TKFNet: Learning Texture Key Factor Driven Feature for Facial Expression Recognition

TL;DR

This work tackles in-the-wild facial expression recognition by focusing on Texture Key Driver Factors (TKDF), localized texture cues that carry strong discriminative power. It introduces TKFNet, a two-module architecture consisting of the Texture-Aware Feature Extractor (TAFE) and the Dual Contextual Information Filtering (DCIF), which jointly capture fine-grained texture information and adaptively filter contextual cues through multi-branch attention and pooling mechanisms. The method demonstrates state-of-the-art performance on RAF-DB and KDEF, validating that incorporating TKDFs into FER pipelines enhances robustness to intra-class variation and inter-class ambiguity. The approach offers practical impact for real-world emotion understanding systems by improving texture-sensitive recognition under challenging conditions.

Abstract

Facial expression recognition (FER) in the wild remains a challenging task due to the subtle and localized nature of expression-related features, as well as the complex variations in facial appearance. In this paper, we introduce a novel framework that explicitly focuses on Texture Key Driver Factors (TKDF), localized texture regions that exhibit strong discriminative power across emotional categories. By carefully observing facial image patterns, we identify that certain texture cues, such as micro-changes in skin around the brows, eyes, and mouth, serve as primary indicators of emotional dynamics. To effectively capture and leverage these cues, we propose a FER architecture comprising a Texture-Aware Feature Extractor (TAFE) and Dual Contextual Information Filtering (DCIF). TAFE employs a ResNet-based backbone enhanced with multi-branch attention to extract fine-grained texture representations, while DCIF refines these features by filtering context through adaptive pooling and attention mechanisms. Experimental results on RAF-DB and KDEF datasets demonstrate that our method achieves state-of-the-art performance, verifying the effectiveness and robustness of incorporating TKDFs into FER pipelines.

Figures (5)

• Figure 1: Challenges in FER, including arbitrary orientations, illumination and occlusion.
• Figure 2: Texture Key driven factors
• Figure 3: Pipeline of TKFNet.
• Figure 4: Samples in RAF-DB and KDEF datastes.
• Figure 5: Confusion matrix of RAF-DB and KDEF.