Quiz Space

Deep Learning for Computer Vision · End Term · 10 May 2026 · January 2026 term

Question 10: A key reason CNNs are parameter-efficient compared to fu…

Question 10

+2 marksOne correct option

A key reason CNNs are parameter-efficient compared to fully connected nets for images is:

  1. A

    Weight sharing and local receptive fields

  2. B

    They never use nonlinearities thus easier to train

  3. C

    They always use pooling

  4. D

    Compared to vanilla neural network and RNN, they are robust to gradient explosion and vanishing gradient.

Show answer

Correct answer

  • A

    Weight sharing and local receptive fields

See the whole paperTake it as a mock test

Question 10 of 22 in the IIT Madras BS Deep Learning for Computer Vision (Deep Learning for Computer Vision) End Term paper sat on 10 May 2026, in the January 2026 term (Deep Learning For Computer Vision 06 May 26). It carries 2 marks.

More questions from this paper

  1. Q1A standard RGB image of size 256×256 is stored as 8-bit unsigned integers per channel. What is the total memory (in byt…
  2. Q2Which statement is correct?
  3. Q3You apply a 5×5 filter with stride 1 and no padding on a 32×32 image. Output size is:
  4. Q4The Sobel operator primarily estimates:
  5. Q5SIFT is designed to be robust mainly to:
  6. Q6In classical scale-space theory, increasing σ in Gaussian smoothing generally:
  7. Q7Backpropagation is best described as:
  8. Q8Which is a key effect of momentum?
  9. Q9L2 regularization on weights most directly encourages:
  10. Q11Stacking multiple 3×3 convolutions (stride 1) increases receptive field because:
  11. Q12In Faster R-CNN, the Region Proposal Network (RPN) outputs:
  12. Q13Which statement is correct ?
  13. Q14Vanishing gradients in vanilla RNNs occur mainly due to:
  14. Q15Select all correct statements:
  15. Q16Select all correct statements :
  16. Q17Select all correct statements:
  17. Q18Box A: top-left (0,0), bottom-right (8,8). Box B: top-left (4,4), bottom-right (12,12). Compute IoU as a decimal.
  18. Q19For a single query, suppose similarity with the positive is s+=2 and with two negatives are s1=1, s2=0. InfoNCE loss: L…
  19. Q20Input image: 64×64. Convolution: kernel 7×7, stride 2, padding 3. Compute output spatial size.
  20. Q21A fully connected network maps input 100 → hidden 50 → output 10. Ignore bias. What is the total number of weights?
  21. Q22Input feature map has M=64 channels. You apply depthwise 3×3 followed by pointwise 1×1 to produce N=128 channels. Ignor…