Non-maximum suppression in PyTorch - Practice Problems & Coding Challenges

Challenge - 5 Problems

❓ Predict Output

intermediate

Output of PyTorch NMS with overlapping boxes

Given the following bounding boxes and scores, what indices does PyTorch's non_max_suppression (NMS) return?

PyTorch

import torch
from torchvision.ops import nms

boxes = torch.tensor([[10, 10, 20, 20], [11, 11, 21, 21], [30, 30, 40, 40]], dtype=torch.float32)
scores = torch.tensor([0.9, 0.8, 0.7])
iou_threshold = 0.5

keep_indices = nms(boxes, scores, iou_threshold)
print(keep_indices.tolist())

A [0, 2]

B [1, 2]

C [0, 1, 2]

D [2]

💡 Hint

NMS keeps the highest scoring box and removes boxes with IoU above threshold.

The first two boxes overlap with IoU > 0.5, so only the highest score box (index 0) is kept. The third box is far and kept as well.

🧠 Conceptual

intermediate

Purpose of Non-Maximum Suppression in Object Detection

What is the main purpose of applying Non-Maximum Suppression (NMS) in object detection pipelines?

A To remove duplicate detections of the same object by keeping only the highest scoring bounding box.

B To increase the number of detected objects by adding more bounding boxes.

C To randomly select bounding boxes to reduce computation.

D To resize bounding boxes to a fixed size.

💡 Hint

Think about why multiple boxes might appear around the same object.

NMS removes overlapping boxes that likely represent the same object, keeping only the one with the highest confidence score.

❓ Hyperparameter

advanced

Effect of IoU Threshold on NMS Output

If you increase the IoU threshold parameter in NMS from 0.3 to 0.7, what is the expected effect on the number of bounding boxes kept?

A All boxes will be removed.

B Fewer boxes will be kept because the suppression is more strict.

C The number of boxes kept will not change.

D More boxes will be kept because the suppression is less strict.

💡 Hint

Higher IoU threshold means boxes need to overlap more to be suppressed.

Increasing the IoU threshold means boxes must overlap more to be suppressed, so fewer boxes are removed and more are kept.

🔧 Debug

advanced

Identify the error in this NMS usage code

What error will this PyTorch code raise when running NMS?

PyTorch

import torch
from torchvision.ops import nms

boxes = torch.tensor([[10, 10, 20, 20], [15, 15, 25, 25]])
scores = [0.9, 0.8]
iou_threshold = 0.5

keep = nms(boxes, scores, iou_threshold)
print(keep)

A No error, code runs fine.

B ValueError because boxes have wrong shape.

C TypeError because scores is a list, not a tensor.

D RuntimeError because iou_threshold is not a tensor.

💡 Hint

Check the data types required by torchvision.ops.nms.

The scores argument must be a torch tensor, but here it is a Python list, causing a TypeError.

❓ Model Choice

expert

Choosing NMS variant for crowded scenes

In a crowded scene with many overlapping objects, which NMS variant is best to reduce missed detections while controlling duplicates?

A Random NMS, to randomly keep boxes and reduce duplicates.

B Soft-NMS, because it reduces scores of overlapping boxes instead of removing them outright.

C No NMS, to keep all detections regardless of overlap.

D Standard NMS, because it strictly removes all overlapping boxes above threshold.

💡 Hint

Consider methods that soften suppression to keep more true positives.

Soft-NMS reduces scores of overlapping boxes instead of removing them, which helps keep true positives in crowded scenes.