多任务测试时训练中同步任务行为，提升跨域泛化能力
Synchronizing Task Behavior: Aligning Multiple Tasks during Test-Time Training
- 通过预测任务间关系实现多任务自适应同步
- 在多个基准上超越现有最先进方法
- 适合需要多任务泛化的实际部署场景
将神经网络泛化到未见过的目标域是实际应用中的重大挑战。测试时训练（TTT）通过使用辅助自监督任务来缩小源域与目标域之间的分布差异，缓解域偏移问题。然而我们发现，当模型需在域偏移下执行多项任务时，传统TTT方法会出现任务行为不同步现象：某一任务达到最优性能所需的调整步骤，未必适用于其他任务。为此，我们提出一种新的TTT方法——同步任务测试时训练（S4T），实现多任务的并行处理。S4T的核心思想是：在域偏移下预测任务间关系，是实现测试时任务同步的关键。为验证该方法，我们在经典多任务基准上集成传统TTT协议进行实验。结果表明，S4T在多个基准上均优于现有最先进方法。
原文摘要 · Abstract (English)
Generalizing neural networks to unseen target domains is a significant challenge in real-world deployments. Test-time training (TTT) addresses this by using an auxiliary self-supervised task to reduce the domain gap caused by distribution shifts between the source and target. However, we find that when models are required to perform multiple tasks under domain shifts, conventional TTT methods suffer from unsynchronized task behavior, where the adaptation steps needed for optimal performance in one task may not align with the requirements of other tasks. To address this, we propose a novel TTT approach called Synchronizing Tasks for Test-time Training (S4T), which enables the concurrent handling of multiple tasks. The core idea behind S4T is that predicting task relations across domain shifts is key to synchronizing tasks during test time. To validate our approach, we apply S4T to conventional multi-task benchmarks, integrating it with traditional TTT protocols. Our empirical results show that S4T outperforms state-of-the-art TTT methods across various benchmarks.
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。