arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2207.13083cs.LGcs.AIcs.CV
收藏

任务无关和事后不可见分布检测

Task Agnostic and Post-hoc Unseen Distribution Detection

KAIST(韩国科学技术院);University of Wisconsin-Madison(威斯康星大学麦迪逊分校)

Radhika Dua, Seongjun Yang, Yixuan Li, Edward Choi

摘要:

尽管最近在分布外(OOD)检测、异常检测和不确定性估计任务方面取得了进展,但不存在任务不可知和事后方法。为了解决这一限制,我们设计了一种新的基于聚类的集成方法,称为任务不可知和事后不可见分布检测(TAPUDD),该方法利用从特定任务训练的模型中提取的特征。它由TAP-Mahalanobis组成,它对训练数据集的特征进行聚类,并确定测试样本与所有聚类的最小Mahalanobis距离。此外,我们提出了Ensembling模块,聚合不同数量的集群的迭代TAP-Mahalanobis的计算,以提供可靠和高效的集群计算。通过对合成数据集和真实数据集的广泛实验,我们观察到我们的方法可以在不同的任务中有效地检测看不见的样本,并且表现得更好或与现有基线相当。为此,我们消除了确定聚类数的最佳值的必要性,并证明了我们的方法对于大规模分类任务更可行。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑