基于类CLIP模型的分布外检测最新进展：综述
Recent Advances in Out-of-Distribution Detection with CLIP-Like Models: A Survey
AI总结：
本文针对基于CLIP等视觉-语言模型的分布外检测研究，提出一种同时考虑图像与文本模态的新分类框架，将现有方法按OOD图像是否可见和OOD文本是否已知划分为四类，并讨论了跨域集成、实际应用与理论理解等未来方向。
摘要：
分布外检测（OOD）是现实应用中的一项关键任务，它训练模型在测试阶段识别与分布内（ID）数据在分布上不同的样本。人工智能的最新进展，特别是像CLIP这样的视觉-语言模型（VLMs），通过从传统的单模态图像检测器转向多模态图像-文本检测器，彻底改变了OOD检测。这一转变激发了广泛的研究；然而，现有的分类方案（例如少样本或零样本类型）仍然仅依赖于ID图像的可获得性，遵循单模态范式。为了更好地契合CLIP的跨模态特性，我们提出了一种基于图像和文本两种模态的新分类框架。具体而言，我们根据OOD数据的视觉和文本信息在图像+文本模态中如何被利用来对现有方法进行分类，并进一步将其划分为四组：OOD图像（即异常样本）已见或未见，以及OOD文本（即可学习向量或类别名称）已知或未知，并跨越两种训练策略（即免训练或需要训练）。更重要的是，我们讨论了类CLIP OOD检测中的开放问题，并指出了未来研究的有前景方向，包括跨域集成、实际应用和理论理解。
英文摘要：
Out-of-distribution detection (OOD) is a pivotal task for real-world applications that trains models to identify samples that are distributionally different from the in-distribution (ID) data during testing. Recent advances in AI, particularly Vision-Language Models (VLMs) like CLIP, have revolutionized OOD detection by shifting from traditional unimodal image detectors to multimodal image-text detectors. This shift has inspired extensive research; however, existing categorization schemes (e.g., few- or zero-shot types) still rely solely on the availability of ID images, adhering to a unimodal paradigm. To better align with CLIP's cross-modal nature, we propose a new categorization framework rooted in both image and text modalities. Specifically, we categorize existing methods based on how visual and textual information of OOD data is utilized within image + text modalities, and further divide them into four groups: OOD Images (i.e., outliers) Seen or Unseen, and OOD Texts (i.e., learnable vectors or class names) Known or Unknown, across two training strategies (i.e., train-free or training-required). More importantly, we discuss open problems in CLIP-like OOD detection and highlight promising directions for future research, including cross-domain integration, practical applications, and theoretical understanding.
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。
