Quiz Space

Deep Learning for Computer Vision · Quiz 2 · 1 Dec 2024 · September 2024 term

Deep Learning for Computer Vision Quiz 2 1 Dec 2024 — Question 11

Question 11

+2 marksOne correct option

Which one of the following statements is False?

  1. A

    In a max pooling layer, the unit that gets selected (maximum entry) in forward propagation gets all the gradient during backpropagation.

  2. B

    Residual blocks are used in ResNets to avoid the vanishing gradient problem.

  3. C

    Feature maps of initial layers of a CNN capture more abstract concepts than the feature maps of final layers.

  4. D

    Dilated convolution increases the receptive field size when compared to the standard convolution operator.

Show answer

Correct answer

  • C

    Feature maps of initial layers of a CNN capture more abstract concepts than the feature maps of final layers.

See the whole paperTake it as a mock test

Question 11 of 26 in 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 (IIT M IMPROVEMENT AN EXAM QIM2 01 Dec 2024). It carries 2 marks.

This question was also asked in

More questions from this paper

  1. Q1Number of Parameters:
  2. Q2Computational Cost:
  3. Q3Number of parameters for depthwise convolution:
  4. Q4Computational Cost for depthwise convolution:
  5. Q5Number of parameters for pointwise convolution:
  6. Q6Computational cost for pointwise convolution:
  7. Q7Figure question
  8. Q8Which one of the following object detection networks uses an ROI pooling layer?
  9. Q9Consider an object detection system evaluated on a dataset consisting of 1000 images. The system makes 1500 predictions…
  10. Q10Figure question
  11. Q12Figure question
  12. Q13Which one of the following statements is false?
  13. Q14Consider two 12×12 bounding boxes(one on the upper left and one of the lower right) in an images with an overlapping re…
  14. Q15Which one of the following statements is true?
  15. Q16Figure question
  16. Q17Match the following: | 1) One-to-many RNN architecture | i) Sentiment analysis of Netflix reviews | |---|---| | 2) Many…
  17. Q18Figure question
  18. Q19Which of the following are true:
  19. Q20Which of the following is true regarding Hard Attention and Soft Attention?
  20. Q21Consider a Faster R-CNN object detection framework, which is being trained with a mini-batch size of 2. The RPN produce…
  21. Q22The RNN given below is used for classification: Based on the above data, answer the given subquestions. Number of weigh…
  22. Q23The RNN given below is used for classification: Based on the above data, answer the given subquestions. Number of weigh…
  23. Q24The RNN given below is used for classification: Based on the above data, answer the given subquestions. Number of weigh…
  24. Q25The RNN given below is used for classification: Based on the above data, answer the given subquestions. Number of weigh…
  25. Q26The RNN given below is used for classification: Based on the above data, answer the given subquestions. Number of weigh…