基于基变换的空间旋转用于免训练测试时自适应
Space Rotation with Basis Transformation for Training-free Test-Time Adaptation
AI总结:
提出免训练的基变换特征空间旋转方法,利用类别差异重构特征空间并动态队列存储样本,在多个基准上性能和效率均优于现有技术。
摘要:
随着视觉-语言模型(VLM)在下游任务应用中的发展,基于VLM的测试时自适应方法因其能够应对测试时分布变化的能力而受到越来越多的关注。尽管先前的方法已取得一定进展,但它们通常要么需要大量的计算资源,要么受限于原始特征空间的局限性,从而在测试时自适应任务中效果欠佳。为解决这些挑战,我们提出了一种免训练的基于基变换的特征空间旋转方法用于测试时自适应。通过利用类别间的固有差异,我们重构原始特征空间并将其映射到新的表示,从而增强类别差异的清晰度,并在测试期间为模型提供更有效的指导。此外,为了更好地捕获各类别的相关信息,我们维护一个动态队列以存储代表性样本。在多个基准上的实验结果表明,我们的方法在性能和效率方面均优于最先进的技术。
英文摘要:
With the development of visual-language models (VLM) in downstream task applications, test-time adaptation methods based on VLM have attracted increasing attention for their ability to address changes distribution in test-time. Although prior approaches have achieved some progress, they typically either demand substantial computational resources or are constrained by the limitations of the original feature space, rendering them less effective for test-time adaptation tasks. To address these challenges, we propose a training-free feature space rotation with basis transformation for test-time adaptation. By leveraging the inherent distinctions among classes, we reconstruct the original feature space and map it to a new representation, thereby enhancing the clarity of class differences and providing more effective guidance for the model during testing. Additionally, to better capture relevant information from various classes, we maintain a dynamic queue to store representative samples. Experimental results across multiple benchmarks demonstrate that our method outperforms state-of-the-art techniques in terms of both performance and efficiency.
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。