Deep Learning Practice · End Term · 13 Sept 2026 · May 2026 term · Set 1

Question 27: Which of the following statements correctly describe the…

Question 27

+2 marksOne or more correct options

Which of the following statements correctly describe the Region Proposal Network (RPN) in Faster R-CNN?

Select all that apply.

A
The RPN is fully convolutional and shares its convolutional feature maps with the downstream detection network.
B
The RPN relies on an external Selective Search module to generate its region proposals.
C
At each sliding-window location, the RPN predicts objectness scores and box refinements relative to k predefined anchor boxes.
D
Anchors of multiple scales and aspect ratios allow the RPN to propose regions for objects of very different sizes and shapes.

Show answer

Correct answers

A
The RPN is fully convolutional and shares its convolutional feature maps with the downstream detection network.
C
At each sliding-window location, the RPN predicts objectness scores and box refinements relative to k predefined anchor boxes.
D
Anchors of multiple scales and aspect ratios allow the RPN to propose regions for objects of very different sizes and shapes.

See the whole paper Take it as a mock test

Question 27 of 31 in the IIT Madras BS Deep Learning Practice (Deep Learning Practice) End Term paper sat on 13 Sept 2026, in the May 2026 term (Deep Learning Practice 13 Sep 26 (Session 2)). It carries 2 marks.

This question was also asked in

Deep Learning Practice End Term — 13 Sept 2026, Set S2 · question 27

Question 27: Which of the following statements correctly describe the…

Question 27

This question was also asked in

More questions from this paper