Quiz Space

Deep Learning for Computer Vision · End Term · 21 Dec 2025 · September 2025 term

Deep Learning for Computer Vision End Term 21 Dec 2025 — Question 11

Question 11

+1 markOne or more correct options

Which statements are correct? (Select all that apply.)

Select all that apply.

  1. A

    A linear autoencoder with MSE and no activation learns a subspace equivalent to PCA (up to rotation) when the hidden dimension < input dimension.

  2. B

    Global attention assigns alignment weights to all encoder time steps for each decoder step.

  3. C

    Positional encodings convey order information that self-attention lacks.

  4. D

    it is impossible to generate multiple, semantically similar captions with different styles for the same image.

Show answer

Correct answers

  • A

    A linear autoencoder with MSE and no activation learns a subspace equivalent to PCA (up to rotation) when the hidden dimension < input dimension.

  • B

    Global attention assigns alignment weights to all encoder time steps for each decoder step.

  • C

    Positional encodings convey order information that self-attention lacks.

See the whole paperTake it as a mock test

Question 11 of 19 in the IIT Madras BS Deep Learning for Computer Vision (Deep Learning for Computer Vision) End Term paper sat on 21 Dec 2025, in the September 2025 term (Deep Learning For Computer Vision 18 Dec 25). It carries 1 mark.

More questions from this paper

  1. Q1Figure question
  2. Q2Figure question
  3. Q3Figure question
  4. Q4Figure question
  5. Q5In a Feature Pyramid Network (FPN), the primary purpose of the top-down pathway with lateral connections is to:
  6. Q6Consider the following pyTorch code:
  7. Q7Figure question
  8. Q8How is disentangled representation evaluated?:
  9. Q9Which statements about generative models are true? (Select all that apply.)
  10. Q10In classifier-free guidance for diffusion models, increasing the guidance scale γ tends to: (Select all that apply.)
  11. Q12Figure question
  12. Q13Figure question
  13. Q14Figure question
  14. Q15Mixup data augmentation primarily:
  15. Q16Figure question
  16. Q17During training, Batch Normalization uses:
  17. Q18Which techniques help mitigate exploding/vanishing gradients in RNNs? (Select all that apply.)
  18. Q19Figure question