UTICA: Multi-Objective Self-Distllation Fondation Model Pretraining for Time Series Classification

Yessin Moakher, Youssef Attia El Hili, Vasilii Feofanov

Keywords: Time Series Foundation Models; Self-supervised learning; Non-contrastive learning; Self-distillation; Representation learning

Abstract: Self-supervised foundation models have achieved remarkable success across domains, including time series. However, the potential of non-contrastive methods, a paradigm that has driven significant advances in computer vision, remains underexplored for time series. In this work, we adapt DINOv2-style self-distillation to pretrain a time series foundation model, building on the Mantis tokenizer and transformer encoder architecture as our backbone. Through a student–teacher framework, our method Utica learns representations that capture both temporal invariance via augmented crops and fine-grained local structure via patch masking. Our approach achieves state-of-the-art classification performance on both UCR and UEA benchmarks. These results suggest that non-contrastive methods are a promising and complementary pretraining strategy for time series foundation models.

Track: Research Track (max 4 pages)

Submission Number: 82