[论文解读] A Unified Survey on Anomaly, Novelty, Open-Set, and Out-of-Distribution Detection: Solutions and Future Challenges

Mohammadreza Salehi, Hossein Mirzaei+4 more|arXiv (Cornell University)|Oct 26, 2021

Anomaly Detection Techniques and Applications被引用 87

一句话总结

一个跨领域的、全面的综述，连接异常检测、新颖性检测、开放集识别和分布外检测，详细描述常见方法、关系及未来研究方向。

ABSTRACT

Machine learning models often encounter samples that are diverged from the training distribution. Failure to recognize an out-of-distribution (OOD) sample, and consequently assign that sample to an in-class label significantly compromises the reliability of a model. The problem has gained significant attention due to its importance for safety deploying models in open-world settings. Detecting OOD samples is challenging due to the intractability of modeling all possible unknown distributions. To date, several research domains tackle the problem of detecting unfamiliar samples, including anomaly detection, novelty detection, one-class learning, open set recognition, and out-of-distribution detection. Despite having similar and shared concepts, out-of-distribution, open-set, and anomaly detection have been investigated independently. Accordingly, these research avenues have not cross-pollinated, creating research barriers. While some surveys intend to provide an overview of these approaches, they seem to only focus on a specific domain without examining the relationship between different domains. This survey aims to provide a cross-domain and comprehensive review of numerous eminent works in respective areas while identifying their commonalities. Researchers can benefit from the overview of research advances in different fields and develop future methodology synergistically. Furthermore, to the best of our knowledge, while there are surveys in anomaly detection or one-class learning, there is no comprehensive or up-to-date survey on out-of-distribution detection, which our survey covers extensively. Finally, having a unified cross-domain perspective, we discuss and shed light on future lines of research, intending to bring these fields closer together.

研究动机与目标

• 识别并阐明异常检测、新颖性检测、开放集识别和分布外检测之间的关系与共性。
• 提供跨域、统一的方法学综述，附带清晰的解释和可视化。
• 评估并基准代表性基线，为当前和未来的研究奠定扎实基础。
• 讨论聚焦于公平性、对抗鲁棒性、隐私、数据效率和可解释性的实际未来方向。

提出的方法

• 提出统一的分类与跨域桥梁，以在各领域传播思想。
• 提供所评方法的数学与可视化解释，以帮助理解。
• 使用共同的分类法，总结并比较AD、ND、OSR和OOD相关的近期深度学习方法。
• 对现有基线进行全面测试，为当前和未来的研究方向奠定基础。
• 突出未来的研究方向以及公平性、鲁棒性、隐私和可解释性等实际需求。

实验结果

研究问题

• RQ1 异常检测、新颖性检测、开放集识别和分布外检测之间有哪些联系与区别？
• RQ2 这些领域的主导方法是什么，理念如何在它们之间进行迁移？
• RQ3 存在哪些基准实践和基线，它们在跨领域任务中的表现如何？
• RQ4 实现可靠开放世界学习的关键未来挑战和必要的研究方向是什么？

主要发现

• 论文识别并阐明了AD、ND、OSR和OOD之间的关系，显示它们共享概念但长期独立研究。
• 它提供跨领域的全面方法学分析，具有清晰的理论与可视化解释。
• 它对现有基线进行了广泛测试，为当前和未来的研究方向奠定扎实基础。
• 综述概述了可行的未来研究方向，强调公平性、对抗鲁棒性、隐私、数据效率和可解释性。