One-shot neural architecture search (NAS) applies weight-sharing supernet to
reduce the unaffordable computation overhead of automated architecture
designing. However, the weight-sharing technique worsens the ranking
consistency of performance due to the interferences between different candidate
networks. To address this issue, we propose a candidates enhancement method and
progressive training pipeline to improve the ranking correlation of supernet.
Specifically, we carefully redesign the sub-networks in the supernet and map
the original supernet to a new one of high capacity. In addition, we gradually
add narrow branches of supernet to reduce the degree of weight sharing which
effectively alleviates the mutual interference between sub-networks. Finally,
our method ranks the 1st place in the Supernet Track of CVPR2021 1st
Lightweight NAS Challenge.

通过重新设计超网络的子网络，逐步添加窄分支以减少权重共享的程度并提高排名相关性，可以有效减轻不同候选网络之间的相互干扰，从而提高了神经结构搜索的自动化设计效率。该方法在 CVPR2021 轻量级 NAS 挑战赛超级网络赛道中获得了第一名。