REVIEW 6 cited by
VisionTS: Visual Masked Autoencoders Are Free-Lunch Zero-Shot Time Series Forecasters
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
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.
Forward citations
Cited by 6 Pith papers
-
TSRouter: Dynamic Modality-Model Selection for Time Series Reasoning
A heterogeneous-graph router jointly selects the optimal modality (text, vision, or both) and model per time series query, beating prior routing baselines and generalizing to unseen models and tasks.
-
Time Series Representations for Classification Lie Hidden in Pretrained Vision Transformers
Frozen vision transformers, applied to image representations of time series, produce classification features that outperform or match time series foundation models on UCR and UEA benchmarks.
-
BLAST: Balanced Sampling Time Series Corpus for Universal Forecasting Models
A balanced sampling strategy over statistically characterized time series patterns lets universal forecasting models train on 78 billion tokens instead of 419 billion, with equal or better zero-shot accuracy.
-
Output Scaling: YingLong-Delayed Chain of Thought in a Large Pretrained Time Series Forecasting Model
Forecasting with a non-causal encoder-only model improves fixed-horizon accuracy when the model is asked to output extra future tokens, an effect the authors call delayed chain-of-thought.
-
Harnessing Vision Models for Time Series Analysis: A Survey
A survey organizing existing methods that encode time series as images and apply vision models, with a dual-view taxonomy of imaging and modeling approaches.
-
Towards Measuring and Modeling Geometric Structures in Time Series Forecasting via Image Modality
A new image-based similarity metric (TGSI) and a three-part training loss (SATL) that together aim to improve the geometric fidelity of time series forecasts.
Discussion (0). Continue with ORCID to comment.