用文本锚点和假异常数据提升图像模型对未知样本的识别能力
TagFog: Textual Anchor Guidance and Fake Outlier Generation for Visual Out-of-Distribution Detection
- 引入基于拼图的假异常数据和ChatGPT生成的语义锚点
- 在多个基准上达到新最好性能，显著提升检测准确率
- 可无缝集成现有方法，适合需要鲁棒性部署的场景
分布外（OOD）检测在实际应用中至关重要。然而，模型通常仅在分布内（ID）数据上训练，导致对OOD样本产生过度自信。本文提出一种新学习框架，利用简单的拼图式假OOD数据和来自ChatGPT对ID知识描述的丰富语义嵌入（即‘锚点’），引导图像编码器训练。该框架可灵活结合现有事后OOD检测方法，在多个基准上进行广泛实验验证，结果表明：丰富的ID知识文本表示与假OOD知识能有效提升视觉编码器的OOD检测能力。使用该框架后，所有基准均达到新最优性能。代码已开源。
原文摘要 · Abstract (English)
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}.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。