arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2405.04759cs.CVcs.LG
收藏

基于谱归一化联合能量的多标签分布外检测

Multi-Label Out-of-Distribution Detection with Spectral Normalized Joint Energy

East China Normal University(华东师范大学);Institute of Artificial Intelligence (TeleAI), China Telecom Corp Ltd(中国电信股份有限公司人工智能研究院(TeleAI))

Yihan Mei, Xinyu Wang, Dell Zhang, Xiaoling Wang

AI总结:

针对多标签分布外检测研究不足的问题,提出谱归一化联合能量方法,通过能量函数整合标签信息并以谱归一化优化特征空间,在多数据集上实现FPR95显著降低,刷新该领域最优性能。

摘要:

在当今互联世界中,实现可靠的分布外(OOD)检测对机器学习模型而言是一项重大挑战。尽管已有大量研究针对多类OOD检测任务提出了改进方法,但针对多标签OOD检测任务的研究仍明显不足。我们提出了谱归一化联合能量(SNoJoE)方法,该方法通过具有理论依据的基于能量的函数概念,整合多个标签的特定标签信息。在训练过程中,我们采用谱归一化来管理模型的特征空间,从而提升模型的有效性和泛化能力,同时增强鲁棒性。我们的研究结果表明,将谱归一化应用于联合能量分数,能显著提升模型的OOD检测能力。我们使用PASCAL-VOC作为分布内数据集,ImageNet-22K或Texture作为分布外数据集开展OOD检测实验。实验结果显示,与此前的最优性能相比,SNoJoE在两个对应OOD数据集上的FPR95分别实现了11%和54%的相对降低,从而确立了该研究领域的新前沿水平。

英文摘要:

In today's interconnected world, achieving reliable out-of-distribution (OOD) detection poses a significant challenge for machine learning models. While numerous studies have introduced improved approaches for multi-class OOD detection tasks, the investigation into multi-label OOD detection tasks has been notably limited. We introduce Spectral Normalized Joint Energy (SNoJoE), a method that consolidates label-specific information across multiple labels through the theoretically justified concept of an energy-based function. Throughout the training process, we employ spectral normalization to manage the model's feature space, thereby enhancing model efficacy and generalization, in addition to bolstering robustness. Our findings indicate that the application of spectral normalization to joint energy scores notably amplifies the model's capability for OOD detection. We perform OOD detection experiments utilizing PASCAL-VOC as the in-distribution dataset and ImageNet-22K or Texture as the out-of-distribution datasets. Our experimental results reveal that, in comparison to prior top performances, SNoJoE achieves 11% and 54% relative reductions in FPR95 on the respective OOD datasets, thereby defining the new state of the art in this field of study.

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。

↑