---
title: "Comment by Jam Yanh on \"Should you trust an object detector’s confidence?\" | Hashnode"
description: "Keeping the same 10,893 detections before and after correction makes the result much easier to interpret. Would you consider adding precision and retained-detec"
url: "https://hashnode.com/posts/object-detection-confidence-calibration/6ac5a141dd27d808f63b1dd3/comment/6ac641547f639fd37cd73ccf"
---

[Discussion](https://hashnode.com/posts/object-detection-confidence-calibration/6ac5a141dd27d808f63b1dd3)

Comment [Should you trust an object detector’s confidence?](https://hashnode.com/posts/object-detection-confidence-calibration/6ac5a141dd27d808f63b1dd3)

[Jam Yanh](https://hashnode.com/@danagua)

[Oct 7](https://hashnode.com/posts/object-detection-confidence-calibration/6ac5a141dd27d808f63b1dd3/comment/6ac641547f639fd37cd73ccf)

Keeping the same 10,893 detections before and after correction makes the result much easier to interpret. Would you consider adding precision and retained-detection counts at a few thresholds on the corrected scores? That would help readers choose an operating threshold without confusing better calibration with improved recall.

[Oleg Serov](https://hashnode.com/@sirserow)

[Oct 7](https://hashnode.com/posts/object-detection-confidence-calibration/6ac5a141dd27d808f63b1dd3/comment/6ac641547f639fd37cd73ccf#reply-6ac658cda2b74ab8ed82afc6)

Jam, thank you, that's a great point! I have the saved per-detection results, so it's possible report precision and retained counts at several corrected-score thresholds. I have added it to the article.

[Jam Yanh](https://hashnode.com/@danagua)

[Oct 10](https://hashnode.com/posts/object-detection-confidence-calibration/6ac5a141dd27d808f63b1dd3/comment/6ac641547f639fd37cd73ccf#reply-6aca0b55725822e0d51dcd85)

Thanks for adding the table, Oleg. Comparing the 0.90 and 0.95 rows makes the tradeoff much clearer: the extra precision comes with substantially fewer retained detections. That is much more useful for choosing a threshold than the ECE number alone.
