Showing cs.LGShow all
2 papers · 1 filter
cs.LG2024
Mining In-distribution Attributes in Outliers for Out-of-distribution Detection
Yutian Lei, Luping Ji, Pei Liu
Out-of-distribution (OOD) detection is indispensable for deploying reliable machine learning systems in real-world scenarios. Recent works, using auxiliary outliers in training, ha…
cs.LG2024
Weakly-Supervised Residual Evidential Learning for Multi-Instance Uncertainty Estimation
Pei Liu, Luping Ji
Uncertainty estimation (UE), as an effective means of quantifying predictive uncertainty, is crucial for safe and reliable decision-making, especially in high-risk scenarios. Exist…