TagFog：面向视觉分布外检测的文本锚点引导与伪造异常样本生成
TagFog: Textual Anchor Guidance and Fake Outlier Generation for Visual Out-of-Distribution Detection
AI总结：
针对视觉模型仅用分布内数据训练易对分布外样本过度自信的问题，提出TagFog框架，结合拼图伪造OOD样本与ChatGPT生成的ID知识文本锚点引导图像编码器训练，可适配现有后处理方法，在多个基准上取得SOTA性能。
摘要：
分布外（OOD）检测在诸多现实应用中至关重要。然而，智能模型通常仅在分布内（ID）数据上训练，导致其在将OOD数据误分类为ID类别时会出现过度自信的问题。本研究提出一种全新的学习框架，该框架利用基于简单Jigsaw（拼图）的伪造OOD数据，以及来自ID知识的ChatGPT描述的丰富语义嵌入（即“锚点”），来引导图像编码器的训练。该学习框架可灵活与现有OOD检测的后处理方法结合，在多个OOD检测基准上的大量实证评估表明，ID知识的丰富文本表示与伪造OOD知识能很好地辅助训练用于OOD检测的视觉编码器。借助该学习框架，所有基准测试均取得了全新的最优性能。代码可在https://github.com/Cverchen/TagFog 获取。
英文摘要：
Out-of-distribution (OOD) detection is crucial in many real-world applications. However, intelligent models are often trained solely on in-distribution (ID) data, leading to overconfidence when misclassifying OOD data as ID classes. In this study, we propose a new learning framework which leverage simple Jigsaw-based fake OOD data and rich semantic embeddings (`anchors') from the ChatGPT description of ID knowledge to help guide the training of the image encoder. The learning framework can be flexibly combined with existing post-hoc approaches to OOD detection, and extensive empirical evaluations on multiple OOD detection benchmarks demonstrate that rich textual representation of ID knowledge and fake OOD knowledge can well help train a visual encoder for OOD detection. With the learning framework, new state-of-the-art performance was achieved on all the benchmarks. The code is available at \url{https://github.com/Cverchen/TagFog}.
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。
