Conventional networks for object skeleton detection are usually hand-crafted. Although effective, they require intensive priori knowledge to configure representative features for objects in different scale granularity.In this paper, we propose adaptive linear span network (AdaLSN), driven by neural architecture search (NAS), to automatically configure and integrate scale-aware features for object skeleton detection. AdaLSN is formulated with the theory of linear span, which provides one of the earliest explanations for multi-scale deep feature fusion. AdaLSN is materialized by defining a mixed unit-pyramid search space, which goes beyond many existing search spaces using unit-level or pyramid-level features.Within the mixed space, we apply genetic architecture search to jointly optimize unit-level operations and pyramid-level connections for adaptive feature space expansion. AdaLSN substantiates its versatility by achieving significantly higher accuracy and latency trade-off compared with state-of-the-arts. It also demonstrates general applicability to image-to-mask tasks such as edge detection and road extraction. Code is available at \href{https://github.com/sunsmarterjie/SDL-Skeleton}{\color{magenta}github.com/sunsmarterjie/SDL-Skeleton}.
翻译:用于探测物体骨骼的常规网络通常是手工制作的。虽然是有效的,但是它们需要密集的先天知识才能为不同规模颗粒的物体配置具有代表性的特征。 在本文中,我们提议在神经结构搜索(NAS)的驱动下,建立适应性的线性网(AdaLSN),以自动配置和整合用于探测物体骨骼的对称特征的对称特征。AdaLSN是用线性线性理论制定的,它提供了多种深度特征聚合的最早解释之一。AdaLSN是通过界定一个单位-金字塔搜索空间来实现的,该空间使用单位级或金字塔级的特性,超越了现有的许多搜索空间。在混合空间中,我们应用基因结构搜索,共同优化单位级操作和金字塔级连接,以进行适应性特征空间扩展。AdaLSNSN证实其多功能性,其实现的精度和耐久性交换,与最先进的特性相比,它也显示了对图像到mask的任务的一般适用性,例如边缘探测和道路提取。代码可在\href{http://gthhu_zylibub.com/smartregyrusqurgyrusqrusqurgyrusqurgyruslusluslustyrustyrgyrustyruslus/squrgyrustyrustyrustyrus.com_kirustyrustyrustyrustyrgregyrgregal_rustyrustyrus/s