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 2405.11337cs.CV
收藏

迈向主动学习与分布外检测的统一方法

A Unified Approach Towards Active Learning and Out-of-Distribution Detection

Technical University of Munich(慕尼黑技术大学);BMW Group(宝马集团);Sprin-D

Sebastian Schmidt, Leonard Schenk, Leo Schwinn, Stephan Günnemann

AI总结:

针对开放世界中主动学习与分布外检测分离研究的现状,提出首个统一解决方案SISOM,利用特征空间距离度量结合两者优势,在多个OpenOOD和AL基准中取得领先性能。

摘要:

在开放世界场景中应用深度学习模型时,主动学习(AL)策略对于从近乎无限的无标签数据中识别候选标签至关重要。在此背景下,鲁棒的分布外(OOD)检测机制对于处理应用目标分布之外的数据必不可少。然而,当前的研究将这两个问题分开探讨。在本研究中,我们提出了SISOM,作为首个针对AL和OOD检测的统一解决方案。通过利用特征空间距离度量,SISOM结合了当前独立任务的优势,以有效解决这两个问题。我们进行了大量实验,展示了在两个任务之间迁移时出现的问题。在评估中,SISOM突显了其有效性,在两个广泛使用的OpenOOD基准中取得第一名,在另一个基准中取得第二名。在AL中,SISOM优于其他方法,在三个基准中取得了top-1性能。

英文摘要:

When applying deep learning models in open-world scenarios, active learning (AL) strategies are crucial for identifying label candidates from a nearly infinite amount of unlabeled data. In this context, robust out-of-distribution (OOD) detection mechanisms are essential for handling data outside the target distribution of the application. However, current works investigate both problems separately. In this work, we introduce SISOM as the first unified solution for both AL and OOD detection. By leveraging feature space distance metrics SISOM combines the strengths of the currently independent tasks to solve both effectively. We conduct extensive experiments showing the problems arising when migrating between both tasks. In these evaluations SISOM underlined its effectiveness by achieving first place in two of the widely used OpenOOD benchmarks and second place in the remaining one. In AL, SISOM outperforms others and delivers top-1 performance in three benchmarks

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。

↑