagram or notation
For each of the entities given, enter the appropriate number from the figure that corresponds to it: Based on the above data, answer the given subquestions.
Self-Attention _______________

A published solution is not available for this question yet.

Report a correction for Q115

Question 116 NAT · 0.5 marks

Consider the BLIP model architecture with an input (image-text pair) as shown below:
Source diagram or notation
For each of the entities given, enter the appropriate number from the figure that corresponds to it: Based on the above data, answer the given subquestions.
BERT Text Encoder Bi Self Attention:__________________

A published solution is not available for this question yet.

Report a correction for Q116

Question 117 NAT · 0.5 marks

Consider the BLIP model architecture with an input (image-text pair) as shown below:
Source diagram or notation
For each of the entities given, enter the appropriate number from the figure that corresponds to it: Based on the above data, answer the given subquestions.
Image-Text Matching Loss (LITM ):__________________

A published solution is not available for this question yet.

Report a correction for Q117

Question 118 NAT · 0.5 marks

Consider the BLIP model architecture with an input (image-text pair) as shown below:
Source diagram or notation
For each of the entities given, enter the appropriate number from the figure that corresponds to it: Based on the above data, answer the given subquestions.
Image Grounded Text Encoder Bi Self Attention: ___________________

A published solution is not available for this question yet.

Report a correction for Q118

Question 119 NAT · 0.5 marks

Consider the BLIP model architecture with an input (image-text pair) as shown below:
Source diagram or notation
For each of the entities given, enter the appropriate number from the figure that corresponds to it: Based on the above data, answer the given subquestions.
Source diagram or notation

A published solution is not available for this question yet.

Report a correction for Q119

Question 120 NAT · 0.5 marks

Consider the BLIP model architecture with an input (image-text pair) as shown below:
Source diagram or notation
For each of the entities given, enter the appropriate number from the figure that corresponds to it: Based on the above data, answer the given subquestions.
Image Grounded Text Encoder Cross Attention: _________________

A published solution is not available for this question yet.

Report a correction for Q120

Question 121 NAT · 0.5 marks

Consider the BLIP model architecture with an input (image-text pair) as shown below:
Source diagram or notation
For each of the entities given, enter the appropriate number from the figure that corresponds to it: Based on the above data, answer the given subquestions.
Image-Text Contrastive Loss (LITC): ____________

A published solution is not available for this question yet.

Report a correction for Q121

Question 122 NAT · 0.5 marks

Consider the BLIP model architecture with an input (image-text pair) as shown below:
Source diagram or notation
For each of the entities given, enter the appropriate number from the figure that corresponds to it: Based on the above data, answer the given subquestions.
Source diagram or notation

A published solution is not available for this question yet.

Report a correction for Q122

Question 123 NAT · 0.5 marks

Consider the BLIP model architecture with an input (image-text pair) as shown below:
Source diagram or notation
For each of the entities given, enter the appropriate number from the figure that corresponds to it: Based on the above data, answer the given subquestions.
Causal Self Attention: _____________

A published solution is not available for this question yet.

Report a correction for Q123

Question 124 NAT · 0.5 marks

Consider the BLIP model architecture with an input (image-text pair) as shown below:
Source diagram or notation
For each of the entities given, enter the appropriate number from the figure that corresponds to it: Based on the above data, answer the given subquestions.
Source diagram or notation

A published solution is not available for this question yet.

Report a correction for Q124

Question 125 NAT · 0.5 marks

Consider the BLIP model architecture with an input (image-text pair) as shown below:
Source diagram or notation
For each of the entities given, enter the appropriate number from the figure that corresponds to it: Based on the above data, answer the given subquestions.
Image Grounded Text Decoder Cross Attention: _____________

A published solution is not available for this question yet.

Report a correction for Q125

Question 126 NAT · 1.0 marks

Source diagram or notation
Based on the above data, answer the given subquestions.
Sigmoid ______________

A published solution is not available for this question yet.

Report a correction for Q126

Question 127 NAT · 1.0 marks

Source diagram or notation
Based on the above data, answer the given subquestions.
Linear ______________

A published solution is not available for this question yet.

Report a correction for Q127

Question 128 NAT · 1.0 marks

Source diagram or notation
Based on the above data, answer the given subquestions.
Indicator Function ______________

A published solution is not available for this question yet.

Report a correction for Q128

Question 129 NAT · 1.0 marks

Source diagram or notation
Based on the above data, answer the given subquestions.
Softplus _____________

A published solution is not available for this question yet.

Report a correction for Q129

Question 130 NAT · 1.0 marks

Source diagram or notation
Based on the above data, answer the given subquestions.
ReLU _______________

A published solution is not available for this question yet.

Report a correction for Q130

Question 131 NAT · 1.0 marks

Source diagram or notation
Based on the above data, answer the given subquestions.
Leaky-ReLU _____________

A published solution is not available for this question yet.

Report a correction for Q131