无需反向传播的轻量级测试时自适应方法，适合边缘设备部署。
Efficient Test-Time Adaptation through Latent Subspace Coefficients Search
- 通过优化低维系数向量实现无梯度自适应，避免反向传播与内存开销。
- 在六个基准上达到顶尖性能，计算量降低63倍，内存减少11倍。
- 适用于资源受限的实时设备，已在ZYNQ-7020平台成功部署。
现实场景中模型常面临分布偏移问题，测试时自适应（TTA）对提升鲁棒性至关重要。然而，多数现有方法依赖反向传播、激活缓存或测试时小批量处理，导致延迟高、内存占用大，难以部署于边缘设备。本文提出高效无梯度测试时自适应框架ELaTTA，冻结模型权重，通过优化预计算的源域主导主成分潜空间中的低维系数向量来适应单个测试样本，该潜空间由截断SVD离线计算并以极低开销存储。推理阶段，使用CMA-ES优化k维系数，增强预测置信度，有效平滑目标函数，在决策边界附近提升稳定性。在六个基准和多种架构上，ELaTTA在严格及持续单实例协议下均达当前最优准确率，计算量最高降低63倍，峰值内存减少11倍。进一步在ZYNQ-7020平台上验证了其在设备端的可行性。
原文摘要 · Abstract (English)
Real-world deployment often exposes models to distribution shifts, making test-time adaptation (TTA) critical for robustness. Yet most TTA methods are unfriendly to edge deployment, as they rely on backpropagation, activation buffering, or test-time mini-batches, leading to high latency and memory overhead. We propose \textbf{ELaTTA} (\textit{Efficient Latent Test-Time Adaptation}), a gradient-free framework for single-instance TTA under strict on-device constraints. ELaTTA freezes model weights and adapts each test sample by optimizing a low-dimensional coefficient vector in a source-induced principal latent subspace, pre-computed offline via truncated SVD and stored with negligible overhead. At inference, ELaTTA encourages prediction confidence by optimizing the $k$-D coefficients with CMA-ES, effectively optimizing a Gaussian-smoothed objective and improving stability near decision boundaries. Across six benchmarks and multiple architectures, ELaTTA achieves state-of-the-art accuracy under both strict and continual single-instance protocols, while reducing compute by up to \emph{63$\times$} and peak memory by up to \emph{11$\times$}. We further demonstrate on-device deployment on a ZYNQ-7020 platform.
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。