论文标题
细粒的随机建筑搜索
Fine-Grained Stochastic Architecture Search
论文作者
论文摘要
最先进的深网通常太大，无法在移动设备和嵌入式系统上部署。移动神经架构搜索（NAS）方法可自动化小型型号的设计，但最先进的NAS方法运行昂贵。可区分的神经体系结构搜索（DNAS）方法降低了搜索成本，但探索了有限的候选架构子空间。在本文中，我们介绍了细粒的随机体系结构搜索（FIGS），这是一种可区分的搜索方法，可在更大的候选架构集上进行搜索。无花果通过基于逻辑 - sigmoid分布应用结构化稀疏的正则惩罚，同时选择并修改搜索空间中的运算符。我们显示了3个现有搜索空间的结果，匹配或胜过原始搜索算法并在ImageNet上产生最先进的参数效率模型（例如，具有2.60万参数的75.4％TOP-1）。使用我们的体系结构作为骨干进行对象检测，我们在可可（例如25.8 params params）上获得的地图明显高于mobilenetv3和mnasnet。
State-of-the-art deep networks are often too large to deploy on mobile devices and embedded systems. Mobile neural architecture search (NAS) methods automate the design of small models but state-of-the-art NAS methods are expensive to run. Differentiable neural architecture search (DNAS) methods reduce the search cost but explore a limited subspace of candidate architectures. In this paper, we introduce Fine-Grained Stochastic Architecture Search (FiGS), a differentiable search method that searches over a much larger set of candidate architectures. FiGS simultaneously selects and modifies operators in the search space by applying a structured sparse regularization penalty based on the Logistic-Sigmoid distribution. We show results across 3 existing search spaces, matching or outperforming the original search algorithms and producing state-of-the-art parameter-efficient models on ImageNet (e.g., 75.4% top-1 with 2.6M params). Using our architectures as backbones for object detection with SSDLite, we achieve significantly higher mAP on COCO (e.g., 25.8 with 3.0M params) than MobileNetV3 and MnasNet.
