This repository contains the implementation code for paper:
SimPer: Simple Self-Supervised Learning of Periodic Targets
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.
We present SimPer, a simple contrastive SSL regime for learning periodic information in data. To exploit the periodic inductive bias, SimPer introduces customized periodicity-invariant and periodicity-variant augmentations, periodic feature similarity measures, and a generalized contrastive loss for learning efficient and robust periodic representations.
We benchmark SimPer on common real-world tasks in human behavior analysis, environmental sensing, and healthcare domains. Further analysis also highlights its intriguing properties including better data efficiency, robustness to spurious correlations, and generalization to distribution shifts.
- [10/06/2022] arXiv version posted. The code is currently under cleaning. Please stay tuned for updates.
@article{yang2022simper,
title={SimPer: Simple Self-Supervised Learning of Periodic Targets},
author={Yang, Yuzhe and Liu, Xin and Wu, Jiang and Borac, Silviu and Katabi, Dina and Poh, Ming-Zher and McDuff, Daniel},
journal={arXiv preprint arXiv:2210.03115},
year={2022}
}