Graph Fusion Network for Multi-Oriented Object Detection
Authors:
- Shi-Xue ZhangSZShi-Xue Zhang
- Xiaobin ZhuXZXiaobin Zhu
- Jie-Bo HouJHJie-Bo Hou
- Xu-Cheng YinXYXu-Cheng Yin
Preprint
Abstract
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.Keywords
All Related Versions
This publication has 57 references indexed in Scilit:
- Context-aware co-supervision for accurate object detectionPattern Recognition, 2022
- Bottom-Up Scene Text Detection with Markov Clustering NetworksInternational Journal of Computer Vision, 2020
- Towards Multi-class Object Detection in Unconstrained Remote Sensing Imagery2019
- TextSnake: A Flexible Representation for Detecting Text of Arbitrary Shapes2018
- Accurate Scene Text Detection Through Border Semantics Awareness and Bootstrapping2018
- Deep Residual Learning for Image Recognition2016
- You Only Look Once: Unified, Real-Time Object Detection2016
- Training Region-Based Object Detectors with Online Hard Example Mining2016
- Detecting texts of arbitrary orientations in natural images2012
- Object retrieval with large vocabularies and fast spatial matching2007