Abstract
We address the problem of learning a single model for person re-identification, attribute classification, body part segmentation, and pose estimation. With predictions for these tasks we gain a more holistic understanding of persons, which is valuable for many applications. This is a classical multi-task learning problem. However, no dataset exists that these tasks could be jointly learned from. Hence several datasets need to be combined during training, which in other contexts has often led to reduced performance in the past. We extensively evaluate how the different task and datasets influence each other and how different degrees of parameter sharing between the tasks affect performance. Our final model matches or outperforms its single-task counterparts without creating significant computational overhead, rendering it highly interesting for resource-constrained scenarios such as mobile robotics.
Abstract (translated)
我们解决的问题是学习一个单一的模型用于人的重新识别、属性分类、身体部位分割和姿势估计。通过对这些任务的预测,我们可以更全面地了解人员,这对许多应用程序都很有价值。这是一个经典的多任务学习问题。但是,不存在可以从中共同学习这些任务的数据集。因此,在培训期间需要组合几个数据集,而在其他情况下,这些数据集通常会导致过去的性能下降。我们广泛地评估不同的任务和数据集如何相互影响,以及任务之间不同程度的参数共享如何影响性能。我们的最终模型匹配或优于它的单个任务对应物,而不会产生显著的计算开销,这使得它对于资源受限的场景(如移动机器人)非常有趣。
URL
https://arxiv.org/abs/1906.03019