LA-Net: Landmark-Aware Learning for Reliable Facial Expression Recognition under Label Noise
This addresses label noise issues in facial expression recognition for real-world applications, representing an incremental improvement over existing methods.
The paper tackles the problem of label noise in facial expression recognition by proposing LA-Net, which uses facial landmarks to improve training supervision and feature extraction, achieving state-of-the-art performance on in-the-wild and synthetic noisy datasets.
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.