Self-Paced Label Distribution Learning for In-The-Wild Facial Expression Recognition

Label distribution learning (LDL) has achieved great progress in facial expression recognition (FER), where the generating label distribution is a key procedure for LDL-based FER. However, many existing researches have shown the common problem with noisy samples in FER, especially on in-the-wild datasets. This issue may lead to generating unreliable label distributions (which can be seen as label noise), and will further negatively affect the FER model. To this end, we propose a play-and-plug method of self-paced label distribution learning (SPLDL) for in-the-wild FER. Specifically, a simple yet efficient label distribution generator is adopted to generate label distributions to guide label distribution learning. We then introduce self-paced learning (SPL) paradigm and develop a novel self-paced label distribution learning strategy, which considers both classification losses and distribution losses. SPLDL first learns easy samples with reliable label distributions and gradually steps to complex ones, effectively suppressing the negative impact introduced by noisy samples and unreliable label distributions. Extensive experiments on in-the-wild FER datasets (i.e., RAF-DB and AffectNet) based on three backbone networks demonstrate the effectiveness of the proposed method.