arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2204.05306cs.CVcs.AIcs.LG
收藏

全光谱分布外检测

Full-Spectrum Out-of-Distribution Detection

Nanyang Technological University(南洋理工大学)

Jingkang Yang, Kaiyang Zhou, Ziwei Liu

摘要:

现有的分布外(OOD)检测文献明确定义语义转变为OOD的一个标志,但没有一个共识的协变量偏移。经历协变量偏移但未经历语义变化的样本要么被排除在测试集中,要么被视为OOD,这与机器学习的主要目标相矛盾--能够泛化到训练分布之外。在本文中,我们考虑到这两种类型的转变,并引入全谱OOD(FS-OOD)检测,一个更现实的问题设置,既考虑检测语义转变和容忍协变量偏移,并设计了三个基准。这些新的基准测试具有更细粒度的分布分类(即,训练ID、协变量移位ID、近OOD和远OOD),以便更全面地评估算法的优缺点。为了解决FS-OOD检测问题,我们提出了SEM,一个简单的基于特征的语义评分函数。SEM主要由两种概率度量组成:一种是基于包含语义和非语义信息的高层特征,另一种是基于仅捕获非语义图像风格的低层特征统计。通过简单的组合,非语义部分被抵消,这在SEM中只留下语义信息,可以更好地处理FS-OOD检测。在三个新基准上的大量实验表明,SEM显著优于当前最先进的方法。我们的代码和基准测试在https://github.com/Jingkang50/OpenOOD上发布。

英文摘要:

Existing out-of-distribution (OOD) detection literature clearly defines semantic shift as a sign of OOD but does not have a consensus over covariate shift. Samples experiencing covariate shift but not semantic shift are either excluded from the test set or treated as OOD, which contradicts the primary goal in machine learning -- being able to generalize beyond the training distribution. In this paper, we take into account both shift types and introduce full-spectrum OOD (FS-OOD) detection, a more realistic problem setting that considers both detecting semantic shift and being tolerant to covariate shift; and designs three benchmarks. These new benchmarks have a more fine-grained categorization of distributions (i.e., training ID, covariate-shifted ID, near-OOD, and far-OOD) for the purpose of more comprehensively evaluating the pros and cons of algorithms. To address the FS-OOD detection problem, we propose SEM, a simple feature-based semantics score function. SEM is mainly composed of two probability measures: one is based on high-level features containing both semantic and non-semantic information, while the other is based on low-level feature statistics only capturing non-semantic image styles. With a simple combination, the non-semantic part is cancelled out, which leaves only semantic information in SEM that can better handle FS-OOD detection. Extensive experiments on the three new benchmarks show that SEM significantly outperforms current state-of-the-art methods. Our code and benchmarks are released in https://github.com/Jingkang50/OpenOOD.

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。

↑