长时间尺度连续测试时自适应中的可塑性保持
Maintain Plasticity in Long-timescale Continual Test-time Adaptation
AI总结：
针对连续测试时域自适应中模型可塑性随时间下降的问题，提出基于标签翻转变化的自适应收缩-恢复策略，通过自适应间隔权重重初始化保持可塑性，在多个基准上取得优异性能。
摘要：
连续测试时域自适应（CTTA）旨在调整预训练源模型，使其在非平稳目标环境中随时间表现良好。尽管先前的方法在优化自适应过程方面做出了大量努力，但一个关键问题仍然存在：模型能否在长时间内保持可塑性以适应不断变化的环境？可塑性是指模型持续调整预测以应对非平稳环境的能力。在这项工作中，我们探索了可塑性——这一在连续自适应中至关重要但常被忽视的方面，以促进更持久的自适应。首先，我们观察到大多数CTTA方法在长时间尺度连续自适应阶段会经历稳定且一致的可塑性下降。此外，我们发现可塑性的丧失与标签翻转的变化密切相关。基于这种相关性，我们提出了一种简单而有效的策略——自适应收缩-恢复（ASR），以保持模型的可塑性。具体而言，ASR通过自适应间隔进行权重重新初始化。自适应间隔根据标签翻转的变化确定。我们的方法在广泛的CTTA基准上进行了验证，取得了优异的性能。
英文摘要：
Continual test-time domain adaptation (CTTA) aims to adjust pre-trained source models to perform well over time across non-stationary target environments. While previous methods have made considerable efforts to optimize the adaptation process, a crucial question remains: can the model adapt to continually-changing environments with preserved plasticity over a long time? The plasticity refers to the model's capability to adjust predictions in response to non-stationary environments continually. In this work, we explore plasticity, this essential but often overlooked aspect of continual adaptation to facilitate more sustained adaptation in the long run. First, we observe that most CTTA methods experience a steady and consistent decline in plasticity during the long-timescale continual adaptation phase. Moreover, we find that the loss of plasticity is strongly associated with the change in label flip. Based on this correlation, we propose a simple yet effective policy, Adaptive Shrink-Restore (ASR), towards preserving the model's plasticity. In particular, ASR does the weight re-initialization by the adaptive intervals. The adaptive interval is determined based on the change in label flipping. Our method is validated on extensive CTTA benchmarks, achieving excellent performance.
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。
