Non-maximum suppression in PyTorch - Cheat Sheet & Quick Revision

Recall & Review

beginner

What is Non-maximum Suppression (NMS) in object detection?

NMS is a technique to remove duplicate bounding boxes by keeping only the box with the highest confidence score and discarding others that overlap too much with it.

beginner

Why do we need Non-maximum Suppression in object detection?

Because object detectors often predict many overlapping boxes for the same object, NMS helps keep only the best box to avoid multiple detections of the same object.

intermediate

What is the role of the IoU (Intersection over Union) threshold in NMS?

The IoU threshold decides how much overlap is allowed between boxes. Boxes with IoU above this threshold are considered duplicates and suppressed.

intermediate

How does PyTorch implement Non-maximum Suppression?

PyTorch provides a function torchvision.ops.nms(boxes, scores, iou_threshold) that returns indices of boxes to keep after applying NMS.

intermediate

What happens if the IoU threshold in NMS is set too low or too high?

If too low, many boxes are removed, possibly missing some objects. If too high, many overlapping boxes remain, causing duplicate detections.

What does Non-maximum Suppression primarily remove?

A Background pixels

B Low confidence scores

C Small objects

D Duplicate bounding boxes with high overlap

NMS removes duplicate bounding boxes that overlap too much, keeping only the one with the highest confidence.

In PyTorch, which function is used for Non-maximum Suppression?

A torchvision.ops.nms()

B torch.ops.torchvision.nms()

C torch.nms()

D torch.nn.NMS()

The correct PyTorch function is torchvision.ops.nms() to perform Non-maximum Suppression.

What does the IoU threshold control in NMS?

A Maximum allowed overlap between boxes

B Number of boxes to keep

C Size of the bounding box

D Minimum confidence score to keep a box

IoU threshold controls the maximum allowed overlap between boxes before one is suppressed.

If the IoU threshold is set very high, what is the likely effect?

A More boxes are removed

B More duplicate boxes remain

C No boxes are removed

D Only the smallest boxes remain

A high IoU threshold means boxes can overlap a lot before suppression, so more duplicates remain.

Which metric is used to measure overlap between bounding boxes in NMS?

A Cosine similarity

B Euclidean distance

C Intersection over Union (IoU)

D Manhattan distance

IoU measures the overlap area divided by the union area of two boxes, used in NMS.

Explain how Non-maximum Suppression works and why it is important in object detection.

Think about how multiple boxes can cover the same object and how NMS helps keep only the best one.

Describe how to use PyTorch's NMS function including its inputs and outputs.

Consider what information you need to give the function and what you get back.