LA-Net: Landmark-Aware Learning for Reliable Facial Expression Recognition under Label Noise

TL;DR

LA-Net leverages facial landmarks to improve facial expression recognition accuracy under noisy labels by enhancing supervision and feature robustness, achieving state-of-the-art results without extra inference costs.

Contribution

Introduces LA-Net, a landmark-aware model that mitigates label noise in FER through neighborhood-based label distribution and contrastive loss with landmarks.

Findings

Outperforms existing methods on noisy FER datasets

Effectively reduces impact of label noise

Compatible with various deep neural networks

Abstract

Facial expression recognition (FER) remains a challenging task due to the ambiguity of expressions. The derived noisy labels significantly harm the performance in real-world scenarios. To address this issue, we present a new FER model named Landmark-Aware Net~(LA-Net), which leverages facial landmarks to mitigate the impact of label noise from two perspectives. Firstly, LA-Net uses landmark information to suppress the uncertainty in expression space and constructs the label distribution of each sample by neighborhood aggregation, which in turn improves the quality of training supervision. Secondly, the model incorporates landmark information into expression representations using the devised expression-landmark contrastive loss. The enhanced expression feature extractor can be less susceptible to label noise. Our method can be integrated with any deep neural network for better training supervision without introducing extra inference costs. We conduct extensive experiments on both in-the-wild datasets and synthetic noisy datasets and demonstrate that LA-Net achieves state-of-the-art performance.