Masked Neural Sparse Encoder for Face Occlusion Detection

This paper presents an effective way to extract low-level features based on sparse coding for facial occlusion detection. Masked Neural Sparse Encoder (MNSE) is proposed to be a sparse coding solver that brings out better feature bases for data representation and improvement in the anomaly detection task. To guarantee the representational capability of features, a set of masks is applied to force each feature basis is heeded on learning a specific stroke within a certain area. The mask set is constructed by clustering primary strokes from training samples, and represents them with corresponding centers of clusters. Hence, these masks stand for main strokes in concerned areas with higher probabilities. Experiments show MNSE contains better representational capability in data from different domains. Compared with the standard sparse coding and the auto-encoder based approaches, MNSE lifts the accuracy up around 20%.