基于离群标签暴露的零样本分布外检测
Zero-Shot Out-of-Distribution Detection with Outlier Label Exposure
AI总结：
本文提出 Outlier Label Exposure (OLE) 方法，利用辅助离群类别标签作为伪OOD文本提示增强CLIP的零样本分布外检测，并通过离群原型学习与生成模块解决标签噪声与决策区域不可分问题，在大规模OOD检测基准上取得最先进性能。
摘要：
随着像 CLIP 这样的视觉-语言模型被广泛应用于零样本任务，并在分布内（ID）数据上取得卓越性能，在零样本设置下检测并拒绝分布外（OOD）输入对于确保此类模型实时使用的安全性变得至关重要。大多数现有的零样本 OOD 检测器依赖基于 ID 类别标签的提示来指导 CLIP 分类 ID 图像并拒绝 OOD 图像。在本工作中，我们提出利用大量多样化的辅助离群类别标签作为伪 OOD 类别文本提示输入给 CLIP，以增强零样本 OOD 检测，这种方法被称为 Outlier Label Exposure (OLE)。其核心直觉是，ID 图像与这些离群类别提示的相似度预期低于 OOD 图像。一个问题在于，原始类别标签通常包含噪声标签，例如 ID 标签的同义词，导致基于原始 OLE 的检测无效。为解决此问题，我们引入了离群原型学习模块，利用离群标签的提示嵌入学习少量关键离群原型，用于基于嵌入相似度的 OOD 评分。此外，离群类别及其原型与 ID 类别可能松散耦合，导致它们之间出现不可分的决策区域。因此，我们还引入了离群标签生成模块，合成离群原型与 ID 类别嵌入以生成中间离群原型，进一步校准 OLE 中的检测。尽管方法简单，大量实验表明 OLE 显著提升了检测性能，并在大规模 OOD 和困难 OOD 检测基准上取得了新的最先进性能。
英文摘要：
As vision-language models like CLIP are widely applied to zero-shot tasks and gain remarkable performance on in-distribution (ID) data, detecting and rejecting out-of-distribution (OOD) inputs in the zero-shot setting have become crucial for ensuring the safety of using such models on the fly. Most existing zero-shot OOD detectors rely on ID class label-based prompts to guide CLIP in classifying ID images and rejecting OOD images. In this work we instead propose to leverage a large set of diverse auxiliary outlier class labels as pseudo OOD class text prompts to CLIP for enhancing zero-shot OOD detection, an approach we called Outlier Label Exposure (OLE). The key intuition is that ID images are expected to have lower similarity to these outlier class prompts than OOD images. One issue is that raw class labels often include noise labels, e.g., synonyms of ID labels, rendering raw OLE-based detection ineffective. To address this issue, we introduce an outlier prototype learning module that utilizes the prompt embeddings of the outlier labels to learn a small set of pivotal outlier prototypes for an embedding similarity-based OOD scoring. Additionally, the outlier classes and their prototypes can be loosely coupled with the ID classes, leading to an inseparable decision region between them. Thus, we also introduce an outlier label generation module that synthesizes our outlier prototypes and ID class embeddings to generate in-between outlier prototypes to further calibrate the detection in OLE. Despite its simplicity, extensive experiments show that OLE substantially improves detection performance and achieves new state-of-the-art performance in large-scale OOD and hard OOD detection benchmarks.
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。
