Quiz Space

Deep Learning for Computer Vision · Quiz 2 · 24 Mar 2024 · January 2024 term

Question 4: Which of the following is true regarding Hard Attention a…

Question 4

+2 marksOne or more correct options

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

Select all that apply.

  1. A

    Soft Attention is smooth and differentiable

  2. B

    Variance reduction techniques are used to train Hard Attention models

  3. C

    Soft Attention is computationally cheaper than Hard Attention when the source input is large

  4. D

    The inference (test time) overhead is low in Hard Attention when compared to Soft Attention models

Show answer

Correct answers

  • A

    Soft Attention is smooth and differentiable

  • B

    Variance reduction techniques are used to train Hard Attention models

  • D

    The inference (test time) overhead is low in Hard Attention when compared to Soft Attention models

Video solution

The video solution to this question is being recorded and will play here. Until then, the answer key is above.

See the whole paperTake it as a mock test

Question 4 of 28 in the IIT Madras BS Deep Learning for Computer Vision (Deep Learning for Computer Vision) Quiz 2 paper sat on 24 Mar 2024, in the January 2024 term (IIT M DEGREE AN EXAM QDB2 24 Mar 2024). It carries 2 marks.

More questions from this paper

  1. Q1Which of the following statements are true?
  2. Q2Which of the below properties are not exhibited by the gradient-based explanation generation method, Grad-CAM? (Select …
  3. Q3Which of the following statements accurately describes the visualization techniques used in Convolutional Neural Networ…
  4. Q5Frechet Inception Distance (FID) is used for measuring the feature distance between real and generated images to evalua…
  5. Q6If x is an input feature vector and y is the corresponding output/label, which distributions are modeled in a vanilla G…
  6. Q7What is the size of the feature map after applying two successive convolution operations with given parameters? Image s…
  7. Q8Figure question
  8. Q9Figure question
  9. Q10Which method is commonly used to explain Convolutional Neural Networks (CNNs) through visualization?
  10. Q11Figure question
  11. Q12Consider two 10×10 bounding boxes (one on the upper left and one of the lower right) in an image with an overlapping re…
  12. Q13Which one of the following statements is true?
  13. Q14What are Haar-like features primarily used for in computer vision?
  14. Q15Figure question
  15. Q16Figure question
  16. Q17Which of the following is not a component of a Transformer network?
  17. Q18Consider the following assertion and the reason for the assertion below : Assertion: The images generated by VAEs exhib…
  18. Q19Figure question
  19. Q20Linear
  20. Q21Indicator function
  21. Q22Leaky-ReLU_
  22. Q23Fill in the blanks for the given sub questions. KL divergence is not a distance metric because KL(P||Q) is_ to KL(Q||P)…
  23. Q24Fill in the blanks for the given sub questions. Also KL divergence is always greater than equal to _
  24. Q25Fill in the blanks for the given sub questions. Suppose P := Bernoulli(0.9) and Q := Bernoulli(0.1), then KL(P||Q) = c …
  25. Q26Fill in the blanks for the given sub questions. Suppose P := Bernoulli(0.9) and Q := Bernoulli(0.1), then KL(P||Q) = c …
  26. Q27The values of D(G(z)) during the initial phase of training_
  27. Q28After successfully training the GAN