.
Our work shows that overconfident and inaccurate predictions of DNNs become severe in small-data regime and propose some solutions to fix it. A revised version of the paper will be available soon.
Show this thread
Thanks all for your interest in our work on “Sample Efficient Uncertainty Estimation for Deep earning”. Unfortunately, the tweeted CAT/COVID-19 teaser image has created a lot of confusion and overshadowed the actual message of the paper.
-
-
Thanks. Twitter will use this info to make your timeline better. UndoUndo
-
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.