压缩模型会严重削弱其测试时自适应能力，需重新设计压缩策略。
On the Interaction Between Model Compression and Test-Time Adaptation
- 通过诊断框架分析压缩对表征表达与适应空间的影响。
- 压缩程度越高，测试时自适应性能越差，但监督微调仍保持高准确率。
- 结构化压缩限制了模型恢复能力，需兼顾可适应性设计。
部署在真实场景中的深度神经网络需兼具高效性与适应性，要求模型压缩与测试时自适应（TTA）。尽管二者分别研究充分，其交互机制仍不清晰。本文系统分析结构化压缩如何影响模型在分布偏移下的自适应能力。基于ResNet-18和ViT-Base，在CIFAR-10-C与ImageNet-C上评估多种压缩方法与标准TTA技术的组合。提出诊断框架，考察表征表达力与适应子空间兼容性。结果揭示：尽管压缩模型在监督微调下保持高准确率，其TTA性能随压缩强度增加显著下降。原因在于表征多样性降低与结构约束导致恢复能力受限。该效应强烈依赖压缩方式，凸显需设计保留适应性的压缩策略。
原文摘要 · Abstract (English)
Deep neural networks deployed in the wild must be both efficient and adaptable, requiring model compression and test-time adaptation (TTA). While both are well studied in isolation, their interaction remains poorly understood. We systematically analyze how structured compression affects a model's ability to adapt under distribution shift. Using ResNet-18 and ViT-Base on CIFAR-10-C and ImageNet-C, we evaluate multiple compression methods combined with standard TTA techniques. We introduce a diagnostic framework that examines representational expressivity and adaptation subspace compatibility. Our results reveal a consistent gap: although compressed models retain high accuracy under supervised adaptation, their TTA performance degrades significantly with increasing compression. We show that this stems from reduced representational diversity and structural constraints that limit recoverability. These effects strongly depend on the compression method, highlighting the need to design compression strategies that preserve adaptability.
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。