From Images to Signals: Are Large Vision Models Useful for Time Series Analysis?

TL;DR

This study evaluates the effectiveness of Large Vision Models in time series analysis, finding they excel in classification but face limitations in forecasting, guiding future multimodal research.

Contribution

First comprehensive study assessing LVMs for time series, covering multiple models, datasets, and tasks, with detailed analysis of their strengths and limitations.

Findings

LVMs are effective for time series classification.

LVMs face challenges in forecasting accuracy.

Current LVM forecasters are limited to specific types and exhibit biases.

Abstract

Transformer-based models have gained increasing attention in time series research, driving interest in Large Language Models (LLMs) and foundation models for time series analysis. As the field moves toward multi-modality, Large Vision Models (LVMs) are emerging as a promising direction. In the past, the effectiveness of Transformer and LLMs in time series has been debated. When it comes to LVMs, a similar question arises: are LVMs truely useful for time series analysis? To address it, we design and conduct the first principled study involving 4 LVMs, 8 imaging methods, 18 datasets and 26 baselines across both high-level (classification) and low-level (forecasting) tasks, with extensive ablation analysis. Our findings indicate LVMs are indeed useful for time series classification but face challenges in forecasting. Although effective, the contemporary best LVM forecasters are limited to specific types of LVMs and imaging methods, exhibit a bias toward forecasting periods, and have limited ability to utilize long look-back windows. We hope our findings could serve as a cornerstone for future research on LVM- and multimodal-based solutions to different time series tasks.