只在必要时才更新模型，让边缘设备也能高效用上测试时自适应。
EmbodiTTA: Resource-Efficient Test-Time Adaptation for Embodied Visual Systems
- 按需触发适应，仅当检测到显著域偏移时才启动
- 在低资源下保持高精度，能耗降低超60%
- 适合部署在手机、机器人等算力受限设备
持续测试时自适应（CTTA）在每个数据批次上持续调整已部署模型，虽能实现最优准确率，但因内存开销大、能耗高，难以在资源受限的边缘设备上应用。本文提出一种新范式——按需测试时自适应（OD-TTA），仅在检测到显著域偏移时触发适应。OD-TTA包含三项创新：1）轻量级域偏移检测机制，仅在必要时激活适应，大幅降低计算开销；2）源模型选择模块，动态选取合适源模型以保证高且稳定的准确率；3）解耦批量归一化（BN）更新策略，支持小批量下的内存高效适应。大量实验表明，OD-TTA在性能相当甚至更优的同时，显著降低能耗与计算开销，使测试时自适应真正具备实用价值。
原文摘要 · Abstract (English)
Continual Test-time adaptation (CTTA) continuously adapts the deployed model on every incoming batch of data. While achieving optimal accuracy, existing CTTA approaches present poor real-world applicability on resource-constrained edge devices, due to the substantial memory overhead and energy consumption. In this work, we first introduce a novel paradigm -- on-demand TTA -- which triggers adaptation only when a significant domain shift is detected. Then, we present OD-TTA, an on-demand TTA framework for accurate and efficient adaptation on edge devices. OD-TTA comprises three innovative techniques: 1) a lightweight domain shift detection mechanism to activate TTA only when it is needed, drastically reducing the overall computation overhead, 2) a source domain selection module that chooses an appropriate source model for adaptation, ensuring high and robust accuracy, 3) a decoupled Batch Normalization (BN) update scheme to enable memory-efficient adaptation with small batch sizes. Extensive experiments show that OD-TTA achieves comparable and even better performance while reducing the energy and computation overhead remarkably, making TTA a practical reality.
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。