This paper presents A3D, an adaptive 3D network that can infer at a wide range of computational constraints with one-time training. Instead of training multiple models in a grid-search manner, it generates good configurations by trading off between network width and spatio-temporal resolution. Furthermore, the computation cost can be adapted after the model is deployed to meet variable constraints, for example, on edge devices. Even under the same computational constraints, the performance of our adaptive networks can be significantly boosted over the baseline counterparts by the mutual training along three dimensions. When a multiple pathway framework, e.g. SlowFast, is adopted, our adaptive method encourages a better trade-off between pathways than manual designs. Extensive experiments on the Kinetics dataset show the effectiveness of the proposed framework. The performance gain is also verified to transfer well between datasets and tasks. Code will be made available.

翻译：本文介绍A3D,这是一个适应性3D网络,可以一次性培训,在一系列广泛的计算限制下作出推论。它不是以网格搜索方式培训多种模型,而是通过交换网络宽度和时空分辨率而产生良好的配置。此外,在模型部署后,可以调整计算成本,以适应各种制约因素,例如边缘装置等。即使在相同的计算限制下,我们的适应网络的性能也可以通过三个方面的相互培训,大大超过基线对口单位。如果采用多种路径框架,例如慢速,我们的适应方法鼓励在路径之间比手工设计更好的取舍。关于动因图数据集的广泛实验显示了拟议框架的有效性。还核实了绩效收益,以便在数据集和任务之间转移良好。将提供代码。