You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
LS degrades the uncertainty rank ordering of correct vs incorrect predictions by regularising the max logit more when a prediction is likely to be correct, and less when it is likely to be wrong.
208
208
This elucidates previously reported experimental results where strong classifiers underperform in SC. We then demonstrate the empirical effectiveness of post-hoc logit normalisation for recovering lost SC performance caused by LS.
209
209
Furthermore, linking back to our gradient analysis, we again provide an explanation for why such normalisation is effective. <br><br>
0 commit comments