In this study, we introduce a new family of capsule networks, deformable capsules (DeformCaps), to address a very important problem in computer vision: object detection. We propose two new algorithms associated with our DeformCaps: a novel capsule structure (SplitCaps), and a novel dynamic routing algorithm (SE-Routing), which balance computational efficiency with the need for modeling a large number of objects and classes, which have never been achieved with capsule networks before. We demonstrate that the proposed methods allow capsules to efficiently scale-up to large-scale computer vision tasks for the first time, and create the first-ever capsule network for object detection in the literature. Our proposed architecture is a one-stage detection framework and obtains results on MS COCO which are on-par with state-of-the-art one-stage CNN-based methods, while producing fewer false positive detections, generalizing to unusual poses/viewpoints of objects.
翻译:在此研究中,我们引入了新型的胶囊网络、变形胶囊(变形胶囊),以解决计算机视觉中一个非常重要的问题:物体探测。我们提出了与我们的变形胶囊相关的两种新算法:新型胶囊结构(SplitCaps)和新型动态路由算法(SE-Routing),这种算法平衡了计算效率与大量天体和类别建模的需要,而这些天体和类别以前从未与胶囊网络建模过。我们证明,拟议方法允许胶囊首次有效扩大规模,完成大规模计算机视觉任务,并创建了文献中第一层天体探测天体的胶囊网络。我们提议的结构是一个阶段性探测框架,并取得了MS COCO的结果,这种系统与最先进的单阶段CNN方法是平行的,同时产生较少的假阳性检测,将不同物体的外形/视点概括化为非常态的物体。