论文标题
协方差感知功能对齐，并具有预计的源统计信息，以适应多个图像损坏
Covariance-aware Feature Alignment with Pre-computed Source Statistics for Test-time Adaptation to Multiple Image Corruptions
论文作者
论文摘要
现实世界图像识别系统通常面临损坏的输入图像，这会导致分布变化并降低模型的性能。这些系统通常在中央服务器中使用单个预测模型，并从各种环境中发送的过程图像，例如分布在城市或汽车中的相机。这样的单个模型在测试时间面临以异质方式损坏的图像。因此，他们需要在测试过程中立即适应多个腐败，而不是以高成本进行重新训练。旨在在不访问培训数据集的情况下调整模型的测试时间适应（TTA）是可以解决此问题的设置之一。现有的TTA方法确实在单个腐败方面很好地工作。但是，当发生多种类型的腐败时，适应能力受到限制，这更现实。我们假设这是因为分配转移更加复杂，并且在多次腐败的情况下，适应变得更加困难。实际上，我们通过实验发现，TTA之后存在较大的分布差距。为了解决测试期间的分布差距，我们提出了一种新型的TTA方法，称为协方差感知特征对齐（CAFE）。我们从经验上表明，咖啡馆在图像损坏（包括多种类型的损坏）上的先验tta方法优于先前的TTA方法。
Real-world image recognition systems often face corrupted input images, which cause distribution shifts and degrade the performance of models. These systems often use a single prediction model in a central server and process images sent from various environments, such as cameras distributed in cities or cars. Such single models face images corrupted in heterogeneous ways in test time. Thus, they require to instantly adapt to the multiple corruptions during testing rather than being re-trained at a high cost. Test-time adaptation (TTA), which aims to adapt models without accessing the training dataset, is one of the settings that can address this problem. Existing TTA methods indeed work well on a single corruption. However, the adaptation ability is limited when multiple types of corruption occur, which is more realistic. We hypothesize this is because the distribution shift is more complicated, and the adaptation becomes more difficult in case of multiple corruptions. In fact, we experimentally found that a larger distribution gap remains after TTA. To address the distribution gap during testing, we propose a novel TTA method named Covariance-Aware Feature alignment (CAFe). We empirically show that CAFe outperforms prior TTA methods on image corruptions, including multiple types of corruptions.
