通过动态样本选择进行持续测试时域自适应
Continual Test-time Domain Adaptation via Dynamic Sample Selection
AI总结：
本文提出了一种用于持续测试时域自适应的动态样本选择（DSS）方法，通过动态阈值筛选低质量样本并结合正负向学习降低伪标签噪声影响，在图像和3D点云域均取得优于现有技术的效果。
摘要：
持续测试时域自适应（CTDA）的目标是在不访问源数据的情况下，逐步使预训练模型适应一系列目标域。本文提出了一种用于CTDA的动态样本选择（DSS）方法。DSS由动态阈值设定、正向学习和负向学习过程组成。传统上，模型从无标签的未知环境数据中学习，并通过自训练平等地依赖所有样本的伪标签来更新其参数。然而，这些伪标签中存在噪声预测，因此并非所有样本都同等可信。因此，在我们的方法中，首先设计了一个动态阈值模块，以从高质量样本中筛选出疑似低质量样本。所选的低质量样本更有可能被错误预测。因此，我们对高质量和低质量样本均应用联合正负向学习，以降低使用错误信息的风险。我们进行了大量实验，证明了我们提出的方法在图像域CTDA中的有效性，并超越了最先进的结果。此外，我们的方法还在3D点云域进行了评估，展示了其多功能性及更广泛应用的潜力。
英文摘要：
The objective of Continual Test-time Domain Adaptation (CTDA) is to gradually adapt a pre-trained model to a sequence of target domains without accessing the source data. This paper proposes a Dynamic Sample Selection (DSS) method for CTDA. DSS consists of dynamic thresholding, positive learning, and negative learning processes. Traditionally, models learn from unlabeled unknown environment data and equally rely on all samples' pseudo-labels to update their parameters through self-training. However, noisy predictions exist in these pseudo-labels, so all samples are not equally trustworthy. Therefore, in our method, a dynamic thresholding module is first designed to select suspected low-quality from high-quality samples. The selected low-quality samples are more likely to be wrongly predicted. Therefore, we apply joint positive and negative learning on both high- and low-quality samples to reduce the risk of using wrong information. We conduct extensive experiments that demonstrate the effectiveness of our proposed method for CTDA in the image domain, outperforming the state-of-the-art results. Furthermore, our approach is also evaluated in the 3D point cloud domain, showcasing its versatility and potential for broader applicability.
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。
