The model scored poorly after annotating the "detection adjustment" code

[Conearth]

Hi, this is an amazing job.
Here I come across a small problem.
On MSL dataset, the model performed good, looks like:
======================TEST MODE====================== Threshold : 0.0017330783803481142 pred: (73700,) gt: (73700,) pred: (73700,) gt: (73700,) Accuracy : 0.9853, Precision : 0.9161, Recall : 0.9473, F-score : 0.9314

But after I annotated the "detection adjustment" code, the score was poorly, looks like:
======================TEST MODE====================== Threshold : 0.0017330783803481142 pred: (73700,) gt: (73700,) pred: (73700,) gt: (73700,) Accuracy : 0.8866, Precision : 0.1120, Recall : 0.0109, F-score : 0.0199

And I'm sure only the "detection adjustment" code was annotated.

Can you help me out of this problem?
thx.

[wuhaixu2016]

Thanks for your interest.

• We have especially clarified this in the paper (Section 4 Implementation details).

• It is notable that the adjustment operation is widely used in previous papers. Thus, we adopt this for a fair comparison with other methods.

[Conearth]

Thank you very much for your attention. In your experiment, do the reconstruction based methods compared in the article use the same adjustment strategy?

[wuhaixu2016]

Sure, all the comparing methods adopt this adjustment strategy for evaluation.

[Conearth]

That's good. Thx.