Online Multi-level Contrastive Representation Distillation for Cross-Subject fNIRS Emotion Recognition

TL;DR

This paper introduces OMCRD, a novel framework using multi-level contrastive learning among lightweight models to improve cross-subject emotion recognition from fNIRS signals, addressing device constraints and physiological variability.

Contribution

The paper proposes a new multi-level contrastive distillation framework for cross-subject fNIRS emotion recognition, enabling effective knowledge transfer among lightweight models.

Findings

OMCRD achieves state-of-the-art results in emotion recognition tasks.

The framework enhances cross-subject generalization in fNIRS-based emotion recognition.

Experimental results validate the effectiveness of multi-view sentimental mining.

Abstract

Utilizing functional near-infrared spectroscopy (fNIRS) signals for emotion recognition is a significant advancement in understanding human emotions. However, due to the lack of artificial intelligence data and algorithms in this field, current research faces the following challenges: 1) The portable wearable devices have higher requirements for lightweight models; 2) The objective differences of physiology and psychology among different subjects aggravate the difficulty of emotion recognition. To address these challenges, we propose a novel cross-subject fNIRS emotion recognition method, called the Online Multi-level Contrastive Representation Distillation framework (OMCRD). Specifically, OMCRD is a framework designed for mutual learning among multiple lightweight student networks. It utilizes multi-level fNIRS feature extractor for each sub-network and conducts multi-view sentimental mining using physiological signals. The proposed Inter-Subject Interaction Contrastive Representation (IS-ICR) facilitates knowledge transfer for interactions between student models, enhancing cross-subject emotion recognition performance. The optimal student network can be selected and deployed on a wearable device. Some experimental results demonstrate that OMCRD achieves state-of-the-art results in emotional perception and affective imagery tasks.