Neural Architecture Search (NAS) has shown excellent results in designing architectures for computer vision problems. NAS alleviates the need for human-defined settings by automating architecture design and engineering. However, NAS methods tend to be slow, as they require large amounts of GPU computation. This bottleneck is mainly due to the performance estimation strategy, which requires the evaluation of the generated architectures, mainly by training them, to update the sampler method. In this paper, we propose EPE-NAS, an efficient performance estimation strategy, that mitigates the problem of evaluating networks, by scoring untrained networks and creating a correlation with their trained performance. We perform this process by looking at intra and inter-class correlations of an untrained network. We show that EPE-NAS can produce a robust correlation and that by incorporating it into a simple random sampling strategy, we are able to search for competitive networks, without requiring any training, in a matter of seconds using a single GPU. Moreover, EPE-NAS is agnostic to the search method, since it focuses on the evaluation of untrained networks, making it easy to integrate into almost any NAS method.
翻译:在设计计算机视觉问题架构方面,神经结构搜索(NAS)显示了在设计计算机视觉问题架构方面的优异结果。NAS通过建筑设计和工程自动化减轻了人类定义环境的需要。然而,NAS的方法往往缓慢,因为它们需要大量的GPU计算。这一瓶颈主要是由于绩效评估战略,该战略要求对生成的架构进行评估,主要是通过培训来更新取样器方法。在本文件中,我们建议EPE-NAS(高效的绩效评估战略)通过评分未受过训练的网络和与其训练有素的绩效建立相关性来缓解网络的评估问题。我们通过考察未受过训练的网络的内部和阶级间相互关系来开展这一过程。我们表明,EPE-NAS能够产生强有力的相关性,通过将其纳入简单的随机抽样战略,我们可以在短短的几秒内就使用单一的GPU,在不需要任何培训的情况下寻找竞争性的网络。此外,EPE-NAS(NAS)对于搜索方法来说是敏感的,因为它侧重于未受过训练的网络的评价,容易融入几乎所有NAS的方法。