测试时蒸馏用于持续模型适应
Test-Time Distillation for Continual Model Adaptation
AI总结：
本文提出CoDiRe框架，通过动态融合VLM和目标模型预测构建鲁棒教师，利用MSP缓解熵偏见，通过最优传输对齐预测，实现稳定持续适应，优于现有方法。
摘要：
深度神经网络在部署时常因分布偏移导致性能下降。持续测试时适应（CTTA）旨在无监督方式解决此问题。然而，现有依赖自监督的方法易产生自指反馈循环，放大初始预测误差。本文提出测试时蒸馏（TTD），将适应过程重新定义为由冻结视觉-语言模型（VLM）作为外部信号引导的蒸馏过程。尽管有前景，直接蒸馏面临两个问题：（1）通用陷阱，VLM的广泛但非专业知识导致特定任务表现不佳；（2）熵偏见，基于熵的简单模型融合因异质模型校准不同而失效。为解决这些问题，本文提出CoDiRe框架，构建鲁棒混合教师，利用最大softmax概率（MSP）作为更可靠的置信度度量，通过最优传输对齐预测，实现持续稳定适应。实验表明，CoDiRe优于现有方法，在ImageNet-C上仅用48%的时间成本超越CoTTA 10.55%。项目页面可在https://github.com/walawalagoose/TTD上公开获取。
英文摘要：
Deep neural networks often suffer performance degradation upon deployment due to distribution shifts. Continual Test-Time Adaptation (CTTA) aims to address this issue in an unsupervised manner. However, existing methods that rely on self-supervision are prone to an inherent self-referential feedback loop that amplifies initial prediction errors, leading to model drift. We revisit this limitation and propose Test-Time Distillation (TTD), which reframes adaptation as a distillation process guided by a frozen Vision-Language Model (VLM) as an external signal. While promising, we find that direct distillation is fraught with two pitfalls: (1) the Generalist Trap, where the VLM's broad but non-specialized knowledge leads to suboptimal performance on specific tasks and shifts; and (2) the Entropy Bias, where naive model fusion techniques based on entropy fail due to the disparate calibration of heterogeneous models. These pitfalls highlight the need to build a robust supervisory signal and leverage it to guide the target model toward stable adaptation. Hence, we present CoDiRe, a Continual Distillation and Rectification framework for TTD. CoDiRe first constructs a robust blended teacher by dynamically fusing the predictions of the VLM and the target model. Critically, it circumvents the Entropy Bias by leveraging Maximum Softmax Probability (MSP) as a more reliable confidence metric for weighting each model's expertise. Then it applies an Optimal Transport-based rectification to further align predictions with the blended teacher, enabling continuous and stable adaptation. Extensive experiments show that CoDiRe outperforms state-of-the-art baselines, exceeding CoTTA by 10.55% with only 48% of its time cost on ImageNet-C. Project page is publicly available at https://github.com/walawalagoose/TTD.
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。
