针对少样本分布外检测的类分布内（ID-like）提示学习
ID-like Prompt Learning for Few-Shot Out-of-Distribution Detection
AI总结：
提出基于CLIP的OOD检测框架，通过发现并利用类分布内异常值进行提示学习，在少样本场景下显著提升了最具挑战性OOD样本的检测性能。
摘要：
分布外（OOD）检测方法通常利用辅助异常值来训练模型识别OOD样本，特别是从辅助异常值数据集中发现具有挑战性的异常值以改进OOD检测。然而，它们在有效区分那些与分布内（ID）数据极其相似的OOD样本（即\idlike样本）时，可能仍面临局限性。为此，我们提出了一种新颖的OOD检测框架，该框架利用CLIP从ID样本的邻近空间中发现\idlike异常值，从而帮助识别这些最具挑战性的OOD样本。接着，提出了一种提示学习框架，利用已识别的\idlike异常值进一步发挥CLIP在OOD检测中的能力。得益于强大的CLIP，我们仅需少量ID样本即可学习模型的提示，而无需暴露其他辅助异常值数据集。通过聚焦最具挑战性的\idlike OOD样本并巧妙利用CLIP的能力，我们的方法在多种真实世界图像数据集上取得了卓越的少样本学习性能（例如，在ImageNet-1k数据集的4-shot OOD检测中，与最先进的方法相比，我们的方法将平均FPR95降低了12.16%，并将平均AUROC提高了2.76%）。代码可在https://github.com/ycfate/ID-like获取。
英文摘要：
Out-of-distribution (OOD) detection methods often exploit auxiliary outliers to train model identifying OOD samples, especially discovering challenging outliers from auxiliary outliers dataset to improve OOD detection. However, they may still face limitations in effectively distinguishing between the most challenging OOD samples that are much like in-distribution (ID) data, i.e., \idlike samples. To this end, we propose a novel OOD detection framework that discovers \idlike outliers using CLIP \cite{DBLP:conf/icml/RadfordKHRGASAM21} from the vicinity space of the ID samples, thus helping to identify these most challenging OOD samples. Then a prompt learning framework is proposed that utilizes the identified \idlike outliers to further leverage the capabilities of CLIP for OOD detection. Benefiting from the powerful CLIP, we only need a small number of ID samples to learn the prompts of the model without exposing other auxiliary outlier datasets. By focusing on the most challenging \idlike OOD samples and elegantly exploiting the capabilities of CLIP, our method achieves superior few-shot learning performance on various real-world image datasets (e.g., in 4-shot OOD detection on the ImageNet-1k dataset, our method reduces the average FPR95 by 12.16\% and improves the average AUROC by 2.76\%, compared to state-of-the-art methods). Code is available at https://github.com/ycfate/ID-like.
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。
