SLAB: A Self-supervised Label Generation Framework to Reduce Annotation Overhead
- 20 April 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Affective Computing
- Vol. PP (3) , 1-16
Abstract
Recently, many emotion-aware services have been designed to improve the user experience during online video consumption (e.g., online meeting platforms, and online tutoring mediums). These services primarily deploy a machine learning model that infers user emotion continuously based on the variation in different physiological signals . However, the major challenge to developing such models is to continuously ask the users to self-report their emotions for ground truth annotation. To address these challenges, we present SLAB (Self-supervised LABel generator), a self-supervised deep learning framework for label generation to reduce the tabular data annotation overhead. SLAB utilizes two pretext tasks coupled with a novel $log-cosh$ loss function to learn useful representations from unlabeled data that apply to the downstream task of label generation. SLAB outperforms supervised learning, semi-supervised learning, and self-supervised learning baselines such as Value Imputation and Mask Estimation (VIME) on continuous emotion annotation datasets - Continuously Annotated Signals of Emotion (CASE) and K-EmoCon. We also demonstrate the generalizability of the SLAB on a unique wheelchair surface vibration dataset (in addition to four publicly available datasets from different domains). These findings highlight that SLAB significantly reduces the annotation overhead in situations where the number of unlabeled samples vastly outnumbers labeled samples.Keywords
Funding Information
- SERB SURE-DST (SUR/2022/001965)
- SERB CRG- DST (CRG/2023/003210)
- Builder project (BT/INF/22/SP42543/2021)
This publication has 46 references indexed in Scilit:
- Domain adaptation for bias mitigation in affective computing: use cases for facial emotion recognition and sentiment analysis systemsDiscover Applied Sciences, 2025
- Pre-trained models for natural language processing: A surveyScience China Technological Sciences, 2020
- A dataset of continuous affect annotations and physiological signals for emotion analysisScientific Data, 2019
- The subjective experience of emotion: a fearful viewCurrent Opinion in Behavioral Sciences, 2018
- Multimodal Emotion Recognition Using Deep Neural Networks2017
- Active learning enabled activity recognitionPervasive and Mobile Computing, 2017
- Feedback Prediction for Blogs2013
- Efficiently Scaling up Crowdsourced Video AnnotationInternational Journal of Computer Vision, 2012
- Measuring emotion: The self-assessment manikin and the semantic differentialJournal of Behavior Therapy and Experimental Psychiatry, 1994
- A circumplex model of affect.Journal of Personality and Social Psychology, 1980