论文标题
任务不可知和事后看不见的分布检测
Task Agnostic and Post-hoc Unseen Distribution Detection
论文作者
论文摘要
尽管最近的分布（OOD）检测，异常检测和不确定性估计任务的最新进展，但并不存在任务不合时宜的和事后的方法。为了解决此限制，我们设计了一种基于聚类的新型结合方法，称为任务不可知和事后看不见的分布检测（TAPUDD），该方法利用了从对特定任务进行训练的模型中提取的功能。它明确地包括Tap-Mahalanobis，该曲线将训练数据集的特征簇起来，并确定了所有群集的测试样本的最小摩alanobis距离。此外，我们提出了一个结合模块，该模块汇总了迭代性TAP-Mahalanobis的计算，以提供不同数量的簇，以提供可靠有效的群集计算。通过对合成和现实世界数据集进行的广泛实验，我们观察到我们的方法可以在各种任务中有效地检测出未见的样品，并与现有基线进行更好或与众不同。为此，我们消除了确定集群数量的最佳价值的必要性，并证明我们的方法对大规模分类任务更可行。
Despite the recent advances in out-of-distribution(OOD) detection, anomaly detection, and uncertainty estimation tasks, there do not exist a task-agnostic and post-hoc approach. To address this limitation, we design a novel clustering-based ensembling method, called Task Agnostic and Post-hoc Unseen Distribution Detection (TAPUDD) that utilizes the features extracted from the model trained on a specific task. Explicitly, it comprises of TAP-Mahalanobis, which clusters the training datasets' features and determines the minimum Mahalanobis distance of the test sample from all clusters. Further, we propose the Ensembling module that aggregates the computation of iterative TAP-Mahalanobis for a different number of clusters to provide reliable and efficient cluster computation. Through extensive experiments on synthetic and real-world datasets, we observe that our approach can detect unseen samples effectively across diverse tasks and performs better or on-par with the existing baselines. To this end, we eliminate the necessity of determining the optimal value of the number of clusters and demonstrate that our method is more viable for large-scale classification tasks.
