mAP (mean Average Precision)

1. Introduction

mAP is a popular evaluation metric used for object detection (localisation and classification).

Object detection models such as SSD, YOLO make predictions of a bounding box and a class label.

2. True/False Positive for bounding box

For bounding box, we measure the overlap between the predicted bounding box and the ground truth bounding box IoU (intersection over union).

if the IoU value of prediction > IoU threshold, then we classify the prediction as True Positive (TF). On the other hand, if IoU value of prediction < IoU threshold, we classify it as False Positive (FP).

True or False Positive depends on IoU threshold. In the example above if using IoU threshold=0.2 then FP wil become TP.

In object detection:

True Positive: if True Positive for both classification and bounding box

False Positive: if otherwise

3. Calculate mAP

3.1 mAP

For the picture above with IoU threshold is o.5

- Average Precision (AP) is the area under the precision-recall curve.

- mAP (mean average precision) is the average of AP.

- AP is calculated for each class and averaged to get the mAP.

- The higher the score, the more accurate the model is in its detections.

The mean Average Precision or mAP score is calculated by taking the mean AP over all classes and/or overall IoU thresholds, depending on different detection challenges.

3.2 Interpolated precision

The interpolated precision, p_interp, is calculated at each recall level, r, by taking the maximum precision measured for that r.

Consider a model that predicted a dataset contains 5 apples. We collect all the predictions made for apples in all the images and rank it in descending order according to the predicted confidence level.