研究人员开发了一种新方法，以改进预训练的视觉语言模型（VLMs）的分布外（OOD）检测。该技术通过纠正采样偏差来解决识别语义上不同的负面标签的挑战。这种可转换为蒙特卡洛采样的去偏负面挖掘方法，在OOD检测设置中确立了新的最先进水平。 AI
影响 通过提高AI模型识别未知类别的意外输入的能力，增强了其可靠性。
排序理由 该集群包含一篇学术论文，详细介绍了提高机器学习模型可靠性的一种新方法。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
新方法改进了视觉语言模型的分布外检测
报道来源 [2]
-
Debiased Negative Mining Improves Out-of-distribution Detection with Pre-trained Vision-Language Models
arXiv:2605.23797v1 Announce Type: new Abstract: Aiming at identifying unexpected inputs from unknown classes, out-of-distribution (OOD) detection has emerged as a pivotal approach to enhancing the reliability of machine learning models. This paper focuses on the burgeoning paradi…
-
Debiased Negative Mining Improves Out-of-distribution Detection with Pre-trained Vision-Language Models
Aiming at identifying unexpected inputs from unknown classes, out-of-distribution (OOD) detection has emerged as a pivotal approach to enhancing the reliability of machine learning models. This paper focuses on the burgeoning paradigm of post-hoc OOD detection with pre-trained vi…