This competition is evaluated on the **mean average precision (mAP)** at different intersection over union (IoU) thresholds. The IoU of a proposed set of object pixels and a set of true object pixels is calculated as:
$$
IoU(A, B) = \frac{A \cap B}{A \cup B}
$$
Where:
- A is the predicted mask.
- B is the ground truth mask.
The metric sweeps over a range of IoU thresholds, at each point calculating an average precision value. The threshold values range from \(0.5\) to \(0.95\) with a step size of \(0.05\):

$$
\{0.5, 0.55, 0.6, 0.65, 0.7, 0.75, 0.8, 0.85, 0.9, 0.95\}
$$

In other words, at a threshold of \(0.5\), a predicted object is considered a "hit" if its Intersection over Union (IoU) with a ground truth object is greater than \(0.5\). At each threshold value \(t\), a precision value (Precision(t))is calculated based on the number of true positives (TP), false negatives (FN), and false positives (FP) resulting from comparing the predicted object to all ground truth objects:

$$
\text{Precision}(t) = \frac{\text{TP}}{\text{TP} + \text{FP} + \text{FN}}
$$

A true positive is counted when a single predicted object matches a ground truth object with an IoU above the threshold. A false positive indicates a predicted object had no associated ground truth object. A false negative indicates a ground truth object had no associated predicted object.

The average precision (AP) of a single image is then calculated as the mean of the precision values across all IoU thresholds:

$$
\text{AP} = \frac{1}{|\text{thresholds}|} \sum_{t \in \text{thresholds}} \frac{\text{TP}_t}{\text{TP}_t + \text{FP}_t + \text{FN}_t}
$$

Lastly, the score returned by the competition metric is the mean taken over the individual average precisions of each image in the test dataset:

$$
\text{Final Score} = \frac{1}{N} \sum_{i=1}^{N} \text{AP}_i
$$

where \(N\) is the number of images in the test set.

This final mAP score will be used to rank participants' submissions in the competition. 
Participants are encouraged to develop and submit models that maximize the mAP score by improving segmentation accuracy across all IoU thresholds.