论文标题
帐篷：通过熵最小化的完全测试时间适应
Tent: Fully Test-time Adaptation by Entropy Minimization
论文作者
论文摘要
模型必须适应测试过程中的新数据和不同的数据。在这种完全测试时间适应的情况下，模型仅具有测试数据及其自身参数。我们建议通过测试熵最小化（帐篷）适应：我们优化了通过其预测的熵来衡量的置信模型。我们的方法估计归一化统计量并优化频道仿射转换，以在每批上在线更新。帐篷减少了损坏的Imagenet和Cifar-10/100上图像分类的概括错误，并在Imagenet-C上达到了新的最新错误。帐篷处理从SVHN到MNIST/MNIST-M/USP的数字识别，从GTA到CityScapes的语义细分以及Visda-C基准测试的数字识别。这些结果是在一个测试时间优化时期实现的，而无需改变训练。
A model must adapt itself to generalize to new and different data during testing. In this setting of fully test-time adaptation the model has only the test data and its own parameters. We propose to adapt by test entropy minimization (tent): we optimize the model for confidence as measured by the entropy of its predictions. Our method estimates normalization statistics and optimizes channel-wise affine transformations to update online on each batch. Tent reduces generalization error for image classification on corrupted ImageNet and CIFAR-10/100 and reaches a new state-of-the-art error on ImageNet-C. Tent handles source-free domain adaptation on digit recognition from SVHN to MNIST/MNIST-M/USPS, on semantic segmentation from GTA to Cityscapes, and on the VisDA-C benchmark. These results are achieved in one epoch of test-time optimization without altering training.
