不需重新训练，用对数概率缩放实现跨模型高精度分布外数据检测。
Logit Scaling for Out-of-Distribution Detection
- 通过缩放模型输出的logits，区分正常数据与分布外数据。
- 在9种模型、17个数据集上达到领先性能，跨架构表现稳定。
- 无需训练数据统计，适用于已部署模型的实时检测场景。
在开放世界中安全部署机器学习与AI模型的关键在于准确识别分布外（OOD）数据，即与训练数据差异显著的样本。现有方法通常需要重新训练模型或依赖训练数据的统计信息，而这些信息可能已不可用。此外，许多方法在不同模型架构间迁移时性能下降。本文提出一种简单、事后处理的方法——对数概率缩放（Logit Scaling, LTS），无需访问训练数据分布，保持已训练网络不变，并在多种模型架构上表现出色。该方法通过调整logits，有效区分分布内（ID）与分布外（OOD）样本。我们在多个基准测试中验证，涵盖CIFAR-10、CIFAR-100、ImageNet和OpenOOD，覆盖3个ID数据集与14个OOD数据集，以及9种模型架构。结果表明，LTS在性能、鲁棒性与可移植性方面均达到当前最优水平，为通用的高级分布外检测提供可行方案。
原文摘要 · Abstract (English)
The safe deployment of machine learning and AI models in open-world settings hinges critically on the ability to detect out-of-distribution (OOD) data accurately, data samples that contrast vastly from what the model was trained with. Current approaches to OOD detection often require further training the model, and/or statistics about the training data which may no longer be accessible. Additionally, many existing OOD detection methods struggle to maintain performance when transferred across different architectures. Our research tackles these issues by proposing a simple, post-hoc method that does not require access to the training data distribution, keeps a trained network intact, and holds strong performance across a variety of architectures. Our method, Logit Scaling (LTS), as the name suggests, simply scales the logits in a manner that effectively distinguishes between in-distribution (ID) and OOD samples. We tested our method on benchmarks across various scales, including CIFAR-10, CIFAR-100, ImageNet and OpenOOD. The experiments cover 3 ID and 14 OOD datasets, as well as 9 model architectures. Overall, we demonstrate state-of-the-art performance, robustness and adaptability across different architectures, paving the way towards a universally applicable solution for advanced OOD detection.
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。