Deep neural networks have achieved remarkable success in a variety of computer vision applications. However, there is a problem of degrading accuracy when the data distribution shifts between training and testing. As a solution of this problem, Test-time Adaptation~(TTA) has been well studied because of its practicality. Although TTA methods increase accuracy under distribution shift by updating the model at test time, using high-uncertainty predictions is known to degrade accuracy. Since the input image is the root of the distribution shift, we incorporate a new perspective on enhancing the input image into TTA methods to reduce the prediction's uncertainty. We hypothesize that enhancing the input image reduces prediction's uncertainty and increase the accuracy of TTA methods. On the basis of our hypothesis, we propose a novel method: Test-time Enhancer and Classifier Adaptation~(TECA). In TECA, the classification model is combined with the image enhancement model that transforms input images into recognition-friendly ones, and these models are updated by existing TTA methods. Furthermore, we found that the prediction from the enhanced image does not always have lower uncertainty than the prediction from the original image. Thus, we propose logit switching, which compares the uncertainty measure of these predictions and outputs the lower one. In our experiments, we evaluate TECA with various TTA methods and show that TECA reduces prediction's uncertainty and increases accuracy of TTA methods despite having no hyperparameters and little parameter overhead.

翻译：深度神经网络在多种计算机视觉应用中取得了显著成功。然而，当训练与测试之间的数据分布发生偏移时，模型的准确率会下降。作为该问题的解决方案，测试时自适应（TTA）因其实用性受到广泛研究。尽管TTA方法通过在测试阶段更新模型来提高分布偏移下的准确率，但使用高不确定性预测会降低准确率。由于输入图像是分布偏移的根源，我们融入了一种增强输入图像的新视角，以降低预测的不确定性。我们假设增强输入图像能降低预测不确定性并提升TTA方法的准确率。基于这一假设，我们提出了一种新方法：测试时增强器与分类器自适应（TECA）。在TECA中，分类模型与图像增强模型相结合，后者能将输入图像转化为更利于识别的形式，并通过现有TTA方法对二者进行更新。此外，我们发现增强图像的预测并不总是比原始图像的预测具有更低的不确定性。因此，我们提出了逻辑切换方法，通过比较两者预测的不确定性测度并输出较低者。在实验中，我们结合多种TTA方法评估了TECA，结果表明，尽管TECA无超参数且参数开销极小，但其能降低预测不确定性并提升TTA方法的准确率。