VisionTS: Visual Masked Autoencoders Are Free-Lunch Zero-Shot Time Series Forecasters

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Mouxiang, Shen, Lefei, Li, Zhuo, Wang, Xiaoyun Joy, Sun, Jianling, Liu, Chenghao
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908395648319488
author Chen, Mouxiang
Shen, Lefei
Li, Zhuo
Wang, Xiaoyun Joy
Sun, Jianling
Liu, Chenghao
author_facet Chen, Mouxiang
Shen, Lefei
Li, Zhuo
Wang, Xiaoyun Joy
Sun, Jianling
Liu, Chenghao
contents Foundation models have emerged as a promising approach in time series forecasting (TSF). Existing approaches either repurpose large language models (LLMs) or build large-scale time series datasets to develop TSF foundation models for universal forecasting. However, these methods face challenges due to the severe cross-domain gap or in-domain heterogeneity. This paper explores a new road to building a TSF foundation model from rich, high-quality natural images. Our key insight is that a visual masked autoencoder, pre-trained on the ImageNet dataset, can naturally be a numeric series forecaster. By reformulating TSF as an image reconstruction task, we bridge the gap between image pre-training and TSF downstream tasks. Surprisingly, without further adaptation in the time series domain, the proposed VisionTS could achieve better zero-shot forecast performance than existing TSF foundation models. With fine-tuning for one epoch, VisionTS could further improve the forecasting and achieve state-of-the-art performance in most cases. Extensive experiments reveal intrinsic similarities between images and real-world time series, suggesting that visual models may offer a "free lunch" for TSF and highlight the potential for future cross-modality research. Our code is publicly available at https://github.com/Keytoyze/VisionTS.
format Preprint
id arxiv_https___arxiv_org_abs_2408_17253
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle VisionTS: Visual Masked Autoencoders Are Free-Lunch Zero-Shot Time Series Forecasters
Chen, Mouxiang
Shen, Lefei
Li, Zhuo
Wang, Xiaoyun Joy
Sun, Jianling
Liu, Chenghao
Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
Foundation models have emerged as a promising approach in time series forecasting (TSF). Existing approaches either repurpose large language models (LLMs) or build large-scale time series datasets to develop TSF foundation models for universal forecasting. However, these methods face challenges due to the severe cross-domain gap or in-domain heterogeneity. This paper explores a new road to building a TSF foundation model from rich, high-quality natural images. Our key insight is that a visual masked autoencoder, pre-trained on the ImageNet dataset, can naturally be a numeric series forecaster. By reformulating TSF as an image reconstruction task, we bridge the gap between image pre-training and TSF downstream tasks. Surprisingly, without further adaptation in the time series domain, the proposed VisionTS could achieve better zero-shot forecast performance than existing TSF foundation models. With fine-tuning for one epoch, VisionTS could further improve the forecasting and achieve state-of-the-art performance in most cases. Extensive experiments reveal intrinsic similarities between images and real-world time series, suggesting that visual models may offer a "free lunch" for TSF and highlight the potential for future cross-modality research. Our code is publicly available at https://github.com/Keytoyze/VisionTS.
title VisionTS: Visual Masked Autoencoders Are Free-Lunch Zero-Shot Time Series Forecasters
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2408.17253