Apprenticeship-Inspired Elegance: Synergistic Knowledge Distillation Empowers Spiking Neural Networks for Efficient Single-Eye Emotion Recognition

TL;DR

This paper presents a novel knowledge distillation method that enables lightweight spiking neural networks to effectively recognize emotions from single-eye videos by leveraging multimodal teacher networks, achieving high accuracy without specialized sensors.

Contribution

It introduces a synergistic knowledge distillation scheme that allows unimodal SNNs to learn from multimodal teachers for efficient emotion recognition from single-eye data.

Findings

Achieves superior accuracy over state-of-the-art methods

Demonstrates effectiveness on multiple datasets

Reduces reliance on specialized sensing devices

Abstract

We introduce a novel multimodality synergistic knowledge distillation scheme tailored for efficient single-eye motion recognition tasks. This method allows a lightweight, unimodal student spiking neural network (SNN) to extract rich knowledge from an event-frame multimodal teacher network. The core strength of this approach is its ability to utilize the ample, coarser temporal cues found in conventional frames for effective emotion recognition. Consequently, our method adeptly interprets both temporal and spatial information from the conventional frame domain, eliminating the need for specialized sensing devices, e.g., event-based camera. The effectiveness of our approach is thoroughly demonstrated using both existing and our compiled single-eye emotion recognition datasets, achieving unparalleled performance in accuracy and efficiency over existing state-of-the-art methods.