用1%参数的轻量模型复现大视觉模型的时序预测能力
OccamVTS: Distilling Vision Models to 1% Parameters for Time Series Forecasting
- 从大视觉模型中蒸馏出仅1%的关键参数用于时序预测
- 在多个数据集上以1%参数达到顶尖性能，少样本场景更优
- 通过特征对齐过滤语义噪声，避免过拟合冗余信息
时序预测在众多应用中至关重要，近期方法借助大视觉模型（LVMs）通过视觉表示捕捉时间模式。我们发现，尽管视觉模型提升预测性能，但99%的参数对时序任务无用。跨模态分析表明，时序数据与低级纹理特征匹配，而非高级语义，后者会降低预测精度。我们提出OccamVTS，一种知识蒸馏框架，仅提取LVMs中1%的预测信息，构建轻量网络。利用预训练的LVM作为教师模型，采用金字塔式特征对齐结合相关性与特征蒸馏，转移有效模式并过滤语义噪声。反直觉的是，这种激进的参数压缩通过消除对无关视觉特征的过拟合，反而提升了精度，同时保留了关键时序模式。在多个基准数据集上的大量实验表明，OccamVTS仅用1%参数即可持续实现最优性能，尤其在少样本和零样本场景表现突出。
原文摘要 · Abstract (English)
Time series forecasting is fundamental to diverse applications, with recent approaches leverage large vision models (LVMs) to capture temporal patterns through visual representations. We reveal that while vision models enhance forecasting performance, 99% of their parameters are unnecessary for time series tasks. Through cross-modal analysis, we find that time series align with low-level textural features but not high-level semantics, which can impair forecasting accuracy. We propose OccamVTS, a knowledge distillation framework that extracts only the essential 1% of predictive information from LVMs into lightweight networks. Using pre-trained LVMs as privileged teachers, OccamVTS employs pyramid-style feature alignment combined with correlation and feature distillation to transfer beneficial patterns while filtering out semantic noise. Counterintuitively, this aggressive parameter reduction improves accuracy by eliminating overfitting to irrelevant visual features while preserving essential temporal patterns. Extensive experiments across multiple benchmark datasets demonstrate that OccamVTS consistently achieves state-of-the-art performance with only 1% of the original parameters, particularly excelling in few-shot and zero-shot scenarios.
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。