WinoTS: Wavelet-based Self-Distillation for Time Series Models

WinoTS introduces a wavelet‑based self‑distillation framework for time‑series models that uses time‑frequency augmentations to create multi‑scale structural views, avoiding distortion of signal dynamics. The method outperforms state‑of‑the‑art baselines in long‑term forecasting, cross‑domain zero‑shot transfer, and unsupervised anomaly detection, and linear probing on frozen representations often beats fully supervised training from scratch. Ablation studies show WinoTS is architecture‑agnostic and demonstrates that time‑frequency transformations offer a principled alternative to vision‑style spatial augmentations.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

• computer-vision
• efficiency
• benchmarks