How to calculate the mean +/- standard deviation

[CNing715]

Thanks for your great work.

I have a question and need your help.
How to calculate the mean +/- standard deviation (like 80.43±0.72) in "Table 1: Test accuracy (%) on RAF-DB, FER2013 and AffectNet with synthetic noisy labels."?
Is it to record the maximum accuracy in each experiment, and then calculate the mean and standard deviation of multiple experiments?

Hope to hear from you soon. TQ

[zyh-uaiaaaa]

When learning with noisy labels, you could simply record the test accuracy after the last epoch of training or record the mean test accuracy of the last several epochs. We run experiments three times to get three accuracy values and then compute the mean and standard deviation of them.

[CNing715]

Many thanks for your reply. I now have another question and need your help.

I used the experimental setting mentioned in your RUL paper to reproduce the experiment on fer2013, but the accuracy rate can only reach about 68%. What do you think might be the reason?