Recently, neural architecture search (NAS) has been exploited to design feature pyramid networks (FPNs) and achieved promising results for visual object detection. Encouraged by the success, we propose a novel One-Shot Path Aggregation Network Architecture Search (OPANAS) algorithm, which significantly improves both searching efficiency and detection accuracy. Specifically, we first introduce six heterogeneous information paths to build our search space, namely top-down, bottom-up, fusing-splitting, scale-equalizing, skip-connect and none. Second, we propose a novel search space of FPNs, in which each FPN candidate is represented by a densely-connected directed acyclic graph (each node is a feature pyramid and each edge is one of the six heterogeneous information paths). Third, we propose an efficient one-shot search method to find the optimal path aggregation architecture, that is, we first train a super-net and then find the optimal candidate with an evolutionary algorithm. Experimental results demonstrate the efficacy of the proposed OPANAS for object detection: (1) OPANAS is more efficient than state-of-the-art methods (e.g., NAS-FPN and Auto-FPN), at significantly smaller searching cost (e.g., only 4 GPU days on MS-COCO); (2) the optimal architecture found by OPANAS significantly improves main-stream detectors including RetinaNet, Faster R-CNN and Cascade R-CNN, by 2.3-3.2 % mAP comparing to their FPN counterparts; and (3) a new state-of-the-art accuracy-speed trade-off (52.2 % mAP at 7.6 FPS) at smaller training costs than comparable state-of-the-arts. Code will be released at https://github.com/VDIGPKU/OPANAS.
翻译:最近,神经结构搜索(NAS)被用于设计金字塔网络(FPNs),并在视觉物体探测方面取得了令人乐观的成果。我们为这一成功提出一个新的新型“单点路径集成网络建筑搜索(Opanas)”算法,该算法大大提高了搜索效率和检测准确性。具体地说,我们首先引入了六条不同的信息路径来建设我们的搜索空间,即自上而下、自下而上、断裂、比例均衡、跳接连和无。第二,我们提议为FPNs提供一个新的搜索空间,其中每个FPNs候选人都使用一个紧密连接的定向周期性图表(每个节点是一个功能性金字塔,每个边缘都是六条信息路径之一 ) 。 第三,我们提出一个高效的单点搜索方法来寻找最佳路径集成结构,即自上而下、自下、自上、自上、自上、自上、自上、自上、自上、自上、自上、自上、自上、自上、自上、自上、自上、自上、自上、自上、经、自上、自上、自上、自上、自上、经、自上、自上、自、自上、自、自上、自上、自、自、自、自、自上、自、自、自、自上、自上、经、自、自、自、自、自、自、自、自、自、自、自、自、自、自、自、自、自、自、自、自、自、自、自、自、自、自、自、自、自、自、自、自、自、自、自、自、自、自、自、自、自、自、自、自、自、自、自、自、自、自、自、自、自、自、自、自、自、自、自、自、自、自、自、自、自、自、自、自、自、自、自、自、自、自、自、自、自、自、自、自、自、自、自、自、自、自、自、自、自、自、自、自、自、自、自、自、自、自、自、自、