Exploring Simple, High Quality Out-of-Distribution Detection with L2 Normalization
CoRR(2023)
摘要
We demonstrate that L2 normalization over feature space can produce capable
performance for Out-of-Distribution (OoD) detection for some models and
datasets. Although it does not demonstrate outright state-of-the-art
performance, this method is notable for its extreme simplicity: it requires
only two addition lines of code, and does not need specialized loss functions,
image augmentations, outlier exposure or extra parameter tuning. We also
observe that training may be more efficient for some datasets and
architectures. Notably, only 60 epochs with ResNet18 on CIFAR10 (or 100 epochs
with ResNet50) can produce performance within two percentage points (AUROC) of
several state-of-the-art methods for some near and far OoD datasets. We provide
theoretical and empirical support for this method, and demonstrate viability
across five architectures and three In-Distribution (ID) datasets.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要