Test-time adaptation (TTA) aims to adapt a pre-trained model to a new test domain without access to source data after deployment. Existing approaches typically rely on self-training with pseudo-labels since ground-truth cannot be obtained from test data. Although the quality of pseudo labels is important for stable and accurate long-term adaptation, it has not been previously addressed. In this work, we propose DPLOT, a simple yet effective TTA framework that consists of two components: (1) domain-specific block selection and (2) pseudo-label generation using paired-view images. Specifically, we select blocks that involve domain-specific feature extraction and train these blocks by entropy minimization. After blocks are adjusted for current test domain, we generate pseudo-labels by averaging given test images and corresponding flipped counterparts. By simply using flip augmentation, we prevent a decrease in the quality of the pseudo-labels, which can be caused by the domain gap resulting from strong augmentation. Our experimental results demonstrate that DPLOT outperforms previous TTA methods in CIFAR10-C, CIFAR100-C, and ImageNet-C benchmarks, reducing error by up to 5.4%, 9.1%, and 2.9%, respectively. Also, we provide an extensive analysis to demonstrate effectiveness of our framework. Code is available at https://github.com/gist-ailab/domain-specific-block-selection-and-paired-view-pseudo-labeling-for-online-TTA.

翻译：测试时自适应（TTA）旨在使预训练模型在部署后无需访问源数据即可适应新的测试域。现有方法通常依赖于基于伪标签的自训练，因为无法从测试数据中获取真实标签。尽管伪标签的质量对于稳定和准确的长期自适应至关重要，但此前尚未得到充分解决。在本文中，我们提出DPLOT，一个简单而有效的TTA框架，包含两个组件：（1）领域特定模块选择和（2）利用配对视图图像生成伪标签。具体而言，我们选择涉及领域特定特征提取的模块，并通过熵最小化训练这些模块。在模块根据当前测试域进行调整后，我们通过平均给定测试图像及其对应的翻转镜像来生成伪标签。通过简单地使用翻转增强，我们防止了因强增强导致的域差距而造成的伪标签质量下降。实验结果表明，DPLOT在CIFAR10-C、CIFAR100-C和ImageNet-C基准测试中优于以往的TTA方法，错误率分别降低高达5.4%、9.1%和2.9%。此外，我们提供了广泛的分析以证明我们框架的有效性。代码可在https://github.com/gist-ailab/domain-specific-block-selection-and-paired-view-pseudo-labeling-for-online-TTA 获取。