Questions: Object Detection Networks

5 questions to test your understanding

Score: 0 / 5
Question 1 Multiple Choice

Two object detection systems are benchmarked: System A runs at 4 FPS with 87% mean average precision (mAP); System B runs at 50 FPS with 76% mAP. Which architectural family most likely corresponds to each?

AA: YOLO-style single-shot detector; B: Faster R-CNN two-stage detector
BA: Faster R-CNN two-stage detector; B: YOLO-style single-shot detector
CA: R-CNN with selective search; B: SSD single-shot detector
DA: sliding-window CNN classifier; B: Faster R-CNN with Feature Pyramid Network
Question 2 Multiple Choice

A detector produces 18 overlapping bounding boxes around the same cat in an image, all with varying confidence scores. What technique selects the single best prediction and discards the rest?

AFeature Pyramid Network (FPN), which merges multi-scale features into one prediction
BRegion Proposal Network (RPN), which filters out redundant proposals before classification
CNon-maximum suppression (NMS), which keeps the highest-confidence box and removes overlapping duplicates
DAnchor box matching, which assigns each object to exactly one grid cell
Question 3 True / False

In Faster R-CNN, the convolutional backbone processes the image only once, and the resulting feature map is shared between the Region Proposal Network and the classification head.

TTrue
FFalse
Question 4 True / False

Object detection is fundamentally equivalent to running an image classifier on a sliding window at nearly every possible location and scale, making it a straightforward extension of image classification.

TTrue
FFalse
Question 5 Short Answer

Explain why Feature Pyramid Networks (FPN) are used in object detection, and what problem they solve that a single feature map from the last convolutional layer cannot handle.

Think about your answer, then reveal below.