When faced with distribution shift at test time, deep neural networks often make inaccurate predictions with unreliable uncertainty estimates. While improving the robustness of neural networks is one promising approach to mitigate this issue, an appealing alternate to robustifying networks against all possible test-time shifts is to instead directly adapt them to unlabeled inputs from the particular distribution shift we encounter at test time. However, this poses a challenging question: in the standard Bayesian model for supervised learning, unlabeled inputs are conditionally independent of model parameters when the labels are unobserved, so what can unlabeled data tell us about the model parameters at test-time? In this paper, we derive a Bayesian model that provides for a well-defined relationship between unlabeled inputs under distributional shift and model parameters, and show how approximate inference in this model can be instantiated with a simple regularized entropy minimization procedure at test-time. We evaluate our method on a variety of distribution shifts for image classification, including image corruptions, natural distribution shifts, and domain adaptation settings, and show that our method improves both accuracy and uncertainty estimation.
翻译:当测试时面临分布变化时,深神经网络往往会做出不准确的预测,且不可靠的不确定性估计值不可靠。 改善神经网络的稳健性是缓解这一问题的一个有希望的办法,但针对所有可能的试验时间转移,一个使网络更加稳健的替代方法是直接调整网络以适应我们测试时遇到的特定分布变化的无标签投入。然而,这提出了一个具有挑战性的问题:在标准的贝叶斯模式中,没有标签的输入在没有观察标签时,有条件地独立于模型参数,因此,没有标签的数据能告诉我们测试时间的模型参数是什么?在本文件中,我们推出一种贝叶斯模型,该模型为分配转移和模型参数下的未标注的投入提供了一种明确界定的关系,并表明这一模型中大致的推论可以与测试时间的简单正规化最小化的最小化程序同时进行。我们评估了各种图像分类分布变化的方法,包括图像腐败、自然分布变化和域域适应设置,并表明我们的方法可以改进准确性和不确定性的估算。