提出轻量级注意力多任务模型，提升人脸属性识别精度与泛化能力
FAR-AMTN: Attention Multi-Task Network for Face Attribute Recognition
- 用共享注意力模块减少参数量，同时增强组内特征表达
- 通过跨组特征融合，挖掘属性间语义关联，提升识别准确率
- 动态权重策略促进多任务同步收敛，适合多属性联合识别场景
为提升多任务网络在人脸属性识别中的泛化性能，需高效共享多个相关任务间的相关信息。传统多任务方法采用共享低层模块和独立高层模块，导致任务增加时参数呈指数增长，且高层特征交互受限，难以探索属性间语义关系，影响泛化效果。为此，本文提出FAR-AMTN，一种面向人脸属性识别的注意力多任务网络。其引入权重共享的组特定注意力（WSGSA）模块，在保持参数量低的同时提升组内特征表示能力；设计跨组特征融合（CGFF）模块，促进不同属性组间的特征交互，增强学习效果；并采用动态权重策略（DWS），实现多任务同步收敛。在CelebA和LFWA数据集上的实验表明，FAR-AMTN在显著减少参数量的同时，实现了更优的识别精度。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。