Abstract
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.
Abstract (translated)
深度神经网络在各种计算机视觉应用中取得了显著的成功。然而，当数据分布在训练和测试之间转移时，数据分布的改变会导致模型的准确性下降。为了解决这个问题，由于其实用性，测试时间适应（TTA）方法已经得到了很好的研究。虽然TTA方法通过在测试时更新模型来增加准确性，但使用高不确定预测已知会降低准确性。由于输入图像是分布转移的根源，我们将增强输入图像的新视角纳入TTA方法中，以减少预测的不确定性。我们假设，增强输入图像会降低预测的不确定性并提高TTA方法的准确性。根据我们的假设，我们提出了一个新的方法：测试时间增强器和分类器适应（TECA）。在TECA中，将分类模型与将输入图像转换为对齐友好图像的图像增强模型相结合，并通过现有的TTA方法更新这些模型。此外，我们发现，增强后的图像的预测不确定性并不总是低于原始图像的预测不确定性。因此，我们提出了对数切换，它比较了这些预测和输出的不确定性度量，并输出较低的那个。在我们的实验中，我们用各种TTA方法评估TECA，并发现TECA通过没有超参数且参数开销较小的情况下，减少了预测的不确定性并提高了TTA方法的准确性。
URL
https://arxiv.org/abs/2403.17423
