论文标题
带彩票的多端神经建筑搜索
Multi-trial Neural Architecture Search with Lottery Tickets
论文作者
论文摘要
神经体系结构搜索（NAS）在最近的图像识别任务中取得了重大进展。大多数现有的NAS方法应用受限的搜索空间，这限制了搜索模型的上限性能。为了解决这个问题，我们提出了一个名为Mobilenet3-Mt的新搜索空间。通过减少网络全面的人体知识，Mobilenet3-MT可以容纳更多的潜在候选者。为了在这个具有挑战性的搜索空间中进行搜索，我们提出了一种有效的基于多试进化的NAS方法，称为MENAS。具体而言，我们通过逐渐在人群中修剪模型来加速进化搜索过程。每种型号都经过早期停止训练，并由其彩票票取代（探索的最佳修剪网络）。通过这种方式，可以预防繁琐的网络的完整培训管道，并自动生成更有效的网络。 ImageNet-1K，CIFAR-10和CIFAR-100的广泛实验结果表明，MENA可以实现最新的性能。
Neural architecture search (NAS) has brought significant progress in recent image recognition tasks. Most existing NAS methods apply restricted search spaces, which limits the upper-bound performance of searched models. To address this issue, we propose a new search space named MobileNet3-MT. By reducing human-prior knowledge in omni dimensions of networks, MobileNet3-MT accommodates more potential candidates. For searching in this challenging search space, we present an efficient Multi-trial Evolution-based NAS method termed MENAS. Specifically, we accelerate the evolutionary search process by gradually pruning models in the population. Each model is trained with an early stop and replaced by its Lottery Tickets (the explored optimal pruned network).In this way, the full training pipeline of cumbersome networks is prevented and more efficient networks are automatically generated. Extensive experimental results on ImageNet-1K, CIFAR-10, and CIFAR-100 demonstrate that MENAS achieves state-of-the-art performance.
