Computer Vision Evaluation Metrics

The AIEX Platform Evaluation Metrics

Evaluation metrics are an essential part of evaluating algorithms. There are a variety of metrics offered by the AIEX platform to enable users to evaluate training algorithms effectively. Among them, COCO metrics are recognized by the AIEX platform as one of the most comprehensive set of evaluation metrics. To find more details about COCO metrics follow this link.

Object detectors on COCO are evaluated by these 12 metrics:

Average Precision (AP):

• AP (AP at IoU=.50:.05:.95 (primary challenge metric))
• AP_IoU=.50 (AP at IoU=.50 (PASCAL VOC metric))
• AP_IoU=.75 (AP at IoU=.75 (strict metric))

AP Across Scales:

• AP_small (AP for small objects: area < 32²)
• AP_medium (AP for medium objects: 32² < area < 96²)
• AP^large (AP for large objects: area > 96²)

Average Recall (AR):

• AR_max=1 (AR given 1 detection per image)
• AR_max=10 (AR given 10 detections per image)
• AR_max=100 (AR given 100 detections per image)

AR Across Scales:

• AR_small         (AR for small objects: area < 32²)
• AR_medium    (AR for medium objects: 32² < area < 96²)
• AR_large (AR for large objects: area > 96²)

AIEX platform metrics are shown below:

Precision = P

Recall = R

macro F1 = mF1

macro accuracy= mACC

macro recall=mR

macro precision=mP

mAP IoU-0.5 =mAP@0.5

mAP IoU-0.5:0.95 = mAP @0.5:0.95

AR IoU-0.5 = AR @0.5

AR IoU-0.5:0.95 = AR @0.5:0.95