Time Series Foundation models can not only make predictions, but also classify. From NXAI's perspective, this is crucial because classification plays a major role in many industrial applications. The research team examined several foundation models for this purpose, and the TiRex time series model delivers convincing performance.
In this study, we examine whether frozen pre-trained forecasting models can provide effective representations for classification. To this end, we compare different representation extraction strategies and introduce two model-agnostic embedding augmentations. Our experiments show that the best forecasting models achieve classification accuracy that matches or even surpasses that of state-of-the-art models pre-trained specifically for classification. Moreover, we observe a positive correlation between forecasting and classification performance. These findings challenge the assumption that task-specific pre-training is necessary, and suggest that learning to forecast may provide a powerful route toward constructing general-purpose time series foundation models.
