Deep Learning for Computer Vision Quiz 2: 23 November 2025 (September 2025 term)

Which of the following architectures introduced the ROI pooling layer for extracting fixed-size feature maps from variable-size region proposals?

Which object detection method first integrated a Region Proposal Network (RPN) to generate region proposals within the detection model?

Which architecture performs object detection as a single regression problem from image pixels to bounding boxes and class probabilities?

Consider the following statements P and Q regarding AlexNet and choose the correct option: (P) In AlexNet, a trainable Local Response Normalization Layers were introduced to emulate the competitive nature of real neurons, where highly active neurons suppress the activity of neighboring neurons, creating competition among different kernel outputs.
(Q) In AlexNet, a total of 8 Convolutional layers contain only about 6-7% of the total parameters hence account for the least computation.

Consider two bounding boxes in an image:
- Box A: top-left at (0, 0), bottom-right at (12, 12) - Box B: top-left at (4, 4), bottom-right at (16, 16) What is the Intersection over Union (IoU) between these two boxes ______________

Which one of the following statements is True?

Match the following computer vision tasks to situations:

Match the following:

Which of the following techniques help mitigate the vanishing gradient problem in recurrent neural networks?
1. Gradient clipping
2. Use of ReLU activation to preserve gradient flow
3. Use of LSTM units
4. Data augmentation (e.g., reversing input sequence)

Which of the following techniques help mitigate the exploding gradient problem in recurrent neural networks?
1. Gradient clipping
2. Use of Sigmoid activation to prevent gradient growth
3. Use of LSTM units
4. Data augmentation (e.g., reversing input sequence)

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

Which of the following is true regarding Hard Attention and Soft Attention?

Which of the following are False:

Which techniques help mitigate exploding/vanishing gradients in RNNs? (Select all that apply.)

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.

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.

Based on the above data, answer the given subquestions.

Number of Parameters:_____________

Based on the above data, answer the given subquestions.

Computational Cost:________________

Using the same dimensions specified in the previous question main data, calculate the number of parameters and computational cost, but make use of Depthwise Seperable convolution and pointwise convolution instead of standard convolution.
Based on the above data, answer the given subquestions.

Number of parameters for depthwise seperable convolution: __________

Using the same dimensions specified in the previous question main data, calculate the number of parameters and computational cost, but make use of Depthwise Seperable convolution and pointwise convolution instead of standard convolution.
Based on the above data, answer the given subquestions.

Computational Cost for depthwise seperable convolution:____________

Using the same dimensions specified in the previous question main data, calculate the number of parameters and computational cost, but make use of Depthwise Seperable convolution and pointwise convolution instead of standard convolution.
Based on the above data, answer the given subquestions.

Number of parameters for pointwise convolution:_____________

Using the same dimensions specified in the previous question main data, calculate the number of parameters and computational cost, but make use of Depthwise Seperable convolution and pointwise convolution instead of standard convolution.
Based on the above data, answer the given subquestions.

Computational cost for pointwise convolution:____________

Based on the above data, answer the given subquestions.

Number of weights in Weight Matrix U1 is:_____________

Based on the above data, answer the given subquestions.

Number of weights in Weight Matrix V1 is:_____________

Based on the above data, answer the given subquestions.

Number of weights in Weight Matrix U2 is:_____________

Based on the above data, answer the given subquestions.

Number of weights in Weight Matrix V2 is:_____________

Based on the above data, answer the given subquestions.

Number of weights in Weight Matrix W is:_____________

You are given the encoder hidden states $h_1, h_2, h_3 \in \mathbb{R}^2$ and the decoder hidden state $s_2 \in \mathbb{R}^2$ at time step $t = 2$.

Use **dot-product attention**, where the attention score is computed as:

$e_{tj} = s_t^\top h_j \quad \text{and} \quad \alpha_{tj} = \frac{\exp(e_{tj})}{\sum_{k=1}^{3} \exp(e_{tk})}$

The context vector is then computed as:

$c_t = \sum_{j=1}^{3} \alpha_{tj} h_j$

Use the following values:

$s_2 = \begin{bmatrix} 1 \\ 0 \end{bmatrix}, \quad h_1 = \begin{bmatrix} 1 \\ 2 \end{bmatrix}, \quad h_2 = \begin{bmatrix} 0 \\ 1 \end{bmatrix}, \quad h_3 = \begin{bmatrix} 2 \\ 3 \end{bmatrix}$

Note: Use approximate values of exponential $\exp(1) \approx 2.72$, $\exp(2) \approx 7.39$, etc.

Answer the given subquestions:

You are given the encoder hidden states $h_1, h_2, h_3 \in \mathbb{R}^2$ and the decoder hidden state $s_2 \in \mathbb{R}^2$ at time step $t = 2$.

Use **dot-product attention**, where the attention score is computed as:

$e_{tj} = s_t^\top h_j \quad \text{and} \quad \alpha_{tj} = \frac{\exp(e_{tj})}{\sum_{k=1}^{3} \exp(e_{tk})}$

The context vector is then computed as:

$c_t = \sum_{j=1}^{3} \alpha_{tj} h_j$

Use the following values:

$s_2 = \begin{bmatrix} 1 \\ 0 \end{bmatrix}, \quad h_1 = \begin{bmatrix} 1 \\ 2 \end{bmatrix}, \quad h_2 = \begin{bmatrix} 0 \\ 1 \end{bmatrix}, \quad h_3 = \begin{bmatrix} 2 \\ 3 \end{bmatrix}$

Note: Use approximate values of exponential $\exp(1) \approx 2.72$, $\exp(2) \approx 7.39$, etc.

Answer the given subquestions:

You are given the encoder hidden states $h_1, h_2, h_3 \in \mathbb{R}^2$ and the decoder hidden state $s_2 \in \mathbb{R}^2$ at time step $t = 2$.

Use **dot-product attention**, where the attention score is computed as:

$e_{tj} = s_t^\top h_j \quad \text{and} \quad \alpha_{tj} = \frac{\exp(e_{tj})}{\sum_{k=1}^{3} \exp(e_{tk})}$

The context vector is then computed as:

$c_t = \sum_{j=1}^{3} \alpha_{tj} h_j$

Use the following values:

$s_2 = \begin{bmatrix} 1 \\ 0 \end{bmatrix}, \quad h_1 = \begin{bmatrix} 1 \\ 2 \end{bmatrix}, \quad h_2 = \begin{bmatrix} 0 \\ 1 \end{bmatrix}, \quad h_3 = \begin{bmatrix} 2 \\ 3 \end{bmatrix}$

Note: Use approximate values of exponential $\exp(1) \approx 2.72$, $\exp(2) \approx 7.39$, etc.

Answer the given subquestions:

You are given the encoder hidden states $h_1, h_2, h_3 \in \mathbb{R}^2$ and the decoder hidden state $s_2 \in \mathbb{R}^2$ at time step $t = 2$.

Use **dot-product attention**, where the attention score is computed as:

$e_{tj} = s_t^\top h_j \quad \text{and} \quad \alpha_{tj} = \frac{\exp(e_{tj})}{\sum_{k=1}^{3} \exp(e_{tk})}$

The context vector is then computed as:

$c_t = \sum_{j=1}^{3} \alpha_{tj} h_j$

Use the following values:

$s_2 = \begin{bmatrix} 1 \\ 0 \end{bmatrix}, \quad h_1 = \begin{bmatrix} 1 \\ 2 \end{bmatrix}, \quad h_2 = \begin{bmatrix} 0 \\ 1 \end{bmatrix}, \quad h_3 = \begin{bmatrix} 2 \\ 3 \end{bmatrix}$

Note: Use approximate values of exponential $\exp(1) \approx 2.72$, $\exp(2) \approx 7.39$, etc.

Answer the given subquestions:

You are given the encoder hidden states $h_1, h_2, h_3 \in \mathbb{R}^2$ and the decoder hidden state $s_2 \in \mathbb{R}^2$ at time step $t = 2$.

Use **dot-product attention**, where the attention score is computed as:

$e_{tj} = s_t^\top h_j \quad \text{and} \quad \alpha_{tj} = \frac{\exp(e_{tj})}{\sum_{k=1}^{3} \exp(e_{tk})}$

The context vector is then computed as:

$c_t = \sum_{j=1}^{3} \alpha_{tj} h_j$

Use the following values:

$s_2 = \begin{bmatrix} 1 \\ 0 \end{bmatrix}, \quad h_1 = \begin{bmatrix} 1 \\ 2 \end{bmatrix}, \quad h_2 = \begin{bmatrix} 0 \\ 1 \end{bmatrix}, \quad h_3 = \begin{bmatrix} 2 \\ 3 \end{bmatrix}$

Note: Use approximate values of exponential $\exp(1) \approx 2.72$, $\exp(2) \approx 7.39$, etc.

Answer the given subquestions:

You are given the encoder hidden states $h_1, h_2, h_3 \in \mathbb{R}^2$ and the decoder hidden state $s_2 \in \mathbb{R}^2$ at time step $t = 2$.

Use **dot-product attention**, where the attention score is computed as:

$e_{tj} = s_t^\top h_j \quad \text{and} \quad \alpha_{tj} = \frac{\exp(e_{tj})}{\sum_{k=1}^{3} \exp(e_{tk})}$

The context vector is then computed as:

$c_t = \sum_{j=1}^{3} \alpha_{tj} h_j$

Use the following values:

$s_2 = \begin{bmatrix} 1 \\ 0 \end{bmatrix}, \quad h_1 = \begin{bmatrix} 1 \\ 2 \end{bmatrix}, \quad h_2 = \begin{bmatrix} 0 \\ 1 \end{bmatrix}, \quad h_3 = \begin{bmatrix} 2 \\ 3 \end{bmatrix}$

Note: Use approximate values of exponential $\exp(1) \approx 2.72$, $\exp(2) \approx 7.39$, etc.

Answer the given subquestions:

You are given the encoder hidden states $h_1, h_2, h_3 \in \mathbb{R}^2$ and the decoder hidden state $s_2 \in \mathbb{R}^2$ at time step $t = 2$.

Use **dot-product attention**, where the attention score is computed as:

$e_{tj} = s_t^\top h_j \quad \text{and} \quad \alpha_{tj} = \frac{\exp(e_{tj})}{\sum_{k=1}^{3} \exp(e_{tk})}$

The context vector is then computed as:

$c_t = \sum_{j=1}^{3} \alpha_{tj} h_j$

Use the following values:

$s_2 = \begin{bmatrix} 1 \\ 0 \end{bmatrix}, \quad h_1 = \begin{bmatrix} 1 \\ 2 \end{bmatrix}, \quad h_2 = \begin{bmatrix} 0 \\ 1 \end{bmatrix}, \quad h_3 = \begin{bmatrix} 2 \\ 3 \end{bmatrix}$

Note: Use approximate values of exponential $\exp(1) \approx 2.72$, $\exp(2) \approx 7.39$, etc.

Answer the given subquestions:

You are given the encoder hidden states $h_1, h_2, h_3 \in \mathbb{R}^2$ and the decoder hidden state $s_2 \in \mathbb{R}^2$ at time step $t = 2$.

Use **dot-product attention**, where the attention score is computed as:

$e_{tj} = s_t^\top h_j \quad \text{and} \quad \alpha_{tj} = \frac{\exp(e_{tj})}{\sum_{k=1}^{3} \exp(e_{tk})}$

The context vector is then computed as:

$c_t = \sum_{j=1}^{3} \alpha_{tj} h_j$

Use the following values:

$s_2 = \begin{bmatrix} 1 \\ 0 \end{bmatrix}, \quad h_1 = \begin{bmatrix} 1 \\ 2 \end{bmatrix}, \quad h_2 = \begin{bmatrix} 0 \\ 1 \end{bmatrix}, \quad h_3 = \begin{bmatrix} 2 \\ 3 \end{bmatrix}$

Note: Use approximate values of exponential $\exp(1) \approx 2.72$, $\exp(2) \approx 7.39$, etc.

Answer the given subquestions:

You are given the encoder hidden states $h_1, h_2, h_3 \in \mathbb{R}^2$ and the decoder hidden state $s_2 \in \mathbb{R}^2$ at time step $t = 2$.

Use **additive attention**, where the alignment score is computed as:

$e_{tj} = v_a^\top \tanh(W_1 s_t + W_2 h_j) \quad \text{and} \quad \alpha_{tj} = \frac{\exp(e_{tj})}{\sum_{k=1}^{3} \exp(e_{tk})}$

The context vector is then computed as:

$c_t = \sum_{j=1}^{3} \alpha_{tj} h_j$

Use the following values:

$s_2 = \begin{bmatrix} 1 \\ 0 \end{bmatrix}, \quad h_1 = \begin{bmatrix} 1 \\ 2 \end{bmatrix}, \quad h_2 = \begin{bmatrix} 0 \\ 1 \end{bmatrix}, \quad h_3 = \begin{bmatrix} 2 \\ 3 \end{bmatrix}$

$W_1 = \begin{bmatrix} 1 & 0 \\ 0 & 1 \end{bmatrix}, \quad W_2 = \begin{bmatrix} 1 & 1 \\ 1 & 1 \end{bmatrix}, \quad v_a = \begin{bmatrix} 1 \\ -1 \end{bmatrix}$

Based on the above data, answer the given subquestions.

You are given the encoder hidden states $h_1, h_2, h_3 \in \mathbb{R}^2$ and the decoder hidden state $s_2 \in \mathbb{R}^2$ at time step $t = 2$.

Use **additive attention**, where the alignment score is computed as:

$e_{tj} = v_a^\top \tanh(W_1 s_t + W_2 h_j) \quad \text{and} \quad \alpha_{tj} = \frac{\exp(e_{tj})}{\sum_{k=1}^{3} \exp(e_{tk})}$

The context vector is then computed as:

$c_t = \sum_{j=1}^{3} \alpha_{tj} h_j$

Use the following values:

$s_2 = \begin{bmatrix} 1 \\ 0 \end{bmatrix}, \quad h_1 = \begin{bmatrix} 1 \\ 2 \end{bmatrix}, \quad h_2 = \begin{bmatrix} 0 \\ 1 \end{bmatrix}, \quad h_3 = \begin{bmatrix} 2 \\ 3 \end{bmatrix}$

$W_1 = \begin{bmatrix} 1 & 0 \\ 0 & 1 \end{bmatrix}, \quad W_2 = \begin{bmatrix} 1 & 1 \\ 1 & 1 \end{bmatrix}, \quad v_a = \begin{bmatrix} 1 \\ -1 \end{bmatrix}$

Based on the above data, answer the given subquestions.

You are given the encoder hidden states $h_1, h_2, h_3 \in \mathbb{R}^2$ and the decoder hidden state $s_2 \in \mathbb{R}^2$ at time step $t = 2$.

Use **additive attention**, where the alignment score is computed as:

$e_{tj} = v_a^\top \tanh(W_1 s_t + W_2 h_j) \quad \text{and} \quad \alpha_{tj} = \frac{\exp(e_{tj})}{\sum_{k=1}^{3} \exp(e_{tk})}$

The context vector is then computed as:

$c_t = \sum_{j=1}^{3} \alpha_{tj} h_j$

Use the following values:

$s_2 = \begin{bmatrix} 1 \\ 0 \end{bmatrix}, \quad h_1 = \begin{bmatrix} 1 \\ 2 \end{bmatrix}, \quad h_2 = \begin{bmatrix} 0 \\ 1 \end{bmatrix}, \quad h_3 = \begin{bmatrix} 2 \\ 3 \end{bmatrix}$

$W_1 = \begin{bmatrix} 1 & 0 \\ 0 & 1 \end{bmatrix}, \quad W_2 = \begin{bmatrix} 1 & 1 \\ 1 & 1 \end{bmatrix}, \quad v_a = \begin{bmatrix} 1 \\ -1 \end{bmatrix}$

Based on the above data, answer the given subquestions.

You are given the encoder hidden states $h_1, h_2, h_3 \in \mathbb{R}^2$ and the decoder hidden state $s_2 \in \mathbb{R}^2$ at time step $t = 2$.

Use **additive attention**, where the alignment score is computed as:

$e_{tj} = v_a^\top \tanh(W_1 s_t + W_2 h_j) \quad \text{and} \quad \alpha_{tj} = \frac{\exp(e_{tj})}{\sum_{k=1}^{3} \exp(e_{tk})}$

The context vector is then computed as:

$c_t = \sum_{j=1}^{3} \alpha_{tj} h_j$

Use the following values:

$s_2 = \begin{bmatrix} 1 \\ 0 \end{bmatrix}, \quad h_1 = \begin{bmatrix} 1 \\ 2 \end{bmatrix}, \quad h_2 = \begin{bmatrix} 0 \\ 1 \end{bmatrix}, \quad h_3 = \begin{bmatrix} 2 \\ 3 \end{bmatrix}$

$W_1 = \begin{bmatrix} 1 & 0 \\ 0 & 1 \end{bmatrix}, \quad W_2 = \begin{bmatrix} 1 & 1 \\ 1 & 1 \end{bmatrix}, \quad v_a = \begin{bmatrix} 1 \\ -1 \end{bmatrix}$

Based on the above data, answer the given subquestions.

You are given the encoder hidden states $h_1, h_2, h_3 \in \mathbb{R}^2$ and the decoder hidden state $s_2 \in \mathbb{R}^2$ at time step $t = 2$.

Use **additive attention**, where the alignment score is computed as:

$e_{tj} = v_a^\top \tanh(W_1 s_t + W_2 h_j) \quad \text{and} \quad \alpha_{tj} = \frac{\exp(e_{tj})}{\sum_{k=1}^{3} \exp(e_{tk})}$

The context vector is then computed as:

$c_t = \sum_{j=1}^{3} \alpha_{tj} h_j$

Use the following values:

$s_2 = \begin{bmatrix} 1 \\ 0 \end{bmatrix}, \quad h_1 = \begin{bmatrix} 1 \\ 2 \end{bmatrix}, \quad h_2 = \begin{bmatrix} 0 \\ 1 \end{bmatrix}, \quad h_3 = \begin{bmatrix} 2 \\ 3 \end{bmatrix}$

$W_1 = \begin{bmatrix} 1 & 0 \\ 0 & 1 \end{bmatrix}, \quad W_2 = \begin{bmatrix} 1 & 1 \\ 1 & 1 \end{bmatrix}, \quad v_a = \begin{bmatrix} 1 \\ -1 \end{bmatrix}$

Based on the above data, answer the given subquestions.

You are given the encoder hidden states $h_1, h_2, h_3 \in \mathbb{R}^2$ and the decoder hidden state $s_2 \in \mathbb{R}^2$ at time step $t = 2$.

Use **additive attention**, where the alignment score is computed as:

$e_{tj} = v_a^\top \tanh(W_1 s_t + W_2 h_j) \quad \text{and} \quad \alpha_{tj} = \frac{\exp(e_{tj})}{\sum_{k=1}^{3} \exp(e_{tk})}$

The context vector is then computed as:

$c_t = \sum_{j=1}^{3} \alpha_{tj} h_j$

Use the following values:

$s_2 = \begin{bmatrix} 1 \\ 0 \end{bmatrix}, \quad h_1 = \begin{bmatrix} 1 \\ 2 \end{bmatrix}, \quad h_2 = \begin{bmatrix} 0 \\ 1 \end{bmatrix}, \quad h_3 = \begin{bmatrix} 2 \\ 3 \end{bmatrix}$

$W_1 = \begin{bmatrix} 1 & 0 \\ 0 & 1 \end{bmatrix}, \quad W_2 = \begin{bmatrix} 1 & 1 \\ 1 & 1 \end{bmatrix}, \quad v_a = \begin{bmatrix} 1 \\ -1 \end{bmatrix}$

Based on the above data, answer the given subquestions.

You are given the encoder hidden states $h_1, h_2, h_3 \in \mathbb{R}^2$ and the decoder hidden state $s_2 \in \mathbb{R}^2$ at time step $t = 2$.

Use **additive attention**, where the alignment score is computed as:

$e_{tj} = v_a^\top \tanh(W_1 s_t + W_2 h_j) \quad \text{and} \quad \alpha_{tj} = \frac{\exp(e_{tj})}{\sum_{k=1}^{3} \exp(e_{tk})}$

The context vector is then computed as:

$c_t = \sum_{j=1}^{3} \alpha_{tj} h_j$

Use the following values:

$s_2 = \begin{bmatrix} 1 \\ 0 \end{bmatrix}, \quad h_1 = \begin{bmatrix} 1 \\ 2 \end{bmatrix}, \quad h_2 = \begin{bmatrix} 0 \\ 1 \end{bmatrix}, \quad h_3 = \begin{bmatrix} 2 \\ 3 \end{bmatrix}$

$W_1 = \begin{bmatrix} 1 & 0 \\ 0 & 1 \end{bmatrix}, \quad W_2 = \begin{bmatrix} 1 & 1 \\ 1 & 1 \end{bmatrix}, \quad v_a = \begin{bmatrix} 1 \\ -1 \end{bmatrix}$

Based on the above data, answer the given subquestions.

You are given the encoder hidden states $h_1, h_2, h_3 \in \mathbb{R}^2$ and the decoder hidden state $s_2 \in \mathbb{R}^2$ at time step $t = 2$.

Use **additive attention**, where the alignment score is computed as:

$e_{tj} = v_a^\top \tanh(W_1 s_t + W_2 h_j) \quad \text{and} \quad \alpha_{tj} = \frac{\exp(e_{tj})}{\sum_{k=1}^{3} \exp(e_{tk})}$

The context vector is then computed as:

$c_t = \sum_{j=1}^{3} \alpha_{tj} h_j$

Use the following values:

$s_2 = \begin{bmatrix} 1 \\ 0 \end{bmatrix}, \quad h_1 = \begin{bmatrix} 1 \\ 2 \end{bmatrix}, \quad h_2 = \begin{bmatrix} 0 \\ 1 \end{bmatrix}, \quad h_3 = \begin{bmatrix} 2 \\ 3 \end{bmatrix}$

$W_1 = \begin{bmatrix} 1 & 0 \\ 0 & 1 \end{bmatrix}, \quad W_2 = \begin{bmatrix} 1 & 1 \\ 1 & 1 \end{bmatrix}, \quad v_a = \begin{bmatrix} 1 \\ -1 \end{bmatrix}$

Based on the above data, answer the given subquestions.