Quiz Space

Deep Learning for Computer Vision · Quiz 2 · 16 Mar 2025 · January 2025 term

Question 20: Consider a Faster R-CNN object detection framework, whic…

Question 20

+3 marksNumerical answer

Consider a Faster R-CNN object detection framework, which is being trained with a minibatch size of 2. The RPN produces 512 proposals, out of which 256 and 128 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: 384

See the whole paperTake it as a mock test

Question 20 of 37 in the IIT Madras BS Deep Learning for Computer Vision (Deep Learning for Computer Vision) Quiz 2 paper sat on 16 Mar 2025, in the January 2025 term (IIT M IMPROVEMENT AN EXAM QIM2 16 Mar 2025). It carries 3 marks.

More questions from this paper

  1. Q1Figure question
  2. Q2Which one of the following object detection networks uses an ROI pooling layer?
  3. Q3Match the following: | 1) VGGNet | i) 1 \times 1 convolution | |---|---| | 2) EfficientNet | ii) identity mapping | | 3…
  4. Q4Which one of the following statements is False?
  5. Q5Figure question
  6. Q6In object detection using CNNs, which loss function is typically used to optimize the confidence scores assigned to pre…
  7. Q7Consider two 12 × 12 bounding boxes(one on the upper left and one of the lower right) in an images with an overlapping …
  8. Q8In object detection using CNNs, what is the challenge addressed by the non-maximum suppression (NMS) technique?
  9. Q9Match the following computer vision tasks to situations: | 1) Instance Segmentation | i) There are cars in these pixels…
  10. Q10Match the following: | 1) One-to-many RNN architecture | i) Sentiment analysis of Netflix reviews | |---|---| | 2) Many…
  11. Q11Match the following attention mechanisms to their corresponding alignment score functions: | (1) General Attention | (i…
  12. Q12Which of the following techniques help control the exploding or vanishing gradient problem in recurrent neural networks…
  13. Q13State whether the given statement is True or False:\ While training an object detection algorithm, you need a training …
  14. Q14How are saliency maps generated in the context of Convolutional Neural Networks (CNNs)?
  15. Q15Consider an object detection system evaluated on a dataset consisting of 1000 images. The system makes 1500 predictions…
  16. Q16Which one of the following statements is false? (Pick the most appropriate one.)
  17. Q17Which of the following statements is True (select all that apply):
  18. Q18Which of the following is true regarding Hard Attention and Soft Attention?
  19. Q19Which of the following are true?
  20. Q21Based on the above data, answer the given subquestions.
  21. Q22Based on the above data, answer the given subquestions.
  22. Q23Based on the above data, answer the given subquestions.
  23. Q24Based on the above data, answer the given subquestions.
  24. Q25Based on the above data, answer the given subquestions.
  25. Q26Based on the above data, answer the given subquestions.
  26. Q27Number of Parameters:
  27. Q28Computational Cost:
  28. Q29Let input have size D_f \times D_f \times M where D_f = 128 and M = 16 and output feature map (after passing input thro…
  29. Q30Let input have size D_f \times D_f \times M where D_f = 128 and M = 16 and output feature map (after passing input thro…
  30. Q31Let input have size D_f \times D_f \times M where D_f = 128 and M = 16 and output feature map (after passing input thro…
  31. Q32Let input have size D_f \times D_f \times M where D_f = 128 and M = 16 and output feature map (after passing input thro…
  32. Q33Number of weights in Weight Matrix U1 is:
  33. Q34Number of weights in Weight Matrix V1 is: _
  34. Q35Number of weights in Weight Matrix U2 is:
  35. Q36Number of weights in Weight Matrix V2 is:
  36. Q37Number of weights in Weight Matrix W is: