排序熵最小化用于持续测试时适应
Ranked Entropy Minimization for Continual Test-Time Adaptation
AI总结：
针对持续测试时适应中熵最小化导致的模型崩溃问题，提出排序熵最小化，通过渐进掩蔽策略保持熵排序，提升稳定性，并在多个基准上验证有效性。
摘要：
测试时适应旨在通过在测试期间学习，以在线方式适应现实环境。熵最小化因其高效性和适应性，已成为测试时适应的主要策略。然而，在持续测试时适应中，稳定性更为重要，而熵最小化在该场景下仍未得到充分探索。我们观察到，熵最小化方法常常遭受模型崩溃，即由于平凡解，模型收敛到对所有图像预测单一类别。我们提出排序熵最小化，以缓解熵最小化方法的稳定性问题，并将其适用性扩展到连续场景。我们的方法通过渐进掩蔽策略显式地结构化预测难度。具体而言，它逐步对齐模型在不同预测难度级别上的概率分布，同时保持熵的排序顺序。所提方法在多个基准上进行了广泛评估，实证结果证明了其有效性。我们的代码可在 https://github.com/pilsHan/rem 获取。
英文摘要：
Test-time adaptation aims to adapt to realistic environments in an online manner by learning during test time. Entropy minimization has emerged as a principal strategy for test-time adaptation due to its efficiency and adaptability. Nevertheless, it remains underexplored in continual test-time adaptation, where stability is more important. We observe that the entropy minimization method often suffers from model collapse, where the model converges to predicting a single class for all images due to a trivial solution. We propose ranked entropy minimization to mitigate the stability problem of the entropy minimization method and extend its applicability to continuous scenarios. Our approach explicitly structures the prediction difficulty through a progressive masking strategy. Specifically, it gradually aligns the model's probability distributions across different levels of prediction difficulty while preserving the rank order of entropy. The proposed method is extensively evaluated across various benchmarks, demonstrating its effectiveness through empirical results. Our code is available at https://github.com/pilsHan/rem
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。
