Question 1
Based on the above data, answer the given subquestions.
Number of Parameters: ______________
Deep Learning for Computer Vision Quiz 2: 1 December 2024 (September 2024 term)
The IIT Madras BS Deep Learning for Computer Vision (Deep Learning for Computer Vision) Quiz 2 paper sat on 1 Dec 2024, in the September 2024 term: 26 questions for 52 marks in 120 minutes. Every question is below with its answer. Take it as a timed mock test to be marked, or read it through first.
- 26
- 52
- 120 min
- 12
- 12
- 2
Show answer
Correct answer: 12800
Question 2
Based on the above data, answer the given subquestions.
Computational Cost: ______________
Show answer
Correct answer: 209715200
Question 3
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 convolution: ______________
Show answer
Correct answer: 400
Question 4
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 convolution: ______________
Show answer
Correct answer: 6553600
Question 5
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: ______________
Show answer
Correct answer: 512
Question 6
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: ______________
Show answer
Correct answer: 8388608
Question 7
Show answer
Correct answer
Question 8
Which one of the following object detection networks uses an ROI pooling layer?
Fast R-CNN
R-CNN
YOLO
All of these
Show answer
Correct answer
Fast R-CNN
Question 9
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:
| Recall | Precision |
|---|---|
| 0.1 | 0.90 |
| 0.2 | 0.85 |
| 0.3 | 0.80 |
| 0.4 | 0.75 |
| 0.5 | 0.70 |
| 0.6 | 0.65 |
| 0.7 | 0.60 |
| 0.8 | 0.55 |
| 0.9 | 0.50 |
| 1.0 | 0.45 |
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
Show answer
Correct answer
0.73
Question 10
1→iv, 2→ii, 3→v, 4→i
1→iv, 2→iii, 3→v, 4→ii
1→iv, 2→v, 3→ii, 4→iii
1→iii, 2→v, 3→i, 4→ii
Show answer
Correct answer
1→iii, 2→v, 3→i, 4→ii
Question 11
Which one of the following statements is False?
In a max pooling layer, the unit that gets selected (maximum entry) in forward propagation gets all the gradient during backpropagation.
Residual blocks are used in ResNets to avoid the vanishing gradient problem.
Feature maps of initial layers of a CNN capture more abstract concepts than the feature maps of final layers.
Dilated convolution increases the receptive field size when compared to the standard convolution operator.
Show answer
Correct answer
Feature maps of initial layers of a CNN capture more abstract concepts than the feature maps of final layers.
Question 12
Sigmoid of alignment scores
Softmax of alignment scores
ReLU of alignment scores
None of these
Show answer
Correct answer
Softmax of alignment scores
Question 13
Which one of the following statements is false?
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
Show answer
Correct answer
None of these
Question 14
Consider two 12×12 bounding boxes(one on the upper left and one of the lower right) in an images with an overlapping region of 8 × 8. The Intersection over Union (IoU) between the two boxes is (choose the closest value):
21%
25%
28%
37%
Show answer
Correct answer
28%
Question 15
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
Show answer
Correct answer
None of these
Question 16
1→ iv, 2→ iii, 3→ ii, 4 → i
1→ ii, 2→ iii, 3 → i, 4 →iv
1→ iv, 2→ iii, 3→ i, 4 → ii
1→ ii, 2→ iv, 3 → iii, 4→ i
Show answer
Correct answer
1→ iv, 2→ iii, 3→ i, 4 → ii
Question 17
Match the following:
| 1) One-to-many RNN architecture | i) Sentiment analysis of Netflix reviews |
|---|---|
| 2) Many-to-one RNN architecture | ii) Convert English sentence to Hindi |
| 3) Many-to-many RNN architecture with equal number of inputs and outputs | iii) Named entity recognition |
| 4) Many-to-many RNN architecture with unequal number of inputs and outputs (Encoder and Decoder model) | iv) Music generation |
1→ iii, 2→ iv, 3→ ii, 4 → i
1→ iv, 2→ i, 3 → iii, 4→ ii
1→ i, 2→ ii, 3 → iii, 4→ iv
1→ i, 2→ iii, 3 → ii, 4→ iv
Show answer
Correct answer
1→ iv, 2→ i, 3 → iii, 4→ ii
Question 18
1→iii, 2→ii, 3→v, 4→iv,5→i
1→iii, 2→iv, 3→i, 4→ii,5→v
1→i, 2→iii, 3→iv, 4→ii,5→v
1→v, 2→iv, 3→iii, 4→i,5→ii
Show answer
Correct answer
1→v, 2→iv, 3→iii, 4→i,5→ii
Question 19
Which of the following are true:
Show answer
Correct answers
Question 20
Which of the following is true regarding Hard Attention and Soft Attention?
Soft Attention is smooth and differentiable
Variance reduction techniques are used to train Soft Attention models
Soft Attention is computationally cheaper than Hard Attention when the source input is large
The inference (test time) overhead is low in Hard Attention when compared to Soft Attention models
Show answer
Correct answers
Soft Attention is smooth and differentiable
The inference (test time) overhead is low in Hard Attention when compared to Soft Attention models
Question 21
Consider a Faster R-CNN object detection framework, which is being trained with a mini-batch size of 2. The RPN produces 512 proposals, out of which 5 and 95 of them are foreground proposals, corresponding to each image in the mini-batch. For a single mini-batch update, the bounding box regression loss will be computed _____________ times.
Show answer
Correct answer: 100
Question 22
The RNN given below is used for classification:
Based on the above data, answer the given subquestions.
Number of weights in Weight Matrix U1 is: ______________
Show answer
Correct answer: 33792
Question 23
The RNN given below is used for classification:
Based on the above data, answer the given subquestions.
Number of weights in Weight Matrix V1 is: ______________
Show answer
Correct answer: 65536
Question 24
The RNN given below is used for classification:
Based on the above data, answer the given subquestions.
Number of weights in Weight Matrix U2 is: ______________
Show answer
Correct answer: 32768
Question 25
The RNN given below is used for classification:
Based on the above data, answer the given subquestions.
Number of weights in Weight Matrix V2 is: ______________
Show answer
Correct answer: 16384
Question 26
The RNN given below is used for classification:
Based on the above data, answer the given subquestions.
Number of weights in Weight Matrix W is: ______________
Show answer
Correct answer: 1920