论文标题
通过投影规范预测分布误差
Predicting Out-of-Distribution Error with the Projection Norm
论文作者
论文摘要
我们提出了一个指标 - 投影规范 - 以预测模型在分发数据（OOD）数据上的性能，而无需访问地面真相标签。投影规范首先使用模型预测来伪标记测试样品，然后在伪标签上训练新的模型。新模型的参数与分配模型不同，预测的OOD误差就越大。从经验上讲，我们的方法在图像和文本分类任务以及跨不同网络体系结构上都优于现有方法。从理论上讲，我们将方法连接到过度参数线性模型的测试误差的界限。此外，我们发现投影规范是在对抗性实例上实现非平凡检测性能的唯一方法。我们的代码可在https://github.com/yaodongyu/projnorm上找到。
We propose a metric -- Projection Norm -- to predict a model's performance on out-of-distribution (OOD) data without access to ground truth labels. Projection Norm first uses model predictions to pseudo-label test samples and then trains a new model on the pseudo-labels. The more the new model's parameters differ from an in-distribution model, the greater the predicted OOD error. Empirically, our approach outperforms existing methods on both image and text classification tasks and across different network architectures. Theoretically, we connect our approach to a bound on the test error for overparameterized linear models. Furthermore, we find that Projection Norm is the only approach that achieves non-trivial detection performance on adversarial examples. Our code is available at https://github.com/yaodongyu/ProjNorm.
