提出ELogitNorm，提升分布外检测效果且不牺牲分类准确率
Enhancing Out-of-Distribution Detection with Extended Logit Normalization
- 在LogitNorm基础上加入特征距离感知损失，无需超参数调优
- 在多个基准测试中显著优于当前最佳训练方法，同时保持高分类精度
- 适合关注模型安全性的研究者与工业落地场景
分布外（OOD）检测对机器学习模型的安全部署至关重要。现有大量工作致力于设计各类打分函数以识别分布外样本，但仅有少数研究关注通过特定模型校准目标训练神经网络，这通常会牺牲预测准确率，并限制打分函数的选择。本文首次揭示了对数归一化（LogitNorm）中的特征坍塌现象，提出一种无需超参数的新范式——扩展对数归一化（ELogitNorm），在保留原方法优势的同时，显著提升多种后处理检测方法的性能。具体而言，ELogitNorm引入特征距离感知损失项，在不损害分布内（ID）分类准确率的前提下，有效增强对分布外样本的检测能力与置信度校准。在多个标准基准上的广泛实验表明，该方法在分布外检测方面超越现有最佳训练时方法，同时维持强健的分布内分类性能。代码已公开于：https://github.com/limchaos/ElogitNorm。
原文摘要 · Abstract (English)
\noindent Out-of-distribution (OOD) detection is essential for the safe deployment of machine learning models. Extensive work has focused on devising various scoring functions for detecting OOD samples, while only a few studies focus on training neural networks using certain model calibration objectives, which often lead to a compromise in predictive accuracy and support only limited choices of scoring functions. In this work, we first identify the feature collapse phenomena in Logit Normalization (LogitNorm), then propose a novel hyperparameter-free formulation that significantly benefits a wide range of post-hoc detection methods. To be specific, we devise a feature distance-awareness loss term in addition to LogitNorm, termed $\textbf{ELogitNorm}$, which enables improved OOD detection and in-distribution (ID) confidence calibration. Extensive experiments across standard benchmarks demonstrate that our approach outperforms state-of-the-art training-time methods in OOD detection while maintaining strong ID classification accuracy. Our code is available on: https://github.com/limchaos/ElogitNorm.
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。