Skip to yearly menu bar Skip to main content


In-Person Poster presentation / top 5% paper

SimPer: Simple Self-Supervised Learning of Periodic Targets

Yuzhe Yang · Xin Liu · Jiang Wu · Silviu Borac · Dina Katabi · Ming-Zher Poh · Daniel McDuff

MH1-2-3-4 #146

Keywords: [ Periodicity ] [ Periodic learning ] [ Periodic targets ] [ self-supervised learning ] [ representation learning ] [ Unsupervised and Self-supervised learning ]


Abstract:

From human physiology to environmental evolution, important processes in nature often exhibit meaningful and strong periodic or quasi-periodic changes. Due to their inherent label scarcity, learning useful representations for periodic tasks with limited or no supervision is of great benefit. Yet, existing self-supervised learning (SSL) methods overlook the intrinsic periodicity in data, and fail to learn representations that capture periodic or frequency attributes. In this paper, we present SimPer, a simple contrastive SSL regime for learning periodic information in data. To exploit the periodic inductive bias, SimPer introduces customized augmentations, feature similarity measures, and a generalized contrastive loss for learning efficient and robust periodic representations. Extensive experiments on common real-world tasks in human behavior analysis, environmental sensing, and healthcare domains verify the superior performance of SimPer compared to state-of-the-art SSL methods, highlighting its intriguing properties including better data efficiency, robustness to spurious correlations, and generalization to distribution shifts.

Chat is not available.