Cross-Age Face Recognition Using Deep Learning Model Based on Dual Attention Mechanism

Although remarkable progresses have been made in the field of face recognition, the cross-age problem is still a huge challenge. The cross-age problem is mainly reflected in the fact that in addition to the unique identity features of each person, facial features also contain age features changing during aging. To address this problem, we propose a novel cross-age face recognition framework based on dual attention mechanism which combines residual-attention mechanism and self-attention mechanism. The introduction of attention mechanism makes the model focus more on identity features, ignoring the influence of age features. Extensive experiments are conducted on two well-known face aging datasets (MORPH and CACD) to show that the proposed method achieves notable improvement over state-of-the-art algorithms.