Quiz Space

Deep Learning for Computer Vision · Quiz 2 · 4 Aug 2024 · May 2024 term

Question 4: Identify the true statement regarding different loss func…

Question 4

+2 marksOne correct option

Identify the true statement regarding different loss functions:

  1. A

    The objective of ranking loss is to predict relative distances between inputs.

  2. B

    The contrastive loss takes an anchor example and brings negative examples closer while pushing away positive examples.

  3. C

    The triplet loss always uses a non-negative margin to compare distances of sample representations.

  4. D

    The hinge loss only considers pairwise examples at a time.

Show answer

Correct answer

  • A

    The objective of ranking loss is to predict relative distances between inputs.

See the whole paperTake it as a mock test

Question 4 of 29 in the IIT Madras BS Deep Learning for Computer Vision (Deep Learning for Computer Vision) Quiz 2 paper sat on 4 Aug 2024, in the May 2024 term (IIT M DEGREE AN EXAM QDB2 4 Aug 2024). It carries 2 marks.

More questions from this paper

  1. Q1Which one of the below statements is incorrect?
  2. Q2Which one of the following statements is false?
  3. Q3Match the following:
  4. Q5In the context of Variational Autoencoders, the idea of variational inference solves the problem of
  5. Q6Which of the following is incorrect for the reparametrization trick used in a Variational AutoEncoder (VAE)?
  6. Q7In an image classification problem, which of the following is the quantity of interest in a generative model?
  7. Q8Figure question
  8. Q9Figure question
  9. Q10Which one of the following statements is true?
  10. Q11Which one of the following statements is false?
  11. Q12Consider two 10×10 bounding boxes(one on the upper left and one of the lower right) in an images with an overlapping re…
  12. Q13A four-dimensional input vector x = [5, 3,−1, 2] is passed to a hidden layer with a single neuron and an activation fun…
  13. Q14Figure question
  14. Q15Figure question
  15. Q16Figure question
  16. Q17Consider a Faster R-CNN object detection framework, which is being trained with a mini-batch size of 2. The RPN produce…
  17. Q18The feature embeddings obtained from a neural network for an anchor sample, positive sample and negative sample are as …
  18. Q19A Siamese network is trained for face verification. The face image to be verified is passed through the first branch an…
  19. Q20z1=_
  20. Q21z2=
  21. Q22z3=_
  22. Q23KL divergence is not a distance metric because \text{KL}(P|Q) is (a) to \text{KL}(Q|P). And KL divergence is always \ge…
  23. Q24KL divergence is not a distance metric because \text{KL}(P|Q) is (a) to \text{KL}(Q|P). And KL divergence is always \ge…
  24. Q25KL divergence is not a distance metric because \text{KL}(P|Q) is (a) to \text{KL}(Q|P). And KL divergence is always \ge…
  25. Q26KL divergence is not a distance metric because \text{KL}(P|Q) is (a) to \text{KL}(Q|P). And KL divergence is always \ge…
  26. Q27Consider generative and discriminative models for a classification task. Generative models learn the data-generating me…
  27. Q28Which of the following are true:
  28. Q29Which of the following is true regarding Hard Attention and Soft Attention?