GP-Adapter: 基于高斯过程的CLIP适配器用于少样本分布外检测
GP-Adapter: Gaussian Process CLIP-Adapter for Few-Shot Out-of-Distribution Detection
AI总结：
提出GP-Adapter，一种无需训练的框架，通过高斯过程不确定性建模增强CLIP，用于少样本分类和分布外检测，无需微调骨干网络，仅依赖少量缓存和轻量超参数选择。
摘要：
我们提出GP-Adapter，一种无需训练的框架，通过高斯过程（GP）不确定性建模增强CLIP（对比语言-图像预训练），用于少样本分类和分布外（OOD）检测。虽然CLIP实现了强大的零样本识别，但它产生确定性的相似度分数，并提供有限的不确定性信息，这在分布偏移和数据稀缺情况下至关重要。GP-Adapter在冻结的CLIP嵌入之上，使用图像特征的RBF核和文本提示的线性核构建模态特定、类别级的一类GP，并融合它们的预测统计量，以生成方差感知的置信度分数用于OOD检测。该方法无需微调CLIP骨干网络，仅依赖于少量$K$样本缓存和轻量超参数选择，内存成本为$O(CK^2)$，其中$C$为类别数，$K$为样本数。在ImageNet和多个OOD基准上的实验表明，GP-Adapter提供了具有竞争力的少样本性能，并且在与提示学习基线结合时持续改进OOD检测，突出了基于GP的不确定性建模与提示学习之间的互补性。总体而言，我们的结果表明，将概率推理与大型预训练视觉-语言模型集成可以提高低数据和分布偏移场景下的可靠性。代码可在该https URL获取。
英文摘要：
We propose GP-Adapter, a training-free framework that augments CLIP (Contrastive Language-Image Pre-training) with Gaussian Process (GP) uncertainty modeling for few-shot classification and out-of-distribution (OOD) detection. While CLIP achieves strong zero-shot recognition, it yields deterministic similarity scores and offers limited uncertainty information, which is critical under distribution shift and data scarcity. GP-Adapter constructs modality-specific, class-wise one-class GPs on top of frozen CLIP embeddings using an RBF kernel for image features and a linear kernel for text prompts and fuses their predictive statistics to produce a variance-aware confidence score for OOD detection. The method requires no fine-tuning of the CLIP backbone and relies only on a small $K$-shot cache and lightweight hyperparameter selection, with memory cost scaling as $O(CK^2)$ for $C$ classes and $K$ shots. Experiments on ImageNet and multiple OOD benchmarks show that GP-Adapter provides competitive few-shot performance and consistently improves OOD detection when combined with prompt-learning baselines, highlighting the complementarity between GP-based uncertainty modeling and prompt learning. Overall, our results suggest that integrating probabilistic inference with large pre-trained vision-language models can improve reliability in low-data and distribution-shifted settings. Code is available at https://github.com/tms-byte/GP-Adapter
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。
