---
title: "Self-Supervised Pretraining for Label-Efficient Facial Expression Recognition using Smart Glasses"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2611.05711v1"
permalink: "https://feed.astralor.com/items/itm_e20cd3e31100f3f221c5d5a1"
published: "2026-11-03T22:37:17.000Z"
score: 57
channel: "tech"
tags: ["推理效率","多模态","Self-Supervised Pretraining","Label-Efficient Facial Expression","Recognition","Smart Glasses Facial","Expression Recognition","FER"]
---

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

## 速览

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., t…

## 关键点

- 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.

## 全文

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.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_e20cd3e31100f3f221c5d5a1