无需额外数据，让模型自适应分布偏移。
IT$^3$: Idempotent Test-Time Training
- 通过强制推理过程重复应用结果不变（幂等性），替代传统需设计辅助任务的测试时训练。
- 在图像分类、飞行器气动预测等任务中，性能显著优于现有方法。
- 适用于多种模型架构，适合实际部署中应对未知分布变化的场景。
深度学习模型在真实场景中常因训练与测试数据分布差异而表现不佳。现有方法如领域自适应和测试时训练（TTT）虽提供部分解决方案，但通常需额外数据或特定领域辅助任务。本文提出幂等性测试时训练（IT$^3$），仅用当前测试样本即可实现即时适应，无需任何辅助任务设计。核心思想是：通过强制模型在推理中反复应用结果保持一致（即幂等性），可替代以往方法中的领域特定辅助任务。理论上，幂等性与预测置信度相关，我们证明在推理过程中最小化模型连续输出间的距离，能提升分布外性能。跨多个领域（图像分类、气动预测、航拍分割）和多种架构（MLPs、CNNs、GNNs）的实验表明，IT$^3$持续优于现有方法，且更简单、适用范围更广。结果表明，幂等性为测试时自适应提供了普适原则，可泛化至不同领域与模型结构。
原文摘要 · Abstract (English)
Deep learning models often struggle when deployed in real-world settings due to distribution shifts between training and test data. While existing approaches like domain adaptation and test-time training (TTT) offer partial solutions, they typically require additional data or domain-specific auxiliary tasks. We present Idempotent Test-Time Training (IT$^3$), a novel approach that enables on-the-fly adaptation to distribution shifts using only the current test instance, without any auxiliary task design. Our key insight is that enforcing idempotence -- where repeated applications of a function yield the same result -- can effectively replace domain-specific auxiliary tasks used in previous TTT methods. We theoretically connect idempotence to prediction confidence and demonstrate that minimizing the distance between successive applications of our model during inference leads to improved out-of-distribution performance. Extensive experiments across diverse domains (including image classification, aerodynamics prediction, and aerial segmentation) and architectures (MLPs, CNNs, GNNs) show that IT$^3$ consistently outperforms existing approaches while being simpler and more widely applicable. Our results suggest that idempotence provides a universal principle for test-time adaptation that generalizes across domains and architectures.
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。