While convolutional neural networks (CNNs) are widely used for handling spatio-temporal scenes, there exist limitations in reasoning relations among spatial features caused by their inherent structures, which have been issued consistently in many studies. In this paper, we propose Broadcasting Convolutional Networks (BCN) that allow global receptive fields to share spatial information. BCNs are simple network modules that collect effective spatial features, embed location informations and broadcast them to the entire feature maps without much additional computational cost. This method gains great improvements in feature localization problems through efficiently extending the receptive fields, and can easily be implemented within any structure of CNNs. We further utilize BCN to propose Multi-Relational Networks (multiRN) that greatly improve existing Relation Networks (RNs). In pixel-based relation reasoning problems, multiRN with BCNs implanted extends the concept of `pairwise relations' from conventional RNs to `multiple relations' by relating each object with multiple objects at once and not in pairs. This yields in O(n) complexity for n number of objects, which is a vast computational gain from RNs that take O(n^2). Through experiments, BCNs are proven for their usability on relation reasoning problems, which is due from their efficient handlings of spatial information.

本文介绍了一种名为Broadcasting Convolutional Network(BCN)的卷积网络模块，它从整个图像中提取关键对象特征，识别它们与局部特征的关系，并将其广播到整个特征图。同时，本文提出了一种名为Multi-Relational Network(multiRN)的多关系卷积网络，并利用BCN模块增强了现有关系网络(RN)，实现了良好的效果，在关系推理问题中取得了最先进的性能。

用于视觉关系推理的广播卷积网络