Abstract
Face images contain a wide variety of attribute information. In this paper, we propose a generalized framework for joint estimation of ordinal and nominal attributes based on information sharing. We tackle the correlation problem between heterogeneous attributes using hard parameter sharing of shallow features, and trade-off multiple loss functions by considering homoskedastic uncertainty for each attribute estimation task. This leads to optimal estimation of multiple attributes of the face and reduces the training cost of multitask learning. Experimental results on benchmarks with multiple face attributes show that the proposed approach has superior performance compared to state of the art. Finally, we discuss the bias issues arising from the proposed approach in face attribute estimation and validate its feasibility on edge systems.
Abstract (translated)
面部图像包含广泛的属性信息。在本文中，我们提出了一个基于信息共享的联合估计顺序和名义属性的通用框架。我们通过浅层特征的共享参数来解决异质属性的相关问题，并考虑每个属性估计任务的同方差不确定性，从而进行了权衡多个损失函数。这导致了对面部多个属性的最优估计，降低了多任务学习训练成本。在具有多个面部属性的基准测试上进行实验，与最先进的报道相比，所提出的方法具有卓越的性能。最后，我们讨论了从所提出的方案中产生的面部属性估计中的偏差问题，并验证了其在边缘系统上的可行性。
URL
https://arxiv.org/abs/2403.00561
