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.

本文提出了 A3D, 一种自适应 3D 网络，可以在一次训练后适应各种计算约束。通过权衡网络宽度和时空分辨率，生成良好的配置，而无需像网格搜索一样训练多个模型 并且计算成本可以在部署后适应变量约束，例如在边缘设备中。在三个维度上相互训练可以显著提高自适应网络的性能。当采用多路径框架（例如 SlowFast）时，我们的自适应方法可以促进更好的路径折衷，并且在 Kinetics 数据集上的广泛实验证实了该方法的有效性，也验证了性能增益在数据集和任务之间的迁移能力。