SPARNet：基于样本划分策略与抗遗忘正则化的持续测试时自适应
SPARNet: Continual Test-Time Adaptation via Sample Partitioning Strategy and Anti-Forgetting Regularization
AI总结：
本文提出SPARNet框架，通过样本划分策略区分可靠与不可靠样本，并引入抗遗忘正则化限制重要参数过度变化，以缓解持续测试时自适应中的错误累积和灾难性遗忘问题。
摘要：
测试时自适应（TTA）旨在当模型部署后遇到域变化时提升模型性能。标准TTA主要考虑目标域是静态的情况，而持续TTA需要经历一系列域变化。这带来了重大挑战，因为模型需要长期自适应，并且不知道域变化何时发生。伪标签的质量难以保证。简单自训练方法产生的噪声伪标签会导致错误累积和灾难性遗忘。在本文中，我们提出了一个名为SPARNet的新框架，它由两部分组成：样本划分策略和抗遗忘正则化。样本划分策略将样本分为两组，即可靠样本和不可靠样本。根据每组样本的特点，我们选择不同的策略来处理不同组的样本。这确保了可靠样本对模型的贡献更大。同时，不可靠样本的负面影响通过均值教师的一致性学习被消除。最后，我们引入一个正则化项来缓解灾难性遗忘问题，该正则化项可以限制重要参数发生过度变化。这一项使得网络中的参数能够长期自适应。通过在CIFAR10-C、CIFAR100-C和ImageNet-C上进行大量实验，我们在持续TTA场景下证明了所提方法的有效性。
英文摘要：
Test-time Adaptation (TTA) aims to improve model performance when the model encounters domain changes after deployment. The standard TTA mainly considers the case where the target domain is static, while the continual TTA needs to undergo a sequence of domain changes. This encounters a significant challenge as the model needs to adapt for the long-term and is unaware of when the domain changes occur. The quality of pseudo-labels is hard to guarantee. Noisy pseudo-labels produced by simple self-training methods can cause error accumulation and catastrophic forgetting. In this work, we propose a new framework named SPARNet which consists of two parts, sample partitioning strategy and anti-forgetting regularization. The sample partition strategy divides samples into two groups, namely reliable samples and unreliable samples. According to the characteristics of each group of samples, we choose different strategies to deal with different groups of samples. This ensures that reliable samples contribute more to the model. At the same time, the negative impacts of unreliable samples are eliminated by the mean teacher's consistency learning. Finally, we introduce a regularization term to alleviate the catastrophic forgetting problem, which can limit important parameters from excessive changes. This term enables long-term adaptation of parameters in the network. The effectiveness of our method is demonstrated in continual TTA scenario by conducting a large number of experiments on CIFAR10-C, CIFAR100-C and ImageNet-C.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
