两篇新研究论文提出了改进预训练视觉语言模型（VLMs）中分布外（OOD）检测的新方法。其中一篇论文通过直接在视觉特征空间中学习类别原型来解决“模态差距”问题，挑战了使用文本嵌入的常见做法。另一篇论文则通过开发一个理论框架来纠正从无标签数据中挖掘负标签时的采样偏差，旨在缓解假阴性问题，从而增强OOD检测能力。 AI
影响 这些方法旨在通过更好地识别意外输入来提高AI模型的可靠性，这对于在现实世界场景中的安全部署至关重要。
排序理由 该集群包含两篇在arXiv上发表的学术论文，详细介绍了AI模型的新研究方法。
AI 生成摘要 · Google Gemini · 来自 4 个来源。 我们如何撰写摘要 →
arXiv:2605.26661v1 Announce Type: cross Abstract: Out-of-distribution (OOD) detection has emerged as a popular technique to enhance the reliability of machine learning models by identifying unexpected inputs from unknown classes. Recent progress in pre-trained vision-language mod…
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…
Out-of-distribution (OOD) detection has emerged as a popular technique to enhance the reliability of machine learning models by identifying unexpected inputs from unknown classes. Recent progress in pre-trained vision-language models (VLMs) has enabled zero-shot OOD detection wit…
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…