Home | Publications | RBA26

Time Series Representations for Classification Lie Hidden in Pretrained Vision Transformers

MCML Authors

Abstract

Time series classification is a fundamental task in healthcare and industry, yet the development of time series foundation models (TSFMs) remains limited by the scarcity of publicly available time series datasets. In this work, we propose Time Vision Transformer (TiViT), a framework that converts time series into images to leverage the representational power of frozen Vision Transformers (ViTs) pretrained on large-scale image datasets. First, we show that the 2D patching of ViTs for time series can increase the number of label-relevant tokens and reduce the sample complexity. Second, we demonstrate that TiViT achieves state-of-the-art performance on time series classification benchmarks by utilizing the hidden representations of large OpenCLIP models. We explore the structure of TiViT representations and find that intermediate layers with high intrinsic dimension are the most effective for time series classification. Finally, we assess the alignment between TiViT and TSFM representations and identify a strong complementarity, with further performance gains achieved by combining their features.

inproceedings RBA26

BERT2S @NeurIPS 2025

Workshop on Recent Advances in Time Series Foundation Models: Have We Reached the 'BERT Moment'? at the 39th Conference on Neural Information Processing Systems. San Diego, CA, USA, Nov 30-Dec 07, 2025.

Authors

S. Roschmann • Q. Bouniot • Z. Akata

Links

URL

Research Area

 B1 | Computer Vision

BibTeXKey: RBA26

#p-akata
Back to Top