What is an intersection over union?
The intersection of two sets divided by their union.
intersection over union explained in plain English
The intersection of two sets divided by their union. In machine-learning image-detection tasks, IoU is used to measure the accuracy of the model's predicted bounding box with respect to the ground-truth bounding box. In this case, the IoU for the two boxes is the ratio between the overlapping area and the total area, and its value ranges from 0 (no overlap of predicted bounding box and ground-truth bounding box) to 1 (predicted bounding box and ground-truth bounding box have the exact same coordinates). For example, in the image below: - The predicted bounding box (the coordinates delimiting where the model predicts the night table in the painting is located) is outlined in purple. - The ground-truth bounding box (the coordinates delimiting where the night table in the painting is actually located) is outlined in green. Here, the intersection of the bounding boxes for prediction and ground truth (below left) is 1, and the union of the bounding boxes for prediction and ground truth (below right) is 7, so the IoU is \(\frac{1}{7}\).
Example
Practitioners refer to intersection over union when building, training, or evaluating machine learning systems. It appears in research papers, product documentation, and technical discussions about AI capabilities and limitations.
People also read
- autoencoder
A system that learns to extract the most important information from the input.
- bounding box
In an image, the (x, y) coordinates of a rectangle around an area of interest, such as the dog in the image below.
- convolution
In mathematics, casually speaking, a mixture of two functions.
- convolutional filter
One of the two actors in a convolutional operation.
- convolutional layer
A layer of a deep neural network in which a convolutional filter passes along an input matrix.
- convolutional neural network
A neural network in which at least one layer is a convolutional layer.
- convolutional operation
The following two-step mathematical operation: 1.
- depthwise separable convolutional neural network
A convolutional neural network architecture based on Inception, but where Inception modules are replaced with depthwise separable convolutions.
- golden dataset
A set of manually curated data that captures ground truth.
- image recognition
A process that classifies object(s), pattern(s), or concept(s) in an image.