COOkeD：零样本CLIP时代下基于集成的分布外（OOD）检测
COOkeD: Ensemble-based OOD detection in the era of zero-shot CLIP
AI总结：
针对单分类器OOD检测性能受限于分布内数据能力的问题，提出融合闭世界分类器、零样本CLIP及线性探测分类器的异构集成方法COOkeD，在多基准和复杂场景下实现SOTA性能与更强鲁棒性。
摘要：
分布外（OOD）检测是可信图像识别系统的重要组成部分，因为测试阶段可能出现未知类别。OOD检测方法通常围绕单分类器展开，导致研究领域分为经典监督设置（例如在CIFAR100上训练的ResNet18分类器）与零样本设置（将类别名称作为提示输入CLIP）两大方向。两类设置下的共同核心挑战是，OOD检测性能隐性受限于分类器在分布内（ID）数据上的能力。\n本研究表明，只要对两类方法都保持一定的开放性，构建异构集成就能实现出色的OOD检测效果——COOkeD融合了三种分类器的预测结果：在特定数据集上端到端训练的闭世界分类器、零样本CLIP分类器，以及基于CLIP图像特征训练的线性探测分类器。尽管该方法乍看体量较大，但它具备模块化、事后可实现的特点，且能利用预训练视觉语言模型（VLM）的现有资源，因此与训练单个标准分类器相比，额外开销极小。\n我们在常用的CIFAR100和ImageNet基准上评估COOkeD，同时还测试了更具挑战性的真实场景，包括训练时标签噪声、测试时协变量偏移，以及此前被忽视的零样本偏移。尽管方法简单，COOkeD仍取得了当前最优性能，且相比经典OOD检测方法和基于CLIP的OOD检测方法具备更强的鲁棒性。代码可在https://github.com/glhr/COOkeD获取。
英文摘要：
Out-of-distribution (OOD) detection is an important building block in trustworthy image recognition systems as unknown classes may arise at test-time. OOD detection methods typically revolve around a single classifier, leading to a split in the research field between the classical supervised setting (e.g. ResNet18 classifier trained on CIFAR100) vs. the zero-shot setting (class names fed as prompts to CLIP). In both cases, an overarching challenge is that the OOD detection performance is implicitly constrained by the classifier's capabilities on in-distribution (ID) data. In this work, we show that given a little open-mindedness from both ends, remarkable OOD detection can be achieved by instead creating a heterogeneous ensemble - COOkeD combines the predictions of a closed-world classifier trained end-to-end on a specific dataset, a zero-shot CLIP classifier, and a linear probe classifier trained on CLIP image features. While bulky at first sight, this approach is modular, post-hoc and leverages the availability of pre-trained VLMs, thus introduces little overhead compared to training a single standard classifier. We evaluate COOkeD on popular CIFAR100 and ImageNet benchmarks, but also consider more challenging, realistic settings ranging from training-time label noise, to test-time covariate shift, to zero-shot shift which has been previously overlooked. Despite its simplicity, COOkeD achieves state-of-the-art performance and greater robustness compared to both classical and CLIP-based OOD detection methods. Code is available at https://github.com/glhr/COOkeD
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。
