Questions tagged [non-max-suppression]

For questions about non-max suppression in the context of object detection.

Filter by
Sorted by
Tagged with
0 votes
0 answers

YOLO v1 confidence score during inference

I am studying the paper of Yolo v1. For the training part, everything is clear to me. I cannot understand how does the confidence works during the inference stage, since Pr(Object) and ground truth ...
0 votes
0 answers

At which step in faster R-CNN is non-maximum suppression performed?

At which step in faster R-CNN is non-maximum suppression performed? In some book, I have read that it is performed after passing the features through the last fully connected layers, which are located ...
  • 1
0 votes
1 answer

Avoid unintentional "merging" in cluttered object detection

I have a problem that has bothered me quite some time. With modern methods object detectors can often be accurately trained, even with small to medium sized datasets. However, there is one thing where ...
0 votes
1 answer

YOLO - does the Intersection over Union is actually a part of Non Maximum Suppresion

In the Stack Overflow thread Intersection Over Union (IOU) ground truth in YOLO they say that in YOLO actually the IoU (intersection over union) is used twice: during training to compare ground truth ...
  • 159
0 votes
1 answer

How to reject boxes inside each other with Non Max Suppression

I’m working on an object detection cnn, and having some issues with non max suppression. When I have a small box inside a large box, NMS is not rejecting the smaller, incorrect box, because its IOU is ...
  • 101
4 votes
1 answer

How does Mask R-CNN automatically output a different number of objects on the image?

Recently, I was reading Pytorch's official tutorial about Mask R-CNN. When I run the code on colab, it turned out that it automatically outputs a different number of channels during prediction. If the ...
2 votes
0 answers

How are nested bounding boxes handled in object detection (and in particular in the case of the SSD)?

The basic approach to non-maximum-suppression makes sense, but I am kind of confused about how you handle nested bounding boxes. Suppose you have two predicted boxes, with one completely enclosing ...
3 votes
1 answer

How does non-max suppression work when one or multiple bounding boxes are predicted for the same object?

My understanding of how non-max suppression works is that it suppresses all overlapping boxes that have a Jaccard overlap smaller than a threshold (e.g. 0.5). The boxes to be considered are on a ...