# Self-Supervised Pretraining for Label-Efficient Facial Expression Recognition using Smart Glasses

**Authors:** Zhengtao Gao, Francesco Bombassei De Bona, Leonardo Alchieri, Ivana Kiprijanovska, Simon Stankoski, Bojan Sofronievski, Hristijan Gjoreski, Marc Langheinrich, Martin Gjoreski  
**Lab:** Università della Svizzera italiana · **Published:** 3 Nov 2026  
**Links:** [arXiv](https://arxiv.org/abs/2611.05711) · [PDF](https://arxiv.org/pdf/2611.05711) · [This page](https://omen-bit.github.io/ai-paper-daily/paper/2611.05711.html)

## Key numbers

- **5% → 100%**: Across label budgets from 5% to 100%
- **5%**: with only 5% of the labels

## Abstract

Facial Expression Recognition (FER) on optomyographic (OMG) smart glasses such as OCOsense enables privacy-preserving, camera-free affect sensing for health and well-being. Most FER systems are fully supervised, i.e., they rely either on hand-crafted expert features with classical machine learning, or on end-to-end deep models trained from labelled data. Both depend on large quantities of labelled expressions, which are costly to collect and limit deployment in real-world, personalized settings. We investigate Self-Supervised Learning (SSL) as a route to label-efficient FER on these glasses. We pretrain a Vision Transformer with a masked-autoencoder objective on unlabelled OCOsense recordings and finetune it for five-class FER under person-independent cross-validation. Across label budgets from 5% to 100%, pretraining consistently improves performance; with only 5% of the labels, the pretrained model outperforms the from-scratch model trained with all labels. Our results show that SSL pretraining is a practical way to reduce labelling cost for smart eyewear FER, and we discuss the implications for future personalization and continual adaptation.

---

Notes written by AI from the paper, numbers copied from the abstract. Check the paper before you rely on them. From AI Papers Daily.