In this paper, we propose a new neural architecture search (NAS) problem of Symmetric Positive Definite (SPD) manifold networks, aiming to automate the design of SPD neural architectures. To address this problem, we first introduce a geometrically rich and diverse SPD neural architecture search space for an efficient SPD cell design. Further, we model our new NAS problem with a one-shot training process of a single supernet. Based on the supernet modeling, we exploit a differentiable NAS algorithm on our relaxed continuous search space for SPD neural architecture search. Statistical evaluation of our method on drone, action, and emotion recognition tasks mostly provides better results than the state-of-the-art SPD networks and traditional NAS algorithms. Empirical results show that our algorithm excels in discovering better performing SPD network design and provides models that are more than three times lighter than searched by the state-of-the-art NAS algorithms.
翻译:在本文中,我们提出一个新的神经结构搜索(NAS)问题,即对正偏偏(SPD)多功能网络的问题,目的是将 SPD神经结构的设计自动化。为了解决这个问题,我们首先引入一个几何上丰富多样的 SPD神经结构搜索空间,以进行高效的 SPD 细胞设计。此外,我们用一个单一超级网的一次性培训程序来模拟我们新的NAS问题。基于超级网模型,我们利用了一种不同的NAS算法,利用了我们放松的SPD神经结构搜索连续搜索空间。我们对无人机、动作和情绪识别任务的统计评估,主要提供了比最新的SPD网络和传统的NAS算法更好的结果。经验性结果表明,我们的算法在发现更好的SPD网络设计方面表现优异,提供了比国家NAS算法所搜索的更轻三倍多的模型。