论文标题
快速对象检测器搜索及以后的表示共享
Representation Sharing for Fast Object Detector Search and Beyond
论文作者
论文摘要
区域建议网络（RPN）为处理两阶段对象检测的对象变化提供了强大的支持。对于没有RPN的一阶段探测器，要有强大的子网络能够直接捕获未知大小的对象，更要求更高的要求。为了增强这种能力，我们提出了一种非常有效的神经体系结构搜索方法，即“快速而多样”（FAD），以更好地探索一阶段探测器的子网络中接受场和卷积类型的最佳配置。 FAD由设计的搜索空间和有效的体系结构搜索算法组成。搜索空间包含专门为对象检测设计的丰富的不同变换。为了应对设计的搜索空间，提出了一种新颖的搜索算法称为表示共享（repshare），以有效地确定定义转换的最佳组合。在我们的实验中，FAD对具有各种骨干的两种类型的一阶段探测器进行了显着改进。特别是，我们的FAD检测器在MS-Coco上（在单尺度测试下）达到46.4 AP，超过了最先进的检测器，包括最新的基于NAS的检测器Auto-FPN（搜索16个GPU-d日）和NAS-FCOS和NAS-FCOS和NAS-FCOS（28 GPU-DAYS）（28 GPU-DAYS），而显着降低了搜索成本为0.6 gpud days does does does does does does does does to 0.6 gpud。除了对象检测之外，我们还进一步证明了FAD在更具挑战性的实例细分中的普遍性，并期望它受益更多的任务。
Region Proposal Network (RPN) provides strong support for handling the scale variation of objects in two-stage object detection. For one-stage detectors which do not have RPN, it is more demanding to have powerful sub-networks capable of directly capturing objects of unknown sizes. To enhance such capability, we propose an extremely efficient neural architecture search method, named Fast And Diverse (FAD), to better explore the optimal configuration of receptive fields and convolution types in the sub-networks for one-stage detectors. FAD consists of a designed search space and an efficient architecture search algorithm. The search space contains a rich set of diverse transformations designed specifically for object detection. To cope with the designed search space, a novel search algorithm termed Representation Sharing (RepShare) is proposed to effectively identify the best combinations of the defined transformations. In our experiments, FAD obtains prominent improvements on two types of one-stage detectors with various backbones. In particular, our FAD detector achieves 46.4 AP on MS-COCO (under single-scale testing), outperforming the state-of-the-art detectors, including the most recent NAS-based detectors, Auto-FPN (searched for 16 GPU-days) and NAS-FCOS (28 GPU-days), while significantly reduces the search cost to 0.6 GPU-days. Beyond object detection, we further demonstrate the generality of FAD on the more challenging instance segmentation, and expect it to benefit more tasks.
