论文标题
部分可观测时空混沌系统的无模型预测
Graph Fusion Network for Multi-Oriented Object Detection
论文作者
论文摘要
在对象检测中，非最大抑制（NMS）方法被广泛采用，以删除用于生成最终对象实例的检测到的密集盒的水平重复。但是，由于密集检测框的质量下降，而不是对上下文信息的明确探索，因此通过简单的交叉联盟（IOU）指标的现有NMS方法往往在多面向和长尺寸的对象检测方面表现不佳。通过重复删除与一般NMS方法区分开来，我们提出了一个新型的图形融合网络，称为GFNET，用于多个方向的对象检测。我们的GFNET是可扩展的，并且可以自适应地融合致密检测框，以检测更准确和整体的多个方向对象实例。具体而言，我们首先采用一种局部感知的聚类算法将密集检测框分组为不同的簇。我们将为属于一个集群的检测框构建一个实例子图。然后，我们通过图形卷积网络（GCN）提出一个基于图的融合网络，以学习推理并融合用于生成最终实例框的检测框。对公共可用多面向文本数据集的广泛实验（包括MSRA-TD500，ICDAR2015，ICDAR2017-MLT）和多面向对象数据集（DOTA）验证我们对多个方向性对象检测中一般NMS方法的方法的有效性和鲁棒性。
In object detection, non-maximum suppression (NMS) methods are extensively adopted to remove horizontal duplicates of detected dense boxes for generating final object instances. However, due to the degraded quality of dense detection boxes and not explicit exploration of the context information, existing NMS methods via simple intersection-over-union (IoU) metrics tend to underperform on multi-oriented and long-size objects detection. Distinguishing with general NMS methods via duplicate removal, we propose a novel graph fusion network, named GFNet, for multi-oriented object detection. Our GFNet is extensible and adaptively fuse dense detection boxes to detect more accurate and holistic multi-oriented object instances. Specifically, we first adopt a locality-aware clustering algorithm to group dense detection boxes into different clusters. We will construct an instance sub-graph for the detection boxes belonging to one cluster. Then, we propose a graph-based fusion network via Graph Convolutional Network (GCN) to learn to reason and fuse the detection boxes for generating final instance boxes. Extensive experiments both on public available multi-oriented text datasets (including MSRA-TD500, ICDAR2015, ICDAR2017-MLT) and multi-oriented object datasets (DOTA) verify the effectiveness and robustness of our method against general NMS methods in multi-oriented object detection.
