Deep Learning for Computer Vision End Term: 31 August 2025, Set QIA3 (May 2025 term)

Why does DETR typically exhibit poor performance in detecting small objects compared to larger ones? Choose the best answer in your opinion.

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:

Which one of the following statements is false?

What is the correct order of operations for processing an image through a Vision Transformer (ViT)?

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?

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).

Which one of the following statements regarding hyperparameter tuning is false?

Which one of the following statements is false? (Pick the most appropriate one.)

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

In which one of the following applications would you use a many- to-one RNN architecture? Choose the most appropriate answer.

Why might Segment Anything (SAM) be particularly useful in data annotation tasks compared to traditional segmentation models?

Which of the following statements are true? (Select all possible correct options)

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?

Which of the following statements are true? (Select all possible correct options)

Which of the following statements about CLIP are TRUE? (Select ALL that apply)

Which one of the following statements is true:

Which of the following are examples of a high-pass filter?

Given is a $3 \times 3$ 8-bit grayscale image:

$\begin{bmatrix} 10 & 50 & 200 \\ 70 & 100 & 150 \\ 20 & 80 & 255 \end{bmatrix}$

What is the central element after applying linear contrast stretching (from the range $[I_{\min}, I_{\max}]$ to $[0, 255]$) ?

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) __________________ .

Based on the above data, answer the given subquestions.

Based on the above data, answer the given subquestions.

Based on the above data, answer the given subquestions.

Element 1:___________

Based on the above data, answer the given subquestions.

Element 2:___________

Based on the above data, answer the given subquestions.

Element 3:___________

Based on the above data, answer the given subquestions.

Element 4:___________

Consider the BLIP model architecture with an input (image-text pair) as shown below:

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 _______________

Consider the BLIP model architecture with an input (image-text pair) as shown below:

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:__________________

Consider the BLIP model architecture with an input (image-text pair) as shown below:

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 ):__________________

Consider the BLIP model architecture with an input (image-text pair) as shown below:

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: ___________________

Consider the BLIP model architecture with an input (image-text pair) as shown below:

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.

Consider the BLIP model architecture with an input (image-text pair) as shown below:

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: _________________

Consider the BLIP model architecture with an input (image-text pair) as shown below:

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): ____________

Consider the BLIP model architecture with an input (image-text pair) as shown below:

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.

Consider the BLIP model architecture with an input (image-text pair) as shown below:

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: _____________

Consider the BLIP model architecture with an input (image-text pair) as shown below:

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.

Consider the BLIP model architecture with an input (image-text pair) as shown below:

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 four-dimensional input vector $x = [4, -5, -7, 10]$ is passed to a hidden layer with a single neuron and an activation function $a(.)$ to obtain $z$. Assume that the corresponding weights (from input to hidden layer) are $[0.02, 0.8, 0.01, 2.5]$ and bias is 5.0. If the activation function $a(.)$ is Sigmoid, Linear, Indicator function, Softplus, ReLU and Leaky- ReLU, what are the corresponding values of $z$? (Note that Indicator function returns 1 for a positive input, and 0 otherwise Softplus is defined as: $\ln(1 + \exp(z))$).

Upto 2 decimal places

Based on the above data, answer the given subquestions.

Sigmoid ______________

A four-dimensional input vector $x = [4, -5, -7, 10]$ is passed to a hidden layer with a single neuron and an activation function $a(.)$ to obtain $z$. Assume that the corresponding weights (from input to hidden layer) are $[0.02, 0.8, 0.01, 2.5]$ and bias is 5.0. If the activation function $a(.)$ is Sigmoid, Linear, Indicator function, Softplus, ReLU and Leaky- ReLU, what are the corresponding values of $z$? (Note that Indicator function returns 1 for a positive input, and 0 otherwise Softplus is defined as: $\ln(1 + \exp(z))$).

Upto 2 decimal places

Based on the above data, answer the given subquestions.

Linear ______________

A four-dimensional input vector $x = [4, -5, -7, 10]$ is passed to a hidden layer with a single neuron and an activation function $a(.)$ to obtain $z$. Assume that the corresponding weights (from input to hidden layer) are $[0.02, 0.8, 0.01, 2.5]$ and bias is 5.0. If the activation function $a(.)$ is Sigmoid, Linear, Indicator function, Softplus, ReLU and Leaky- ReLU, what are the corresponding values of $z$? (Note that Indicator function returns 1 for a positive input, and 0 otherwise Softplus is defined as: $\ln(1 + \exp(z))$).

Upto 2 decimal places

Based on the above data, answer the given subquestions.

Indicator Function ______________

A four-dimensional input vector $x = [4, -5, -7, 10]$ is passed to a hidden layer with a single neuron and an activation function $a(.)$ to obtain $z$. Assume that the corresponding weights (from input to hidden layer) are $[0.02, 0.8, 0.01, 2.5]$ and bias is 5.0. If the activation function $a(.)$ is Sigmoid, Linear, Indicator function, Softplus, ReLU and Leaky- ReLU, what are the corresponding values of $z$? (Note that Indicator function returns 1 for a positive input, and 0 otherwise Softplus is defined as: $\ln(1 + \exp(z))$).

Upto 2 decimal places

Based on the above data, answer the given subquestions.

Softplus _____________

A four-dimensional input vector $x = [4, -5, -7, 10]$ is passed to a hidden layer with a single neuron and an activation function $a(.)$ to obtain $z$. Assume that the corresponding weights (from input to hidden layer) are $[0.02, 0.8, 0.01, 2.5]$ and bias is 5.0. If the activation function $a(.)$ is Sigmoid, Linear, Indicator function, Softplus, ReLU and Leaky- ReLU, what are the corresponding values of $z$? (Note that Indicator function returns 1 for a positive input, and 0 otherwise Softplus is defined as: $\ln(1 + \exp(z))$).

Upto 2 decimal places

Based on the above data, answer the given subquestions.

ReLU _______________

A four-dimensional input vector $x = [4, -5, -7, 10]$ is passed to a hidden layer with a single neuron and an activation function $a(.)$ to obtain $z$. Assume that the corresponding weights (from input to hidden layer) are $[0.02, 0.8, 0.01, 2.5]$ and bias is 5.0. If the activation function $a(.)$ is Sigmoid, Linear, Indicator function, Softplus, ReLU and Leaky- ReLU, what are the corresponding values of $z$? (Note that Indicator function returns 1 for a positive input, and 0 otherwise Softplus is defined as: $\ln(1 + \exp(z))$).

Upto 2 decimal places

Based on the above data, answer the given subquestions.

Leaky-ReLU _____________