[FR] Add mean average recall (mAR) to evaluate_detections

[NicDionne]

Proposal Summary

In a few sentences, provide a clear, high-level description of the feature request. I propose to add a parameter to evaluate_detections. In the same way we can set compute_mAP=True, we should be able to set compute_mAR = True.

Motivation

• What is the use case for this feature?
• It is said that fiftyone evaluate using the COCO evaluation protocol https://cocodataset.org/#detection-eval. But this evaluation protocol also expose the mAR.
• Why is this use case valuable to support for FiftyOne users in general?
• mAR is a metric used in multiple contexts for evaluation.
• Why is this use case valuable to support for your project(s) or organization?
• This would facilate the use of Fiftyone to evaluate detections.

What areas of FiftyOne does this feature affect?

• [ ] App: FiftyOne application
• [x] Core: Core fiftyone Python library
• [ ] Server: FiftyOne server

Details

Use this section to include any additional information about the feature. If you have a proposal for how to implement this feature, please include it here.

Willingness to contribute

The FiftyOne Community welcomes contributions! Would you or another member of your organization be willing to contribute an implementation of this feature?

• [ ] Yes. I can contribute this feature independently
• [x] Yes. I would be willing to contribute this feature with guidance from the FiftyOne community
• [ ] No. I cannot contribute this feature at this time