提出排序熵最小化，解决测试时持续适应中的模型坍塌问题。
Ranked Entropy Minimization for Continual Test-Time Adaptation
- 通过渐进掩码策略构建预测难度层级，保持熵的排序关系。
- 在多个基准上实现稳定适应，避免模型对所有图像预测同一类别。
- 适合需要长期在线学习的视觉系统，如自动驾驶感知模块。
测试时适应旨在通过测试阶段的学习实现对真实环境的在线适应。熵最小化因其高效与可适应性已成为测试时适应的核心策略。然而，在持续测试时适应场景中，稳定性更为关键，该方法仍缺乏深入探索。我们观察到熵最小化常导致模型坍塌——模型收敛至对所有图像预测单一类别，陷入平凡解。为此，我们提出排序熵最小化，缓解熵最小化方法的稳定性问题，并将其扩展至连续场景。该方法通过渐进掩码策略显式构建预测难度结构，逐步对齐不同难度层级下的模型概率分布，同时保留熵的排序关系。我们在多个基准上进行了广泛评估，实证结果证明了其有效性。代码已公开于 https://github.com/pilsHan/rem。
原文摘要 · Abstract (English)
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
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。