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.
@article{arxiv.2010.14535,
title = {Neural Architecture Search of SPD Manifold Networks},
author = {Rhea Sanjay Sukthanker and Zhiwu Huang and Suryansh Kumar and Erik Goron Endsjo and Yan Wu and Luc Van Gool},
journal= {arXiv preprint arXiv:2010.14535},
year = {2021}
}
Comments
This paper is accepted for publication at IJCAI 2021