论文标题
对象骨架检测的自适应线性跨度网络
Adaptive Linear Span Network for Object Skeleton Detection
论文作者
论文摘要
通常手工制作用于对象骨架检测的传统网络。尽管有效，但它们需要大量的先验知识来配置不同规模粒度的对象的代表性特征。在本文中，我们建议由神经体系结构搜索（NAS）驱动的自适应线性跨度网络（ADALSN），以自动配置和集成对象骨架检测的规模意识特征。 Adalsn是用线性跨度理论提出的，该理论为多尺度深度融合提供了最早的解释之一。通过定义混合的单元式搜索空间来实现Adalsn，该搜索空间超越了许多现有的搜索空间，它使用单位级别或金字塔级特征超越了许多现有的搜索空间。在混合空间中，我们应用遗传体系结构搜索以共同优化单位级操作和金字塔级连接，以扩展适应性空间。与最先进的情况相比，Adalsn通过实现更高的准确性和延迟权衡来证实其多功能性。它还证明了对图像对面罩任务的一般适用性，例如边缘检测和道路提取。代码可在\ href {https://github.com/sunsmarterjie/sdl-skeleton} {\ color {magenta} github.com/sunsmarterjie/sdl-skeleton}中获得。
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}.
