Image Foundation Models Prove Effective for Time-Series Analysis

iScienceLuvr · x · 2026-07-11

At an ICML workshop, the author discovered a paper based on a classic idea from the 2017-2018 fastai community: visualizing time-series data as images and fine-tuning a ResNet, but updated to use modern image foundation models.

The paper's results show that this approach performs exceptionally well on CLIP and DINOv2. However, the key isn't the final output layer, but rather using the models' intermediate representations for time-series analysis. The author finds this discovery highly intriguing.

Original post →

More from Multimodal

Multimodal channel →