2 papers
cs.LG2022
XOOD: Extreme Value Based Out-Of-Distribution Detection For Image Classification
Frej Berglind, Haron Temam, Supratik Mukhopadhyay +4
Detecting out-of-distribution (OOD) data at inference time is crucial for many applications of machine learning. We present XOOD: a novel extreme value-based OOD detection framewor…
stat.ML2018
Improving robustness of classifiers by training against live traffic
Kumar Sricharan, Kumar Kallurupalli, Ashok Srivastava
Deep learning models are known to be overconfident in their predictions on out of distribution inputs. This is a challenge when a model is trained on a particular input dataset, bu…