Performance Analysis
Appendix: Boosting Out-of-distribution Detection with Typical Features A Type I error and type II error in OOD detection
In the literature on OOD detection, the type II error is also denoted by "FPR
Supplementary Material for " Label-Imbalanced
Classical methods, such as weighted cross-entropy, fail when training deep nets to the terminal phase of training (TPT), that is training beyond zero training error.
AutoMS: Automatic Model Selection for Novelty Detection with Error Rate Control
Given an unsupervised novelty detection task on a new dataset, how can we automatically select a "best" detection model while simultaneously controlling the
An Infinite-Feature Extension for Bayesian ReLU Nets That Fixes Their Asymptotic Overconfidence
While this may seem of mostly theoretical interest, in this work, we show that it can be used in practice to the benefit of BNNs.
Appendix: Explainable Semantic Space by Grounding Language to Vision with Cross-Modal Contrastive Learning Yizhen Zhang
The result of PC 2 vs. PC 3 (Figure 1) suggests that the first quadrant represents concepts describing
