Quiz Space

Deep Learning for Computer Vision · Quiz 2 · 3 Aug 2025 · May 2025 term

Question 2: Which of the following architectures introduced the ROI p…

Question 2

+2 marksOne correct option

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

  1. A

    R-CNN

  2. B

    Fast R-CNN

  3. C

    Faster R-CNN

  4. D

    YOLO

Show answer

Correct answer

  • B

    Fast R-CNN

See the whole paperTake it as a mock test

Question 2 of 52 in the IIT Madras BS Deep Learning for Computer Vision (Deep Learning for Computer Vision) Quiz 2 paper sat on 3 Aug 2025, in the May 2025 term (IIT M IMPROVEMENT AN EXAM QIB2 03 Aug 2025). It carries 2 marks.

This question was also asked in

More questions from this paper

  1. Q1Figure question
  2. Q3Which object detection method first integrated a Region Proposal Network (RPN) to generate region proposals within the …
  3. Q4Which architecture performs object detection as a single regression problem from image pixels to bounding boxes and cla…
  4. Q5Figure question
  5. Q6Consider the following statements P and Q regarding AlexNet and choose the correct option: (P) In AlexNet, a trainable …
  6. Q7Consider two bounding boxes in an image:\ Box A: top-left at (0, 0), bottom-right at (12, 12) - Box B: top-left at (4, …
  7. Q8Which one of the following statements is True?
  8. Q9Figure question
  9. Q10Match the following: | 1) One-to-many RNN architecture | i) Sentiment analysis of Netflix reviews | |---|---| | 2) Many…
  10. Q11Figure question
  11. Q12Which of the following techniques help mitigate the vanishing gradient problem in recurrent neural networks?\ Gradient …
  12. Q13Which of the following techniques help mitigate the exploding gradient problem in recurrent neural networks?\ Gradient …
  13. Q14Which one of the following statements is false? (Pick the most appropriate one.)
  14. Q15Which of the following is true regarding Hard Attention and Soft Attention?
  15. Q16Which of the following are true:
  16. Q17Consider a Faster R-CNN object detection framework, which is being trained with a mini-batch size of 2. The RPN produce…
  17. Q18Suppose you want to build an encoder-decoder recurrent model with attention. The context vector at time step t is given…
  18. Q19Suppose you want to build an encoder-decoder recurrent model with attention. The context vector at time step t is given…
  19. Q20Consider a Gated Recurrent Unit (GRU) cell at time step ’t’. For each of the entities in the given subquestions, enter …
  20. Q21Consider a Gated Recurrent Unit (GRU) cell at time step ’t’. For each of the entities in the given subquestions, enter …
  21. Q22Consider a Gated Recurrent Unit (GRU) cell at time step ’t’. For each of the entities in the given subquestions, enter …
  22. Q23Consider a Gated Recurrent Unit (GRU) cell at time step ’t’. For each of the entities in the given subquestions, enter …
  23. Q24Consider a Gated Recurrent Unit (GRU) cell at time step ’t’. For each of the entities in the given subquestions, enter …
  24. Q25Consider a Gated Recurrent Unit (GRU) cell at time step ’t’. For each of the entities in the given subquestions, enter …
  25. Q26Number of Parameters:_
  26. Q27Computational Cost:_
  27. Q28Number of parameters for depthwise seperable convolution:_
  28. Q29Computational Cost for depthwise seperable convolution:
  29. Q30Number of parameters for pointwise convolution:_
  30. Q31Computational cost for pointwise convolution:
  31. Q32Number of weights in Weight Matrix U1 is:
  32. Q33Number of weights in Weight Matrix V1 is:
  33. Q34Number of weights in Weight Matrix U2 is:
  34. Q35Number of weights in Weight Matrix V2 is:_
  35. Q36Number of weights in Weight Matrix W is:_
  36. Q37e21: _
  37. Q38e22: _
  38. Q39e23: _
  39. Q40α21: _
  40. Q41α22: _
  41. Q42α23: _
  42. Q43c21: _
  43. Q44c22: _
  44. Q45e21:_
  45. Q46e22:_
  46. Q47e23:_
  47. Q48α21:_
  48. Q49α22:_
  49. Q50α23:_
  50. Q51c21:_
  51. Q52c22:_