FAR-AMTN: Attention Multi-Task Network for Face Attribute Recognition

To enhance the generalization performance of Multi-Task Networks (MTN) in Face Attribute Recognition (FAR), it is crucial to share relevant information across multiple related prediction tasks effectively. Traditional MTN methods create shared low-level modules and distinct high-level modules, causing an exponential increase in model parameters with the addition of tasks. This approach also limits feature interaction at the high level, hindering the exploration of semantic relations among attributes, thereby affecting generalization negatively. In response, this study introduces FAR-AMTN, a novel Attention Multi-Task Network for FAR. It incorporates a Weight-Shared Group-Specific Attention (WSGSA) module with shared parameters to minimize complexity while improving group feature representation. Furthermore, a Cross-Group Feature Fusion (CGFF) module is utilized to foster interactions between attribute groups, enhancing feature learning. A Dynamic Weighting Strategy (DWS) is also introduced for synchronized task convergence. Experiments on the CelebA and LFWA datasets demonstrate that the proposed FAR-AMTN demonstrates superior accuracy with significantly fewer parameters compared to existing models. • Unlike traditional tower-like Multi-Task Networks, FAR-AMTN incorporates the Weight-Shared Group-Specific Attention (WSGSA) module, utilizing shared parameters to improve group feature representation and simultaneously reduce the overall parameter count of the MTN. • FAR-AMTN facilitates feature interaction through the Cross-Group Feature Fusion (CGFF) module, enabling the exploration and utilization of the mutual relationships among group features. The Dynamic Weighting Strategy (DWS) is implemented to achieve synchronized task convergence by addressing both the gradient descent rate and the loss scale. • Testing on the CelebA and LFWA datasets has shown that FAR-AMTN not only achieves superior performance but also maintains a lower parameter count in comparison to existing multi-task learning approaches.