分发外(OOD)输入可能会损害现实世界机器学习系统的性能和安全性。虽然存在许多用于OOD检测的方法,并且在具有较低分辨率和较少类别的小规模数据集上工作良好,但是很少有方法被开发用于大规模OOD检测。现有的大规模方法通常依赖于最大分类概率,例如最先进的分组softmax方法。在这项工作中,我们开发了一种新的方法,该方法基于在训练过程中学习到的标签分布来计算预测类标签的概率。我们的方法比当前最先进的方法性能更好,计算成本只有微不足道的增加。我们在$14$数据集上对我们的方法进行了评估,并在AUROC(84.2 vs 82.4)和AUPR(96.2 vs 93.7)方面取得了统计学显著的改善。
英文摘要:
Out-of-distribution (OOD) inputs can compromise the performance and safety of real world machine learning systems. While many methods exist for OOD detection and work well on small scale datasets with lower resolution and few classes, few methods have been developed for large-scale OOD detection. Existing large-scale methods generally depend on maximum classification probability, such as the state-of-the-art grouped softmax method. In this work, we develop a novel approach that calculates the probability of the predicted class label based on label distributions learned during the training process. Our method performs better than current state-of-the-art methods with only a negligible increase in compute cost. We evaluate our method against contemporary methods across $14$ datasets and achieve a statistically significant improvement with respect to AUROC (84.2 vs 82.4) and AUPR (96.2 vs 93.7).
UPLME: Uncertainty-Aware Probabilistic Language Modelling for Robust Empathy Regression
School of Electrical Engineering, Computing and Mathematical Sciences, Curtin University(电气工程、计算与数学科学学院,科廷大学);North South University(北南大学);BRAC University(布拉克大学);The Australian National University(澳大利亚国立大学);University of ÓBuda(奥布达大学)
Demographic Predictability in 3D CT Foundation Embeddings
Rice University(莱斯大学);McGovern Medical School, UTHealth Houston(德克萨斯大学休斯顿健康科学中心麦戈文医学院);Johns Hopkins University School of Medicine(约翰霍普金斯大学医学院);University of Maryland School of Medicine(马里兰大学医学院)
Automatic Cobb Angle Detection using Vertebra Detector and Vertebra Corners Regression
NepAl Applied Mathematics and Informatics Institute for Research (NAAMII)(尼泊尔应用数学与信息学研究所(NAAMII));Hospital for Advanced Medical Surgery (HAMS)(高级外科医院(HAMS))