提出无需训练的时序分类新方法，提升零样本迁移性能。
Rethinking Zero-Shot Time Series Classification: From Task-specific Classifiers to In-Context Inference
- 用上下文学习替代传统分类器，一次前向传播完成预测。
- 在128个UCR数据集上表现优异，低标签场景下优势明显。
- 理论证明其可等效于训练分类器，适合零样本部署场景。
时序基础模型（TSFMs）的零样本分类通常采用冻结编码器加任务特定分类器的方式，但这种做法违背了零样本部署的无训练前提，并因分类器训练选择引入评估偏差。为此，我们提出TIC-FM，一种上下文学习框架，将标注训练集作为上下文，在不更新参数的情况下通过单次前向传播对所有测试样本进行标签预测。TIC-FM结合时序编码器与轻量级投影适配器，以及分块掩码的潜在记忆变压器。我们进一步提供理论证明：上下文推理可涵盖训练分类器，并能在单次前向传播中模拟基于梯度的分类器训练。在128个UCR数据集上的实验表明，该方法具有强准确率，尤其在极低标签情况下持续提升，验证了真正的无训练迁移能力。源代码已公开于https://github.com/fangjuntao/TIC-FM。
原文摘要 · Abstract (English)
The zero-shot evaluation of time series foundation models (TSFMs) for classification typically uses a frozen encoder followed by a task-specific classifier. However, this practice violates the training-free premise of zero-shot deployment and introduces evaluation bias due to classifier-dependent training choices. To address this issue, we propose TIC-FM, an in-context learning framework that treats the labeled training set as context and predicts labels for all test instances in a single forward pass, without parameter updates. TIC-FM pairs a time series encoder and a lightweight projection adapter with a split-masked latent memory Transformer. We further provide theoretical justification that in-context inference can subsume trained classifiers and can emulate gradient-based classifier training within a single forward pass. Experiments on 128 UCR datasets show strong accuracy, with consistent gains in the extreme low-label situation, highlighting training-free transfer for time series classification.The source code is publicly available at https://github.com/fangjuntao/TIC-FM.
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。