NODIS：神经常微分场景理解
NODIS: Neural Ordinary Differential Scene Understanding
摘要：
图像语义理解是计算机视觉中一个具有挑战性的课题。它不仅需要检测图像中的所有对象，而且还需要识别它们之间的所有关系。检测到的对象，它们的标签和所发现的关系可以用于构建场景图，该场景图提供图像的抽象语义解释。在以前的作品中，关系被确定为解决一个分配问题，制定为混合线性规划。在这项工作中，我们解释，制定为常微分方程（ODE）。所提出的架构执行场景图推理，通过解决一个神经变体的ODE端到端的学习。它在所有三个基准任务上都取得了最先进的结果：场景图生成（SGGen），分类（SGCls）和视觉关系检测（PredCls）。
英文摘要：
Semantic image understanding is a challenging topic in computer vision. It requires to detect all objects in an image, but also to identify all the relations between them. Detected objects, their labels and the discovered relations can be used to construct a scene graph which provides an abstract semantic interpretation of an image. In previous works, relations were identified by solving an assignment problem formulated as Mixed-Integer Linear Programs. In this work, we interpret that formulation as Ordinary Differential Equation (ODE). The proposed architecture performs scene graph inference by solving a neural variant of an ODE by end-to-end learning. It achieves state-of-the-art results on all three benchmark tasks: scene graph generation (SGGen), classification (SGCls) and visual relationship detection (PredCls) on Visual Genome benchmark.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
