论文标题
强大的卑鄙老师进行持续和逐步的测试时间适应
Robust Mean Teacher for Continual and Gradual Test-Time Adaptation
论文作者
论文摘要
由于实践中不可避免地会在测试时间内经历域移动，因此测试时间适应（TTA）在部署后继续调整模型。最近，出现了连续和逐步测试时间适应（TTA）的区域。与标准TTA相反，连续TTA不仅考虑了一个域移动，而且考虑了一系列偏移。渐进的TTA进一步利用了某些属性随着时间的推移而逐渐发展的属性。由于在两个设置中都存在长期测试序列，因此需要解决依赖自我训练的方法的错误积累。在这项工作中，我们提出并表明，在TTA的情况下，与常用的跨凝性相比，对称的跨膜片更适合平均教师的一致性损失。通过我们对（对称）跨凝性梯度特性的分析是合理的。为了将测试特征空间靠近源域，在该源域中良好地摆姿势，对比度学习。由于应用程序的要求有所不同，因此我们解决了几个设置，包括拥有可用的源数据和更具挑战性的无源设置。我们证明了我们提出的方法“强大的卑鄙老师”（RMT）对持续且逐渐的腐败基准CIFAR10C，CIFAR100C和IMAGENET-C的有效性。我们进一步考虑ImageNet-R，并提出了一种新的连续域Net-126基准。所有基准都取得了最先进的结果。
Since experiencing domain shifts during test-time is inevitable in practice, test-time adaption (TTA) continues to adapt the model after deployment. Recently, the area of continual and gradual test-time adaptation (TTA) emerged. In contrast to standard TTA, continual TTA considers not only a single domain shift, but a sequence of shifts. Gradual TTA further exploits the property that some shifts evolve gradually over time. Since in both settings long test sequences are present, error accumulation needs to be addressed for methods relying on self-training. In this work, we propose and show that in the setting of TTA, the symmetric cross-entropy is better suited as a consistency loss for mean teachers compared to the commonly used cross-entropy. This is justified by our analysis with respect to the (symmetric) cross-entropy's gradient properties. To pull the test feature space closer to the source domain, where the pre-trained model is well posed, contrastive learning is leveraged. Since applications differ in their requirements, we address several settings, including having source data available and the more challenging source-free setting. We demonstrate the effectiveness of our proposed method 'robust mean teacher' (RMT) on the continual and gradual corruption benchmarks CIFAR10C, CIFAR100C, and Imagenet-C. We further consider ImageNet-R and propose a new continual DomainNet-126 benchmark. State-of-the-art results are achieved on all benchmarks.
