CEB Improves Model Robustness
Sign Up to like & getrecommendations! Published in 2020 at "Entropy"
DOI: 10.3390/e22101081
Abstract: Intuitively, one way to make classifiers more robust to their input is to have them depend less sensitively on their input. The Information Bottleneck (IB) tries to learn compressed representations of input that are still… read more here.
Keywords: large scale; improves model; model robustness; robustness ceb ... See more keywords