论文标题
特征金字塔网格
Feature Pyramid Grids
论文作者
论文摘要
特征金字塔网络已在对象检测文献中广泛采用，以改善特征表示，以更好地处理规模的变化。在本文中，我们提出了特征金字塔网格（FPG），这是一种深层多条纹特征金字塔，代表特征刻度空间作为平行自下而上途径的常规网格，并由多向侧向连接融合。 FPG可以通过在相似的计算成本下显着提高其性能，从而提高单个pathway特征金字塔网络，从而强调了深金字塔表示的重要性。除了它的一般和统一的结构外，还通过神经结构搜索发现的复杂结构，它还可以与此类方法进行比较，而无需依赖搜索。我们希望FPG具有统一和有效的性质可以成为对象识别的未来工作的强大组成部分。
Feature pyramid networks have been widely adopted in the object detection literature to improve feature representations for better handling of variations in scale. In this paper, we present Feature Pyramid Grids (FPG), a deep multi-pathway feature pyramid, that represents the feature scale-space as a regular grid of parallel bottom-up pathways which are fused by multi-directional lateral connections. FPG can improve single-pathway feature pyramid networks by significantly increasing its performance at similar computation cost, highlighting importance of deep pyramid representations. In addition to its general and uniform structure, over complicated structures that have been found with neural architecture search, it also compares favorably against such approaches without relying on search. We hope that FPG with its uniform and effective nature can serve as a strong component for future work in object recognition.
