AGCD-Net: Attention Guided Context Debiasing Network for Emotion Recognition

TL;DR

AGCD-Net introduces a novel attention-guided causal intervention approach with a hybrid convolutional encoder to reduce context bias and improve emotion recognition accuracy in real-world scenarios.

Contribution

The paper presents AGCD-Net, combining a hybrid ConvNeXt encoder with a causal intervention module to effectively mitigate context bias in emotion recognition.

Findings

Achieves state-of-the-art results on CAER-S dataset.

Effectively reduces context bias in emotion recognition.

Demonstrates robustness in complex real-world scenarios.

Abstract

Context-aware emotion recognition (CAER) enhances affective computing in real-world scenarios, but traditional methods often suffer from context bias-spurious correlation between background context and emotion labels (e.g. associating ``garden'' with ``happy''). In this paper, we propose \textbf{AGCD-Net}, an Attention Guided Context Debiasing model that introduces \textit{Hybrid ConvNeXt}, a novel convolutional encoder that extends the ConvNeXt backbone by integrating Spatial Transformer Network and Squeeze-and-Excitation layers for enhanced feature recalibration. At the core of AGCD-Net is the Attention Guided - Causal Intervention Module (AG-CIM), which applies causal theory, perturbs context features, isolates spurious correlations, and performs an attention-driven correction guided by face features to mitigate context bias. Experimental results on the CAER-S dataset demonstrate the effectiveness of AGCD-Net, achieving state-of-the-art performance and highlighting the importance of causal debiasing for robust emotion recognition in complex settings.