# PRISM: Powerful Time Series to Image (TS2I) Representations for Multivariate Anomaly Detection

arXiv: https://arxiv.org/abs/2608.03926 · HTML: https://mlsanity.com/paper/2608.03926/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 26 references that are in the map.
- First posted on arXiv 4 Aug 2026.

## Builds on (most cited first, 14 of 14)

- [Deep Learning for Time Series Anomaly Detection: A Survey](https://mlsanity.com/paper/2211.05244/) (2022)
- [Imaging Time-Series to Improve Classification and Imputation](https://mlsanity.com/paper/1506.00327/) (2015)
- [Time Series as Images: Vision Transformer for Irregularly Sampled Time Series](https://mlsanity.com/paper/2303.12799/) (2023)
- [A survey on efficient vision transformers: algorithms, techniques, and performance benchmarking](https://mlsanity.com/paper/2309.02031/) (2023)
- [Large Language Model Guided Knowledge Distillation for Time Series Anomaly Detection](https://mlsanity.com/paper/2401.15123/) (2024)
- [Harnessing Vision Models for Time Series Analysis: A Survey](https://mlsanity.com/paper/2502.08869/) (2025)
- [Dive into Time-Series Anomaly Detection: A Decade Review](https://mlsanity.com/paper/2412.20512/) (2024)
- [A Comprehensive Survey of Deep Transfer Learning for Anomaly Detection in Industrial Time Series: Methods, Applications, and Directions](https://mlsanity.com/paper/2307.05638/) (2023)
- [TimEHR: Image-based Time Series Generation for Electronic Health Records](https://mlsanity.com/paper/2402.06318/) (2024)
- [xLSTMAD: A Powerful xLSTM-based Method for Anomaly Detection](https://mlsanity.com/paper/2506.22837/) (2025)
- [Training-Free Time-Series Anomaly Detection: Leveraging Image Foundation Models](https://mlsanity.com/paper/2408.14756/) (2024)
- [Plotting time: On the usage of CNNs for time series classification](https://mlsanity.com/paper/2102.04179/) (2021)
- [Your time series is worth a binary image: machine vision assisted deep framework for time series forecasting](https://mlsanity.com/paper/2302.14390/) (2023)
- [Evaluating Transfer Learning Methods on Real-World Data Streams: A Case Study in Financial Fraud Detection](https://mlsanity.com/paper/2508.02702/) (2025)

## Abstract (arXiv)

Time series anomaly detection (TSAD) underpins applications in predictive maintenance, finance, and cloud computing, however performance remains sensitive to representation choices, especially in multivariate settings. While transforming time series into images has shown success in forecasting and classification, it remains unclear how multivariate, high-dimensional series should be mapped to multi-channel images and whether vision backbones can match time-domain baselines in TSAD. We introduce PRISM, a plug-and-play meta-workflow enabling systematic construction and evaluation of image-based representations for multivariate TSAD. Our evaluation spanning over 7,000 experiments shows that well-designed PRISM configurations are competitive with 24 time-domain baselines, achieving the best VUS-PR on 10 of 14 datasets, with an average improvement of 41% over the best competing method on those datasets. Further, we identify channelization - how the channel dimension of multi-channel images is constructed - as a critical and previously understudied design dimension, and introduce MSM, a novel statistics-based scheme achieving 11-27% gains over PCA-based alternatives. Finally, ImageNet-pretrained encoders transfer effectively to TSAD, with frozen encoders retaining 92% of fine-tuned performance while training 1.8 times faster. Our code is available at: https://github.com/Smendowski/PRISM.