The existing neural architecture search (NAS) methods usually restrict the search space to the pre-defined types of block for a fixed macro-architecture. However, this strategy will limit the search space and affect architecture flexibility if block proposal search (BPS) is not considered for NAS. As a result, block structure search is the bottleneck in many previous NAS works. In this work, we propose a new evolutionary algorithm referred to as latency EvoNAS (LEvoNAS) for block structure search, and also incorporate it to the NAS framework by developing a novel two-stage framework referred to as Block Proposal NAS (BP-NAS). Comprehensive experimental results on two computer vision tasks demonstrate the superiority of our newly proposed approach over the state-of-the-art lightweight methods. For the classification task on the ImageNet dataset, our BPN-A is better than 1.0-MobileNetV2 with similar latency, and our BPN-B saves 23.7% latency when compared with 1.4-MobileNetV2 with higher top-1 accuracy. Furthermore, for the object detection task on the COCO dataset, our method achieves significant performance improvement than MobileNetV2, which demonstrates the generalization capability of our newly proposed framework.

中文翻译：

---

块提案神经体系结构搜索

现有的神经体系结构搜索（NAS）方法通常将搜索空间限制为固定宏体系结构的预定义块类型。但是，如果不考虑对NAS使用提案建议搜索（BPS），则此策略将限制搜索空间并影响体系结构的灵活性。结果，块结构搜索是许多以前的NAS工作的瓶颈。在这项工作中，我们提出了一种新的进化算法，称为等待时间EvoNAS（LEvoNAS），用于块结构搜索，还通过开发一种称为块提议NAS（BP-NAS）的新型两阶段框架，将其纳入了NAS框架。 。在两个计算机视觉任务上的综合实验结果表明，我们最新提出的方法优于最新的轻量级方法。对于ImageNet数据集上的分类任务，与具有较高top-1准确性的1.4-MobileNetV2相比，我们的BPN-A优于1.0-MobileNetV2并具有类似的延迟，并且BPN-B节省了23.7％的延迟。此外，对于COCO数据集上的对象检测任务，我们的方法比MobileNetV2取得了显着的性能改进，这证明了我们新提出的框架的泛化能力。